Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning

2025/07/08 by Samuel Ofosu Mensah, Mensah, Samuel Ofosu, Kerol Djoumessi +3
Computer Science · Medicine · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data #Retinal Imaging and Analysis

paper · pdf · doi:10.48550/arxiv.2507.05852

openalex publication_date 2025/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources while maintaining privacy. Nevertheless, real-world FL often faces major challenges including communication overhead during the transfer of large model parameters and statistical heterogeneity, arising from non-identical independent data distributions across clients. In this work, we propose an FL framework that 1) provides inherent interpretations using prototypes, and 2) tackles statistical heterogeneity by utilising lightweight adapter modules to act as compressed surrogates of local models and guide clients to achieve generalisation despite varying client distribution. Each client locally refines its model by aligning class embeddings toward prototype representations and simultaneously adjust the lightweight adapter. Our approach replaces the need to communicate entire model weights with prototypes and lightweight adapters. This design ensures that each client's model aligns with a globally shared structure while minimising communication load and providing inherent interpretations. Moreover, we conducted our experiments on a real-world retinal fundus image dataset, which provides clinical-site information. We demonstrate inherent interpretable capabilities and perform a classification task, which shows improvements in accuracy over baseline algorithms.

Citations

• FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging
• Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition
• FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning
• FedAdapter: Efficient Federated Learning for Modern NLP
• FedProto: Federated Prototype Learning across Heterogeneous Clients
• Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
• The future of digital health with federated learning
• Think Locally, Act Globally: Federated Learning with Local and Global Representations
• Federated Learning: Challenges, Methods, and Future Directions
• Federated Optimization in Heterogeneous Networks
• Prototypical Networks for Few-shot Learning
• Deep Residual Learning for Image Recognition
• Adam: A Method for Stochastic Optimization

Related

• Prototype Helps Federated Learning: Towards Faster Convergence
• Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency
• FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation
• Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
• Seamless Integration: Sampling Strategies in Federated Learning Systems