Cheng Wang, Zheng Wang, Jianzhong Qi, Chenglu Wen, Xiaoliang Fan, Rongshan Yu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients. We first use the cosine similarity to detect gradient conflicts, and then iteratively eliminate such conflicts by modifying both the direction and the magnitude of the gradients. We further show the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions. Extensive experiments on a suite of federated datasets confirm that FedFV compares favorably against state-of-the-art methods in terms of fairness, accuracy and efficiency. The source code is available at https://github.com/WwZzz/easyFL.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.14937")
get_code_for_paper("2104.14937")
have("2104.14937")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.14937.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.14937)
Connect an agent — have() is free.