Understanding the Impact of Data Noise in Federated Learning: [Experiments & Analysis]
Summary: Empirical study across image, video, audio, text, and tabular FL using DataNoiseGenerator. Shows FL is more noise-sensitive than centralized learning: server aggregation amplifies divergent noisy-client updates, motivating decentralized data cleaning. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jinming Hu (University of Toronto)
- 2. Jiahao Gu (University of Toronto)
- 3. Kenta Ploch (University of Toronto)
- 4. Hao Wang (Stevens Institute of Technology)
- 5. Jingxian Wang (National University of Singapore)
- 6. Wentao Wu (Microsoft)
- 7. Qizhen Zhang (University of Toronto)
BibTeX Citation
@inproceedings{hu_sigmod26,
title = {{Understanding the Impact of Data Noise in Federated Learning: [Experiments \& Analysis]}},
author = {Hu, Jinming and Gu, Jiahao and Ploch, Kenta and Wang, Hao and Wang, Jingxian and Wu, Wentao and Zhang, Qizhen},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802124},
url = {https://dl.acm.org/doi/10.1145/3802124},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 16 of 16 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 | 8,548 | Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs | 2024 | VLDB |
| 2 | 11,280 | Federated Data Distribution Shift Estimation | 2025 | VLDB |
| 3 | 3,312 | BlindFL: Vertical Federated Machine Learning without Peeking into Your Data | 2022 | SIGMOD |
| 4 | 6,494 | Practical Differentially Private and Byzantine-resilient Federated Learning | 2023 | SIGMOD |
| 5 | 13,677 | Communication Efficient and Provable Federated Unlearning | 2024 | VLDB |
| 6 | 8,432 | FS-REAL: A Real-World Cross-Device Federated Learning Platform | 2023 | VLDB |
| 7 | 9,089 | A Blockchain System for Clustered Federated Learning with Peer-to-Peer Knowledge Transfer | 2024 | VLDB |
| 8 | 4,542 | Projected Federated Averaging with Heterogeneous Differential Privacy | 2022 | VLDB |
| 9 | 8,216 | Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation | 2024 | VLDB |
| 10 | 11,731 | FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning | 2023 | SIGMOD |