Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Shaohuai Shi
@article{DBLP:journals/corr/abs-2402-07011, author = {Zhenheng Tang and Yonggang Zhang and Shaohuai Shi and Xinmei Tian and Tongliang Liu and Bo Han and Xiaowen Chu}, title = {FedImpro: Measuring and Improving Client Update in Federated Learning}, journal = {CoRR}, volume = {abs/2402.07011}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.07011}, doi = {10.48550/ARXIV.2402.07011}, eprinttype = {arXiv}, eprint = {2402.07011}, timestamp = {Fri, 16 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-07011.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tcc/ZhangSWL23, author = {Lin Zhang and Shaohuai Shi and Wei Wang and Bo Li}, title = {Scalable {K-FAC} Training for Deep Neural Networks With Distributed Preconditioning}, journal = {{IEEE} Trans. Cloud Comput.}, volume = {11}, number = {3}, pages = {2365--2378}, year = {2023}, url = {https://doi.org/10.1109/TCC.2022.3205918}, doi = {10.1109/TCC.2022.3205918}, timestamp = {Sun, 24 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tcc/ZhangSWL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tpds/TangSLC23, author = {Zhenheng Tang and Shaohuai Shi and Bo Li and Xiaowen Chu}, title = {GossipFL: {A} Decentralized Federated Learning Framework With Sparsified and Adaptive Communication}, journal = {{IEEE} Trans. Parallel Distributed Syst.}, volume = {34}, number = {3}, pages = {909--922}, year = {2023}, url = {https://doi.org/10.1109/TPDS.2022.3230938}, doi = {10.1109/TPDS.2022.3230938}, timestamp = {Sat, 25 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tpds/TangSLC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdcs/ZhangSCWLL23, author = {Lin Zhang and Shaohuai Shi and Xiaowen Chu and Wei Wang and Bo Li and Chengjian Liu}, title = {DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining}, booktitle = {43rd {IEEE} International Conference on Distributed Computing Systems, {ICDCS} 2023, Hong Kong, July 18-21, 2023}, pages = {142--153}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICDCS57875.2023.00054}, doi = {10.1109/ICDCS57875.2023.00054}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icdcs/ZhangSCWLL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdcs/ZhangZSCL23, author = {Lin Zhang and Longteng Zhang and Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {Evaluation and Optimization of Gradient Compression for Distributed Deep Learning}, booktitle = {43rd {IEEE} International Conference on Distributed Computing Systems, {ICDCS} 2023, Hong Kong, July 18-21, 2023}, pages = {361--371}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICDCS57875.2023.00031}, doi = {10.1109/ICDCS57875.2023.00031}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icdcs/ZhangZSCL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/ZhangSL23, author = {Lin Zhang and Shaohuai Shi and Bo Li}, title = {Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/pdf?id=\_Mic8V96Voy}, timestamp = {Tue, 05 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/ZhangSL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/infocom/ShiPCL23, author = {Shaohuai Shi and Xinglin Pan and Xiaowen Chu and Bo Li}, title = {PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining}, booktitle = {{IEEE} {INFOCOM} 2023 - {IEEE} Conference on Computer Communications, New York City, NY, USA, May 17-20, 2023}, pages = {1--10}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/INFOCOM53939.2023.10228874}, doi = {10.1109/INFOCOM53939.2023.10228874}, timestamp = {Tue, 05 Sep 2023 20:33:21 +0200}, biburl = {https://dblp.org/rec/conf/infocom/ShiPCL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/infocom/ZhangSL23, author = {Lin Zhang and Shaohuai Shi and Bo Li}, title = {Accelerating Distributed {K-FAC} with Efficient Collective Communication and Scheduling}, booktitle = {{IEEE} {INFOCOM} 2023 - {IEEE} Conference on Computer Communications, New York City, NY, USA, May 17-20, 2023}, pages = {1--10}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/INFOCOM53939.2023.10228871}, doi = {10.1109/INFOCOM53939.2023.10228871}, timestamp = {Mon, 23 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/infocom/ZhangSL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-12445, author = {Lin Zhang and Shaohuai Shi and Xiaowen Chu and Wei Wang and Bo Li and Chengjian Liu}, title = {Decoupling the All-Reduce Primitive for Accelerating Distributed Deep Learning}, journal = {CoRR}, volume = {abs/2302.12445}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.12445}, doi = {10.48550/ARXIV.2302.12445}, eprinttype = {arXiv}, eprint = {2302.12445}, timestamp = {Tue, 28 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-12445.