FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning
Summary: FedCSS: bilevel, privacy-preserving joint client-and-sample selection for hard, informative data in FL, with meta-learning online adaptation. Convergence guarantees; outperforms baselines on five real datasets, up to 26.4% accuracy and 41.5% less communication. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Anran Li
- 2. Yue Cao
- 3. Jiabao Guo
- 4. Hongyi Peng
- 5. Qing Guo
- 6. Han Yu
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 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,643 | Camel: Managing Data for Efficient Stream Learning | 2022 | SIGMOD | 8.384956e-05 |
| 5,669 | Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy | 2022 | VLDB | 5.380575e-05 |
Previous
Page 1 / 1
Next