Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning

TL;DR

This paper introduces a data-free, class-wise contribution estimation method for federated learning that improves robustness and performance under class imbalance and heterogeneity by leveraging logit maximization without sharing raw data.

Contribution

The authors propose CELM, a novel data-free framework that estimates client contributions based on logit maximization, enhancing federated learning robustness without extra data sharing.

Findings

CELM improves model robustness to class imbalance in federated learning.

The method enhances performance without sharing raw data or auxiliary datasets.

It maintains compatibility with standard federated learning pipelines.

Abstract

Federated learning (FL) enables collaborative learning of computer vision models, where privacy and regulatory constraints prevent centralizing data across devices or organizations. However, practical FL deployments often exhibit severe class imbalance and label skew, causing standard aggregation protocols to overfit dominant clients and degrade minority-class performance. We propose a data-free, class-wise contribution estimation and aggregation framework based on logit maximization (CELM) that does not require sharing raw data, client metadata, or auxiliary public datasets. The FL server probes client updates to obtain class-wise evidence scores and assembles a cross-client evidence matrix, which quantifies both per-class competence and class coverage. Using this matrix, we compute contribution weights that upweight clients providing strong, discriminative evidence for underrepresented classes. The resulting aggregation is stable due to simplex constraints and momentum smoothing, and it remains compatible with standard FL training pipelines. We evaluate the approach on representative vision benchmarks under controlled non-IID and pathological label splits, demonstrating that CELM-based aggregation improves robustness to imbalance and statistical heterogeneity, while yielding better performance without requiring any additional data exchange.