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-01778, author = {Zhenheng Tang and Xiaowen Chu and Ryan Yide Ran and Sunwoo Lee and Shaohuai Shi and Yonggang Zhang and Yuxin Wang and Alex Qiaozhong Liang and Salman Avestimehr and Chaoyang He}, title = {FedML Parrot: {A} Scalable Federated Learning System via Heterogeneity-aware Scheduling on Sequential and Hierarchical Training}, journal = {CoRR}, volume = {abs/2303.01778}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.01778}, doi = {10.48550/ARXIV.2303.01778}, eprinttype = {arXiv}, eprint = {2303.01778}, timestamp = {Mon, 06 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-01778.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-08881, author = {Lin Zhang and Longteng Zhang and Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {Evaluation and Optimization of Gradient Compression for Distributed Deep Learning}, journal = {CoRR}, volume = {abs/2306.08881}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.08881}, doi = {10.48550/ARXIV.2306.08881}, eprinttype = {arXiv}, eprint = {2306.08881}, timestamp = {Tue, 05 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-08881.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2307-01441, author = {Chen Qiu and Yulin Wu and Weixin Huang and Botao Liu and Shaohuai Shi and Xuan Wang}, title = {A Generic Multi-Player Transformation Algorithm for Solving Large-Scale Zero-Sum Extensive-Form Adversarial Team Games}, journal = {CoRR}, volume = {abs/2307.01441}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2307.01441}, doi = {10.48550/ARXIV.2307.01441}, eprinttype = {arXiv}, eprint = {2307.01441}, timestamp = {Mon, 10 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2307-01441.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-02123, author = {Lin Zhang and Shaohuai Shi and Bo Li}, title = {Eva: {A} General Vectorized Approximation Framework for Second-order Optimization}, journal = {CoRR}, volume = {abs/2308.02123}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.02123}, doi = {10.48550/ARXIV.2308.02123}, eprinttype = {arXiv}, eprint = {2308.02123}, timestamp = {Mon, 21 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-02123.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-03303, author = {Longteng Zhang and Lin Zhang and Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {LoRA-FA: Memory-efficient Low-rank Adaptation for Large Language Models Fine-tuning}, journal = {CoRR}, volume = {abs/2308.03303}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.03303}, doi = {10.48550/ARXIV.2308.03303}, eprinttype = {arXiv}, eprint = {2308.03303}, timestamp = {Tue, 05 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-03303.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-01172, author = {Zhenheng Tang and Yuxin Wang and Xin He and Longteng Zhang and Xinglin Pan and Qiang Wang and Rongfei Zeng and Kaiyong Zhao and Shaohuai Shi and Bingsheng He and Xiaowen Chu}, title = {FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs}, journal = {CoRR}, volume = {abs/2309.01172}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.01172}, doi = {10.48550/ARXIV.2309.01172}, eprinttype = {arXiv}, eprint = {2309.01172}, timestamp = {Fri, 09 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-01172.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-12670, author = {Yuxin Wang and Shaohuai Shi and Xin He and Zhenheng Tang and Xinglin Pan and Yang Zheng and Xiaoyu Wu and Amelie Chi Zhou and Bingsheng He and Xiaowen Chu}, title = {Reliable and Efficient In-Memory Fault Tolerance of Large Language Model Pretraining}, journal = {CoRR}, volume = {abs/2310.12670}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.12670}, doi = {10.48550/ARXIV.2310.12670}, eprinttype = {arXiv}, eprint = {2310.12670}, timestamp = {Fri, 09 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-12670.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-03687, author = {Longteng Zhang and Xiang Liu and Zeyu Li and Xinglin Pan and Peijie Dong and Ruibo Fan and Rui Guo and Xin Wang and Qiong Luo and Shaohuai Shi and Xiaowen Chu}, title = {Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models}, journal = {CoRR}, volume = {abs/2311.03687}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.03687}, doi = {10.48550/ARXIV.2311.03687}, eprinttype = {arXiv}, eprint = {2311.03687}, timestamp = {Wed, 29 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-03687.