AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning

Xinyi Xu, Lingjuan Lyu, Xingjun Ma, Chenglin Miao, Chuan-Sheng Foo, Bryan Kian Hsiang Low

NeurIPS 2021 · Multi-agent systems and games › Games and equilibria · approach: Learning with strategic agents · 31 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use cosine-gradient-Shapley-based sparsified rewards instead of FedAvgfederated learning · MNIST 10 agents CLAaverage test accuracy (%): 53 -> 75Improved
Use cosine similarity instead of Euclidean distance for contribution (ablation)gradient reward mechanism · MNIST 10 agents CLAaverage test accuracy (%): 54 -> 75Improved
Use cosine instead of Euclidean distance (ablation)gradient reward mechanism · MNIST 10 agents CLAfairness rho: 94.54 vs 99.82 (EU higher)Hurt
Replace FedAvg with fair gradient rewardfederated learning · MNIST 10 agents UNIfairness rho: -45.60 -> 94.03Improved
Replace ECI with fair gradient rewardvalidation-based Shapley · MNIST 10 agents CLAfairness rho: 99.98 -> 94.54Hurt
Replace ECI with fair gradient rewardvalidation-based Shapley · MNIST 10 agentstime overhead (s): 11937.80 -> 4.94Improved
Increase altruism beta from 1 to 2 (ablation)fair gradient reward · CIFAR-10 10 agents CLAaverage test accuracy (%): 35 -> 36Improved
Increase altruism beta (ablation)fair gradient reward · MNIST 10 agents CLAaverage test accuracy (%): 74 -> 75 -> 73No clear effect
Increase altruism beta (ablation)fair gradient reward · training loss CLA MNISTtraining lossImproved
Use fair gradient reward instead of RRfederated learning · MR 5 agents POWaverage test accuracy (%): 63 -> 62Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy