Oct 20, 2023 · This paper presents Fed-GraB, a novel fl approach for long-tailed scenarios, which effectively addresses data imbalance and heterogeneity.
Oct 11, 2023 · This paper investigates a federated long-tailed learning (Fed-LT) task in which each client holds a locally heterogeneous dataset.
This paper investigates a federated long-tailed learning. (Fed-LT) task in which each client holds a locally heterogeneous dataset; if the datasets can be ...
Data privacy and long-tailed distribution are the norms rather than the exceptions in many real-world tasks. This paper investigates a federated long-tailed ...
This is the code for paper "Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer".
In response, we propose a method termed $\texttt{Fed-GraB}$, comprised of a Self-adjusting Gradient Balancer (SGB) module that re-weights clients' gradients in ...
Using a Self-adjusting Gradient Balancer module that re-weights clients' gradients in a closed-loop manner, based on the feedback of global long-tailed ...
本文研究了联合长尾学习（Fed-LT）任务，其中每个客户端都拥有本地异构数据集；如果数据集可以全局聚合，它们共同呈现出长尾分布。在这种情况下，现有的联合优化 ...
Dec 19, 2023 · To solve this issue, the research group came up with a method called Fed-GraB, which includes a self-regulating gradient balancer (SGB) that can ...
Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer · 1 code implementation • NeurIPS 2023 • Zikai Xiao, Zihan Chen, Songshang Liu, ...