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eccv/WangSZC22, author = {Qiang Wang and Shaohuai Shi and Kaiyong Zhao and Xiaowen Chu}, editor = {Shai Avidan and Gabriel J. Brostow and Moustapha Ciss{\'{e}} and Giovanni Maria Farinella and Tal Hassner}, title = {EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching}, booktitle = {Computer Vision - {ECCV} 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part {XXXII}}, series = {Lecture Notes in Computer Science}, volume = {13692}, pages = {437--453}, publisher = {Springer}, year = {2022}, url = {https://doi.org/10.1007/978-3-031-19824-3\_26}, doi = {10.1007/978-3-031-19824-3\_26}, timestamp = {Sun, 29 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/eccv/WangSZC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/TangZSHH022, author = {Zhenheng Tang and Yonggang Zhang and Shaohuai Shi and Xin He and Bo Han and Xiaowen Chu}, editor = {Kamalika Chaudhuri and Stefanie Jegelka and Le Song and Csaba Szepesv{\'{a}}ri and Gang Niu and Sivan Sabato}, title = {Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning}, booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July 2022, Baltimore, Maryland, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {162}, pages = {21111--21132}, publisher = {{PMLR}}, year = {2022}, url = {https://proceedings.mlr.press/v162/tang22d.html}, timestamp = {Fri, 14 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/TangZSHH022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-09470, author = {Yang Xiang and Zhihua Wu and Weibao Gong and Siyu Ding and Xianjie Mo and Yuang Liu and Shuohuan Wang and Peng Liu and Yongshuai Hou and Long Li and Bin Wang and Shaohuai Shi and Yaqian Han and Yue Yu and Ge Li and Yu Sun and Yanjun Ma and Dianhai Yu}, title = {Nebula-I: {A} General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters}, journal = {CoRR}, volume = {abs/2205.09470}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.09470}, doi = {10.48550/ARXIV.2205.09470}, eprinttype = {arXiv}, eprint = {2205.09470}, timestamp = {Mon, 23 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-09470.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-02465, author = {Zhenheng Tang and Yonggang Zhang and Shaohuai Shi and Xin He and Bo Han and Xiaowen Chu}, title = {Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning}, journal = {CoRR}, volume = {abs/2206.02465}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.02465}, doi = {10.48550/ARXIV.2206.02465}, eprinttype = {arXiv}, eprint = {2206.02465}, timestamp = {Fri, 14 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-02465.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-15143, author = {Lin Zhang and Shaohuai Shi and Wei Wang and Bo Li}, title = {Scalable {K-FAC} Training for Deep Neural Networks with Distributed Preconditioning}, journal = {CoRR}, volume = {abs/2206.15143}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.15143}, doi = {10.48550/ARXIV.2206.15143}, eprinttype = {arXiv}, eprint = {2206.15143}, timestamp = {Mon, 04 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-15143.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2207-09796, author = {Qiang Wang and Shaohuai Shi and Kaiyong Zhao and Xiaowen Chu}, title = {EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching}, journal = {CoRR}, volume = {abs/2207.09796}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2207.09796}, doi = {10.48550/ARXIV.2207.09796}, eprinttype = {arXiv}, eprint = {2207.09796}, timestamp = {Mon, 14 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2207-09796.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-16703, author = {Shaohuai Shi and Qing Yang and Yang Xiang and Shuhan Qi and Xuan Wang}, title = {An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning}, journal = {CoRR}, volume = {abs/2211.16703}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.16703}, doi = {10.48550/ARXIV.2211.16703}, eprinttype = {arXiv}, eprint = {2211.16703}, timestamp = {Tue, 12 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-16703.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/network/ShiTCLWL21, author = {Shaohuai Shi and Zhenheng Tang and Xiaowen Chu and Chengjian Liu and Wei Wang and Bo Li}, title = {A Quantitative Survey of Communication Optimizations in Distributed Deep Learning}, journal = {{IEEE} Netw.}, volume = {35}, number = {3}, pages = {230--237}, year = {2021}, url = {https://doi.org/10.1109/MNET.011.2000530}, doi = {10.1109/MNET.011.2000530}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/network/ShiTCLWL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tpds/ShiCL21, author = {Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {{MG-WFBP:} Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning}, journal = {{IEEE} Trans. Parallel Distributed Syst.