Towards Demystifying Serverless Machine Learning Training
Summary: Systematic study of ML training on FaaS vs IaaS; LambdaML enables fair benchmarking and optimization/synchronization options. Key result: serverless helps only for low-communication, fast-converging models; overall FaaS is faster but not cheaper than IaaS. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jiawei Jiang (ETH Zurich)
- 2. Shaoduo Gan (ETH Zurich)
- 3. Yue Liu (ETH Zurich)
- 4. Fanlin Wang (ETH Zurich)
- 5. Gustavo Alonso (ETH Zurich)
- 6. Ana Klimovic (ETH Zurich)
- 7. Ankit Singla (ETH Zurich)
- 8. Wentao Wu (Microsoft)
- 9. Ce Zhang (ETH Zurich)
BibTeX Citation
@inproceedings{jiang_sigmod21,
title = {{Towards Demystifying Serverless Machine Learning Training}},
author = {Jiang, Jiawei and Gan, Shaoduo and Liu, Yue and Wang, Fanlin and Alonso, Gustavo and Klimovic, Ana and Singla, Ankit and Wu, Wentao and Zhang, Ce},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3459240},
url = {https://dl.acm.org/doi/10.1145/3448016.3459240},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,248 | Serverless Data Science - Are We There Yet? A Case Study of Model Serving | 2022 | SIGMOD | 5.5597893e-05 |
| 8,228 | SDP_PIPE: A Semi-Decentralized Framework for Heterogeneity-aware Pipeline-parallel Training | 2023 | VLDB | 5.3581744e-05 |
| 9,196 | Optimizing Inference Serving on Serverless Platforms | 2022 | VLDB | 5.1956429e-05 |
| 10,017 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD | 5.0825892e-05 |
| 10,528 | FaaSBoard: Efficient Graph Processing with a Disaggregated Architecture on Serverless Services | 2026 | SIGMOD | 4.9605343e-05 |
| 11,368 | ArrayMorph: Optimizing Hyperslab Queries on the Cloud for Machine Learning Pipelines | 2025 | VLDB | 4.9605343e-05 |
| 11,499 | Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing | 2025 | VLDB | 4.9605343e-05 |
| 11,518 | Off-the-shelf Data Analytics on Serverless | 2024 | CIDR | 4.9605343e-05 |
| 11,945 | CDI-E: An Elastic Cloud Service for Data Engineering | 2022 | VLDB | 4.9605343e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,686 | How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study | 2024 | VLDB |
| 2 | 3,577 | A Comparison of Platforms for Implementing and Running Very Large Scale Machine Learning Algorithms | 2014 | SIGMOD |
| 3 | 10,528 | FaaSBoard: Efficient Graph Processing with a Disaggregated Architecture on Serverless Services | 2026 | SIGMOD |
| 4 | 5,097 | Releasing Cloud Databases from the Chains of Performance Prediction Models | 2017 | CIDR |
| 5 | 1,938 | Elastic Machine Learning Algorithms in Amazon SageMaker | 2020 | SIGMOD |
| 6 | 1,019 | Serverless Computing: One Step Forward, Two Steps Back | 2019 | CIDR |
| 7 | 1,716 | Lambada: Interactive Data Analytics on Cold Data Using Serverless Cloud Infrastructure | 2020 | SIGMOD |
| 8 | 9,196 | Optimizing Inference Serving on Serverless Platforms | 2022 | VLDB |
| 9 | 11,518 | Off-the-shelf Data Analytics on Serverless | 2024 | CIDR |
| 10 | 7,248 | Serverless Data Science - Are We There Yet? A Case Study of Model Serving | 2022 | SIGMOD |