
DW
Dawood Wasif, Terrence J. Moore, Chang-Tien Lu, Jin-Hee Cho
· 1 min read
ResearcharXiv cs.AI
Explainable Federated Learning via Global-Local Attribution Alignment
arXiv:2611.20445v1 Announce Type: cross
Abstract: Federated learning enables on-device training without centralizing data, yet existing systems still struggle to provide explanations that are both locally faithful and globally consistent under strict privacy and bandwidth constraints. Prior approaches either keep explanations siloed across clients, transmit heavy or sensitive artifacts, or replace expressive task models with interpretable surrogates that sacrifice accuracy. We propose xFedAlign, a model-agnostic framework that decouples task optimization in parameter space from explanation coordination in a compact group space. Each client distills a lightweight surrogate to produce private, per-class top-k attribution artifacts, which are robustly aggregated by the server into a Global Explanation Prior that softly aligns client explanations without constraining task learning. Across image, text, and tabular benchmarks with IID and non-IID partitions, xFedAlign matches FedAvg accuracy while consistently reducing explanation drift and improving deletion and insertion AUC relative to Local-XAI, FedAttr-Agg, and Fed-XAI, with only a few kilobytes of additional communication per round. Privacy and robustness evaluations further demonstrate reduced membership inference advantage and increased resistance to attribution poisoning, enabling consistent and trustworthy explanations in federated learning.
Original source
This story was published by arXiv cs.AI and written by Dawood Wasif, Terrence J. Moore, Chang-Tien Lu, Jin-Hee Cho. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