}, volume = {32}, number = {8}, pages = {1903--1917}, year = {2021}, url = {https://doi.org/10.1109/TPDS.2021.3052862}, doi = {10.1109/TPDS.2021.3052862}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tpds/ShiCL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/HeWCST0YZD21, author = {Xin He and Shihao Wang and Xiaowen Chu and Shaohuai Shi and Jiangping Tang and Xin Liu and Chenggang Yan and Jiyong Zhang and Guiguang Ding}, title = {Automated Model Design and Benchmarking of Deep Learning Models for {COVID-19} Detection with Chest {CT} Scans}, booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021}, pages = {4821--4829}, publisher = {{AAAI} Press}, year = {2021}, url = {https://doi.org/10.1609/aaai.v35i6.16614}, doi = {10.1609/AAAI.V35I6.16614}, timestamp = {Mon, 04 Sep 2023 12:29:24 +0200}, biburl = {https://dblp.org/rec/conf/aaai/HeWCST0YZD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdcs/ShiZL21, author = {Shaohuai Shi and Lin Zhang and Bo Li}, title = {Accelerating Distributed {K-FAC} with Smart Parallelism of Computing and Communication Tasks}, booktitle = {41st {IEEE} International Conference on Distributed Computing Systems, {ICDCS} 2021, Washington DC, USA, July 7-10, 2021}, pages = {550--560}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICDCS51616.2021.00059}, doi = {10.1109/ICDCS51616.2021.00059}, timestamp = {Fri, 10 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icdcs/ShiZL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/infocom/ShiCL21, author = {Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {Exploiting Simultaneous Communications to Accelerate Data Parallel Distributed Deep Learning}, booktitle = {40th {IEEE} Conference on Computer Communications, {INFOCOM} 2021, Vancouver, BC, Canada, May 10-13, 2021}, pages = {1--10}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/INFOCOM42981.2021.9488803}, doi = {10.1109/INFOCOM42981.2021.9488803}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/infocom/ShiCL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mlsys/ShiZSWZHJZGXLOZ21, author = {Shaohuai Shi and Xianhao Zhou and Shutao Song and Xingyao Wang and Zilin Zhu and Xue Huang and Xinan Jiang and Feihu Zhou and Zhenyu Guo and Liqiang Xie and Rui Lan and Xianbin Ouyang and Yan Zhang and Jieqian Wei and Jing Gong and Weiliang Lin and Ping Gao and Peng Meng and Xiaomin Xu and Chenyang Guo and Bo Yang and Zhibo Chen and Yongjian Wu and Xiaowen Chu}, editor = {Alex Smola and Alex Dimakis and Ion Stoica}, title = {Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters}, booktitle = {Proceedings of Machine Learning and Systems 2021, MLSys 2021, virtual, April 5-9, 2021}, publisher = {mlsys.org}, year = {2021}, url = {https://proceedings.mlsys.org/paper/2021/hash/8613985ec49eb8f757ae6439e879bb2a-Abstract.html}, timestamp = {Tue, 20 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/mlsys/ShiZSWZHJZGXLOZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2101-05442, author = {Xin He and Shihao Wang and Xiaowen Chu and Shaohuai Shi and Jiangping Tang and Xin Liu and Chenggang Yan and Jiyong Zhang and Guiguang Ding}, title = {Automated Model Design and Benchmarking of 3D Deep Learning Models for {COVID-19} Detection with Chest {CT} Scans}, journal = {CoRR}, volume = {abs/2101.05442}, year = {2021}, url = {https://arxiv.org/abs/2101.05442}, eprinttype = {arXiv}, eprint = {2101.05442}, timestamp = {Thu, 29 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2101-05442.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-06533, author = {Shaohuai Shi and Lin Zhang and Bo Li}, title = {Accelerating Distributed {K-FAC} with Smart Parallelism of Computing and Communication Tasks}, journal = {CoRR}, volume = {abs/2107.06533}, year = {2021}, url = {https://arxiv.org/abs/2107.06533}, eprinttype = {arXiv}, eprint = {2107.06533}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-06533.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-02582, author = {Qiang Wang and Shaohuai Shi and Shizhen Zheng and Kaiyong Zhao and Xiaowen Chu}, title = {FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks}, journal = {CoRR}, volume = {abs/2110.02582}, year = {2021}, url = {https://arxiv.org/abs/2110.02582}, eprinttype = {arXiv}, eprint = {2110.02582}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-02582.