Abstract:Federated learning enables collaborative training across distributed clients with heterogeneous data, but such heterogeneity often leads to unstable updates and degraded global performance. Moreover, in practical deployments, client updates may deviate from the expected behavior not only due to benign not i.i.d. distributions, but also due to distributional shifts or anomalous inputs, raising concerns about the reliability of the aggregation process. In this work, we propose a lightweight geometric signal to quantify the functional deviation of a client with respect to the global model. Instead of comparing model parameters or gradients, our approach measures how the local training of each client alters the activation-induced partition of the input space, evaluated on a shared probe set. This yields a permutation-invariant, interpretable metric of client--global divergence that captures differences in how data is processed by the model. We show that this signal effectively identifies clients that induce atypical functional changes, distinguishing stable yet heterogeneous clients from those whose updates significantly diverge from the global regime. As a result, the proposed metric provides a simple tool for monitoring client behavior and enabling risk-aware aggregation strategies in federated learning systems.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.22266 [cs.LG] |
| (or arXiv:2605.22266v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22266 arXiv-issued DOI via DataCite (pending registration) |
From: Cristian Pérez-Corral [view email]
[v1]
Thu, 21 May 2026 10:10:38 UTC (829 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。