Closing the Generalization Gap in Parameter-efficient Federated Edge Learning

TL;DR

This paper introduces a parameter-efficient federated edge learning framework that combines model pruning and client selection, improving generalization and resource efficiency in heterogeneous, resource-constrained environments.

Contribution

It develops a novel generalization-aware optimization approach for FEEL, integrating theoretical analysis with practical system-level resource management.

Findings

Achieves superior learning performance compared to state-of-the-art baselines.

Effectively balances generalization, energy, and delay constraints.

Validates the approach through extensive experiments.

Abstract

Federated edge learning (FEEL) provides a promising foundation for edge artificial intelligence (AI) by enabling collaborative model training while preserving data privacy. However, limited and heterogeneous local datasets, as well as resource-constrained deployment, severely degrade both model generalization and resource utilization, leading to a compromised learning performance. Therefore, we propose a parameter-efficient FEEL framework that jointly leverages model pruning and client selection to tackle such challenges. First, we derive an information-theoretic generalization statement that characterizes the discrepancy between training and testing function losses and embed it into the convergence analysis. It reveals that a larger local generalization statement can undermine the global convergence. Then, we formulate a generalization-aware average squared gradient norm bound minimization problem, by jointly optimizing the pruning ratios, client selection, and communication-computation resources under energy and delay constraints. Despite its non-convexity, the resulting mixed-integer problem is efficiently solved via an alternating optimization algorithm. Extensive experiments demonstrate that the proposed design achieves superior learning performance than state-of-the-art baselines, validating the effectiveness of coupling generalization-aware analysis with system-level optimization for efficient FEEL.