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ccgrid/WangWSHTZC20, author = {Yuxin Wang and Qiang Wang and Shaohuai Shi and Xin He and Zhenheng Tang and Kaiyong Zhao and Xiaowen Chu}, title = {Benchmarking the Performance and Energy Efficiency of {AI} Accelerators for {AI} Training}, booktitle = {20th {IEEE/ACM} International Symposium on Cluster, Cloud and Internet Computing, {CCGRID} 2020, Melbourne, Australia, May 11-14, 2020}, pages = {744--751}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/CCGrid49817.2020.00-15}, doi = {10.1109/CCGRID49817.2020.00-15}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ccgrid/WangWSHTZC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ecai/ShiT0ZC20, author = {Shaohuai Shi and Zhenheng Tang and Qiang Wang and Kaiyong Zhao and Xiaowen Chu}, editor = {Giuseppe De Giacomo and Alejandro Catal{\'{a}} and Bistra Dilkina and Michela Milano and Sen{\'{e}}n Barro and Alberto Bugar{\'{\i}}n and J{\'{e}}r{\^{o}}me Lang}, title = {Layer-Wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guarantees}, booktitle = {{ECAI} 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence {(PAIS} 2020)}, series = {Frontiers in Artificial Intelligence and Applications}, volume = {325}, pages = {1467--1474}, publisher = {{IOS} Press}, year = {2020}, url = {https://doi.org/10.3233/FAIA200253}, doi = {10.3233/FAIA200253}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ecai/ShiT0ZC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdcs/TangSC20, author = {Zhenheng Tang and Shaohuai Shi and Xiaowen Chu}, title = {Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selection}, booktitle = {40th {IEEE} International Conference on Distributed Computing Systems, {ICDCS} 2020, Singapore, November 29 - December 1, 2020}, pages = {1207--1208}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICDCS47774.2020.00153}, doi = {10.1109/ICDCS47774.2020.00153}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icdcs/TangSC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpads/ShiWC20, author = {Shaohuai Shi and Qiang Wang and Xiaowen Chu}, title = {Efficient Sparse-Dense Matrix-Matrix Multiplication on GPUs Using the Customized Sparse Storage Format}, booktitle = {26th {IEEE} International Conference on Parallel and Distributed Systems, {ICPADS} 2020, Hong Kong, December 2-4, 2020}, pages = {19--26}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICPADS51040.2020.00013}, doi = {10.1109/ICPADS51040.2020.00013}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icpads/ShiWC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/WangSZZC20, author = {Qiang Wang and Shaohuai Shi and Shizhen Zheng and Kaiyong Zhao and Xiaowen Chu}, title = {FADNet: {A} Fast and Accurate Network for Disparity Estimation}, booktitle = {2020 {IEEE} International Conference on Robotics and Automation, {ICRA} 2020, Paris, France, May 31 - August 31, 2020}, pages = {101--107}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICRA40945.2020.9197031}, doi = {10.1109/ICRA40945.2020.9197031}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/WangSZZC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/infocom/ShiWCLQLZ20, author = {Shaohuai Shi and Qiang Wang and Xiaowen Chu and Bo Li and Yang Qin and Ruihao Liu and Xinxiao Zhao}, title = {Communication-Efficient Distributed Deep Learning with Merged Gradient Sparsification on GPUs}, booktitle = {39th {IEEE} Conference on Computer Communications, {INFOCOM} 2020, Toronto, ON, Canada, July 6-9, 2020}, pages = {406--415}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/INFOCOM41043.2020.9155269}, doi = {10.1109/INFOCOM41043.2020.9155269}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/infocom/ShiWCLQLZ20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-09692, author = {Zhenheng Tang and Shaohuai Shi and Xiaowen Chu}, title = {Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selection}, journal = {CoRR}, volume = {abs/2002.09692}, year = {2020}, url = {https://arxiv.org/abs/2002.09692}, eprinttype = {arXiv}, eprint = {2002.09692}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-09692.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-10105, author = {Qiang Wang and Shaohuai Shi and Canhui Wang and Xiaowen Chu}, title = {Communication Contention Aware Scheduling of Multiple Deep Learning Training Jobs}, journal = {CoRR}, volume = {abs/2002.10105}, year = {2020}, url = {https://arxiv.org/abs/2002.10105}, eprinttype = {arXiv}, eprint = {2002.10105}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-10105.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-06307, author = {Zhenheng Tang and Shaohuai Shi and Xiaowen Chu and Wei Wang and Bo Li}, title = {Communication-Efficient Distributed Deep Learning: {A} Comprehensive Survey}, journal = {CoRR}, volume = {abs/2003.06307}, year = {2020}, url = {https://arxiv.org/abs/2003.06307}, eprinttype = {arXiv}, eprint = {2003.06307}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-06307.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-10758, author = {Qiang Wang and Shaohuai Shi and Shizhen Zheng and Kaiyong Zhao and Xiaowen Chu}, title = {FADNet: {A} Fast and Accurate Network for Disparity Estimation}, journal = {CoRR}, volume = {abs/2003.10758}, year = {2020}, url = {https://arxiv.org/abs/2003.10758}, eprinttype = {arXiv}, eprint = {2003.10758}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-10758.