# Closing the Generalization Gap in Parameter-efficient Federated Edge Learning

arXiv: https://arxiv.org/abs/2511.23282 · HTML: https://mlsanity.com/paper/2511.23282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [Energy Efficient Federated Learning Over Wireless Communication Networks](https://mlsanity.com/paper/1911.02417/) (2019)
- [One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis](https://mlsanity.com/paper/2001.05713/) (2020)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [Decentralized Federated Learning: A Survey and Perspective](https://mlsanity.com/paper/2306.01603/) (2023)
- [Towards Flexible Device Participation in Federated Learning](https://mlsanity.com/paper/2006.06954/) (2020)
- [Consensus Control for Decentralized Deep Learning](https://mlsanity.com/paper/2102.04828/) (2021)
- [Joint Privacy Enhancement and Quantization in Federated Learning](https://mlsanity.com/paper/2208.10888/) (2022)
- [Rethinking Resource Management in Edge Learning: A Joint Pre-training and Fine-tuning Design Paradigm](https://mlsanity.com/paper/2404.00836/) (2024)
- [FedCiR: Client-Invariant Representation Learning for Federated Non-IID Features](https://mlsanity.com/paper/2308.15786/) (2023)
- [Towards Energy Efficient Distributed Federated Learning for 6G Networks](https://mlsanity.com/paper/2201.08270/) (2022)
- [The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks](https://mlsanity.com/paper/2505.09214/) (2025)
- [Personalized Federated Learning of Probabilistic Models: A PAC-Bayesian Approach](https://mlsanity.com/paper/2401.08351/) (2024)
- [Resource-Aware Hierarchical Federated Learning in Wireless Video Caching Networks](https://mlsanity.com/paper/2402.04216/) (2024)
- [Federated Intelligence: When Large AI Models Meet Federated Fine-Tuning and Collaborative Reasoning at the Network Edge](https://mlsanity.com/paper/2503.21412/) (2025)
- [Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization](https://mlsanity.com/paper/2405.17932/) (2024)
- [AI-in-the-Loop Sensing and Communication Joint Design for Edge Intelligence](https://mlsanity.com/paper/2502.10203/) (2025)

## Abstract (arXiv)

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.