ElasticDL: A Kubernetes-native Deep Learning Framework with Fault-tolerance and Elastic Scheduling.

@inproceedings{zhou-2023-elasticdl, author = {Jun Zhou and Ke Zhang and Feng Zhu and Qitao Shi and Wenjing Fang and Lin Wang and Yi Wang}, editor = {Tat-Seng Chua and Hady Wirawan Lauw and Luo Si and Evimaria Terzi and Panayiotis Tsaparas}, title = {{ElasticDL: A Kubernetes-native Deep Learning Framework with Fault-tolerance and Elastic Scheduling}}, booktitle = {{Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, WSDM 2023, Singapore, 27 February 2023 - 3 March 2023}}, pages = {1148--1151}, publisher = {ACM}, year = {2023}, url = {https://doi.org/10.1145/3539597.3573037}, doi = {https://doi.org/10.1145/3539597.3573037} }