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-13247, author = {Shaohuai Shi and Zhenheng Tang and Xiaowen Chu and Chengjian Liu and Wei Wang and Bo Li}, title = {Communication-Efficient Distributed Deep Learning: Survey, Evaluation, and Challenges}, journal = {CoRR}, volume = {abs/2005.13247}, year = {2020}, url = {https://arxiv.org/abs/2005.13247}, eprinttype = {arXiv}, eprint = {2005.13247}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-13247.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-14469, author = {Shaohuai Shi and Qiang Wang and Xiaowen Chu}, title = {Efficient Sparse-Dense Matrix-Matrix Multiplication on GPUs Using the Customized Sparse Storage Format}, journal = {CoRR}, volume = {abs/2005.14469}, year = {2020}, url = {https://arxiv.org/abs/2005.14469}, eprinttype = {arXiv}, eprint = {2005.14469}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-14469.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-10458, author = {Shaohuai Shi and Xianhao Zhou and Shutao Song and Xingyao Wang and Zilin Zhu and Xue Huang and Xinan Jiang and Feihu Zhou and Zhenyu Guo and Liqiang Xie and Rui Lan and Xianbin Ouyang and Yan Zhang and Jieqian Wei and Jing Gong and Weiliang Lin and Ping Gao and Peng Meng and Xiaomin Xu and Chenyang Guo and Bo Yang and Zhibo Chen and Yongjian Wu and Xiaowen Chu}, title = {Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters}, journal = {CoRR}, volume = {abs/2010.10458}, year = {2020}, url = {https://arxiv.org/abs/2010.10458}, eprinttype = {arXiv}, eprint = {2010.10458}, timestamp = {Tue, 20 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-10458.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/bigdataconf/HeLWYCWSTWZDNZ19, author = {Xin He and Xiaoming Liu and Zhili Wu and Wu Yu and Xiaowen Chu and Shihao Wang and Shaohuai Shi and Zhenheng Tang and Yuxin Wang and Zhihao Zhao and Jing Dai and Ronghao Ni and Xiaofeng Zhang}, editor = {Chaitanya K. Baru and Jun Huan and Latifur Khan and Xiaohua Hu and Ronay Ak and Yuanyuan Tian and Roger S. Barga and Carlo Zaniolo and Kisung Lee and Yanfang (Fanny) Ye}, title = {Computer-Aided Clinical Skin Disease Diagnosis Using {CNN} and Object Detection Models}, booktitle = {2019 {IEEE} International Conference on Big Data {(IEEE} BigData), Los Angeles, CA, USA, December 9-12, 2019}, pages = {4839--4844}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/BigData47090.2019.9006528}, doi = {10.1109/BIGDATA47090.2019.9006528}, timestamp = {Wed, 27 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/bigdataconf/HeLWYCWSTWZDNZ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdcs/ShiWZTWHC19, author = {Shaohuai Shi and Qiang Wang and Kaiyong Zhao and Zhenheng Tang and Yuxin Wang and Xiang Huang and Xiaowen Chu}, title = {A Distributed Synchronous {SGD} Algorithm with Global Top-k Sparsification for Low Bandwidth Networks}, booktitle = {39th {IEEE} International Conference on Distributed Computing Systems, {ICDCS} 2019, Dallas, TX, USA, July 7-10, 2019}, pages = {2238--2247}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICDCS.2019.00220}, doi = {10.1109/ICDCS.2019.00220}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icdcs/ShiWZTWHC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/ShiZWTC19, author = {Shaohuai Shi and Kaiyong Zhao and Qiang Wang and Zhenheng Tang and Xiaowen Chu}, editor = {Sarit Kraus}, title = {A Convergence Analysis of Distributed {SGD} with Communication-Efficient Gradient Sparsification}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, pages = {3411--3417}, publisher = {ijcai.org}, year = {2019}, url = {https://doi.org/10.24963/ijcai.2019/473}, doi = {10.24963/IJCAI.2019/473}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/ShiZWTC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/infocom/ShiC019, author = {Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {{MG-WFBP:} Efficient Data Communication for Distributed Synchronous {SGD} Algorithms}, booktitle = {2019 {IEEE} Conference on Computer Communications, {INFOCOM} 2019, Paris, France, April 29 - May 2, 2019}, pages = {172--180}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/INFOCOM.2019.8737367}, doi = {10.1109/INFOCOM.2019.8737367}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/infocom/ShiC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1901-04359, author = {Shaohuai Shi and Qiang Wang and Kaiyong Zhao and Zhenheng Tang and Yuxin Wang and Xiang Huang and Xiaowen Chu}, title = {A Distributed Synchronous {SGD} Algorithm with Global Top-k Sparsification for Low Bandwidth Networks}, journal = {CoRR}, volume = {abs/1901.04359}, year = {2019}, url = {http://arxiv.org/abs/1901.04359}, eprinttype = {arXiv}, eprint = {1901.04359}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1901-04359.