cs.LGNov 16, 2026

Explainable Federated Learning via Global-Local Attribution Alignment

Authors: Dawood Wasif, Terrence J. Moore, Chang-Tien Lu, Jin-Hee Cho

Organizations: Department of Computer Science, Virginia Tech, Falls Church, VA, USA · DEVCOM Army Research Laboratory, Adelphi, MD, USA

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.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning

    Jun 30, 2026Maximilian Andreas Hoefler, Karsten Mueller, Wojciech SamekFederated LearningHeterogeneous Federated Learning

  2. Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges

    Jun 15, 2026Masoume Gholizade, Fabrizio Ruffini, Pietro Ducange +1Explainable Artificial IntelligencePrivacy-Preserving ML

  3. Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

    Sep 3, 2026Michael Khavkin, Kichang Lee, Jaeho Jin +2Differentially Private Federated LearningDifferential Privacy