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-08705, author = {Xin He and Shihao Wang and Shaohuai Shi and Zhenheng Tang and Yuxin Wang and Zhihao Zhao and Jing Dai and Ronghao Ni and Xiaofeng Zhang and Xiaoming Liu and Zhili Wu and Wu Yu and Xiaowen Chu}, title = {Computer-Aided Clinical Skin Disease Diagnosis Using {CNN} and Object Detection Models}, journal = {CoRR}, volume = {abs/1911.08705}, year = {2019}, url = {http://arxiv.org/abs/1911.08705}, eprinttype = {arXiv}, eprint = {1911.08705}, timestamp = {Thu, 01 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-08705.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-08727, author = {Shaohuai Shi and Zhenheng Tang and Qiang Wang and Kaiyong Zhao and Xiaowen Chu}, title = {Layer-wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guarantees}, journal = {CoRR}, volume = {abs/1911.08727}, year = {2019}, url = {http://arxiv.org/abs/1911.08727}, eprinttype = {arXiv}, eprint = {1911.08727}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-08727.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-08772, author = {Shaohuai Shi and Xiaowen Chu and Ka Chun Cheung and Simon See}, title = {Understanding Top-k Sparsification in Distributed Deep Learning}, journal = {CoRR}, volume = {abs/1911.08772}, year = {2019}, url = {http://arxiv.org/abs/1911.08772}, eprinttype = {arXiv}, eprint = {1911.08772}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-08772.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-09268, author = {Shaohuai Shi and Xiaowen Chu and Bo Li}, title = {{MG-WFBP:} Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning}, journal = {CoRR}, volume = {abs/1912.09268}, year = {2019}, url = {http://arxiv.org/abs/1912.09268}, eprinttype = {arXiv}, eprint = {1912.09268}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-09268.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dasc/ShiWC18, author = {Shaohuai Shi and Qiang Wang and Xiaowen Chu}, title = {Performance Modeling and Evaluation of Distributed Deep Learning Frameworks on GPUs}, booktitle = {2018 {IEEE} 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress, DASC/PiCom/DataCom/CyberSciTech 2018, Athens, Greece, August 12-15, 2018}, pages = {949--957}, publisher = {{IEEE} Computer Society}, year = {2018}, url = {https://doi.org/10.1109/DASC/PiCom/DataCom/CyberSciTec.2018.000-4}, doi = {10.1109/DASC/PICOM/DATACOM/CYBERSCITEC.2018.000-4}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/dasc/ShiWC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpads/ShiWCL18, author = {Shaohuai Shi and Qiang Wang and Xiaowen Chu and Bo Li}, title = {A {DAG} Model of Synchronous Stochastic Gradient Descent in Distributed Deep Learning}, booktitle = {24th {IEEE} International Conference on Parallel and Distributed Systems, {ICPADS} 2018, Singapore, December 11-13, 2018}, pages = {425--432}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/PADSW.2018.8644932}, doi = {10.1109/PADSW.2018.8644932}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icpads/ShiWCL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1805-03812, author = {Shaohuai Shi and Qiang Wang and Xiaowen Chu and Bo Li}, title = {Modeling and Evaluation of Synchronous Stochastic Gradient Descent in Distributed Deep Learning on Multiple GPUs}, journal = {CoRR}, volume = {abs/1805.03812}, year = {2018}, url = {http://arxiv.org/abs/1805.03812}, eprinttype = {arXiv}, eprint = {1805.03812}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1805-03812.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1807-11205, author = {Xianyan Jia and Shutao Song and Wei He and Yangzihao Wang and Haidong Rong and Feihu Zhou and Liqiang Xie and Zhenyu Guo and Yuanzhou Yang and Liwei Yu and Tiegang Chen and Guangxiao Hu and Shaohuai Shi and Xiaowen Chu}, title = {Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes}, journal = {CoRR}, volume = {abs/1807.11205}, year = {2018}, url = {http://arxiv.org/abs/1807.11205}, eprinttype = {arXiv}, eprint = {1807.11205}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1807-11205.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-11141, author = {Shaohuai Shi and Xiaowen Chu}, title = {{MG-WFBP:} Efficient Data Communication for Distributed Synchronous {SGD} Algorithms}, journal = {CoRR}, volume = {abs/1811.11141}, year = {2018}, url = {http://arxiv.org/abs/1811.11141}, eprinttype = {arXiv}, eprint = {1811.11141}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-11141.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/bigcom/XuSC17, author = {Pengfei Xu and Shaohuai Shi and Xiaowen Chu}, title = {Performance Evaluation of Deep Learning Tools in Docker Containers}, booktitle = {3rd International Conference on Big Data Computing and Communications, {BIGCOM} 2017, Chengdu, China, August 10-11, 2017}, pages = {395--403}, publisher = {{IEEE} Computer Society}, year = {2017}, url = {https://doi.org/10.1109/BIGCOM.2017.32}, doi = {10.1109/BIGCOM.2017.32}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/bigcom/XuSC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpads/ShiXC17, author = {Shaohuai Shi and Pengfei Xu and Xiaowen Chu}, title = {Supervised Learning Based Algorithm Selection for Deep Neural Networks}, booktitle = {23rd {IEEE} International Conference on Parallel and Distributed Systems, {ICPADS} 2017, Shenzhen, China, December 15-17, 2017}, pages = {344--351}, publisher = {{IEEE} Computer Society}, year = {2017}, url = {https://doi.org/10.1109/ICPADS.2017.00053}, doi = {10.1109/ICPADS.2017.00053}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpads/ShiXC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ShiXC17, author = {Shaohuai Shi and Pengfei Xu and Xiaowen Chu}, title = {Improving the Performance of Fully Connected Neural Networks by Out-of-Place Matrix Transpose}, journal = {CoRR}, volume = {abs/1702.03192}, year = {2017}, url = {http://arxiv.org/abs/1702.03192}, eprinttype = {arXiv}, eprint = {1702.03192}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/ShiXC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ShiC17, author = {Shaohuai Shi and Xiaowen Chu}, title = {Speeding up Convolutional Neural Networks By Exploiting the Sparsity of Rectifier Units}, journal = {CoRR}, volume = {abs/1704.07724}, year = {2017}, url = {http://arxiv.org/abs/1704.07724}, eprinttype = {arXiv}, eprint = {1704.07724}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/ShiC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1711-03386, author = {Pengfei Xu and Shaohuai Shi and Xiaowen Chu}, title = {Performance Evaluation of Deep Learning Tools in Docker Containers}, journal = {CoRR}, volume = {abs/1711.03386}, year = {2017}, url = {http://arxiv.org/abs/1711.03386}, eprinttype = {arXiv}, eprint = {1711.03386}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1711-03386.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1711-05979, author = {Shaohuai Shi and Xiaowen Chu}, title = {Performance Modeling and Evaluation of Distributed Deep Learning Frameworks on GPUs}, journal = {CoRR}, volume = {abs/1711.05979}, year = {2017}, url = {http://arxiv.org/abs/1711.05979}, eprinttype = {arXiv}, eprint = {1711.05979}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1711-05979.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ccbd/ShiWXC16, author = {Shaohuai Shi and Qiang Wang and Pengfei Xu and Xiaowen Chu}, title = {Benchmarking State-of-the-Art Deep Learning Software Tools}, booktitle = {7th International Conference on Cloud Computing and Big Data, {CCBD} 2016, Macau, China, November 16-18, 2016}, pages = {99--104}, publisher = {{IEEE} Computer Society}, year = {2016}, url = {https://doi.org/10.1109/CCBD.2016.029}, doi = {10.1109/CCBD.2016.029}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ccbd/ShiWXC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ShiWXC16, author = {Shaohuai Shi and Qiang Wang and Pengfei Xu and Xiaowen Chu}, title = {Benchmarking State-of-the-Art Deep Learning Software Tools}, journal = {CoRR}, volume = {abs/1608.07249}, year = {2016}, url = {http://arxiv.org/abs/1608.07249}, eprinttype = {arXiv}, eprint = {1608.07249}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/ShiWXC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cse/QiWS11, author = {Shuhan Qi and Xuan Wang and Shaohuai Shi}, editor = {Wenyu Qu and Kai Lin and Yanming Shen and Weisong Shi and D. Frank Hsu and Xiaolong Jin and Francis C. M. Lau and Junfeng Xu}, title = {Mixed Precision Method for GPU-based {FFT}}, booktitle = {14th {IEEE} International Conference on Computational Science and Engineering, {CSE} 2011, Dalian, China, August 24-26, 2011}, pages = {580--586}, publisher = {{IEEE} Computer Society}, year = {2011}, url = {https://doi.org/10.1109/CSE.2011.103}, doi = {10.1109/CSE.2011.103}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cse/QiWS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/IEEEcit/PengCS10, author = {Jiang{-}Feng Peng and Hu Chen and Shaohuai Shi}, title = {The GPU-based String Matching System in Advanced {AC} Algorithm}, booktitle = {10th {IEEE} International Conference on Computer and Information Technology, {CIT} 2010, Bradford, West Yorkshire, UK, June 29-July 1, 2010}, pages = {1158--1163}, publisher = {{IEEE} Computer Society}, year = {2010}, url = {https://doi.org/10.1109/CIT.2010.210}, doi = {10.1109/CIT.2010.210}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/IEEEcit/PengCS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.