Personalized Interpretation on Federated Learning: A Virtual Concepts approach

TL;DR

This paper introduces a novel federated learning approach that interprets non-IID client data as mixtures of conceptual vectors, enhancing both interpretability and robustness in personalized FL systems.

Contribution

It proposes a virtual concepts-based method to interpret and personalize non-IID data in federated learning, combining interpretability with robustness.

Findings

Validated on benchmark datasets showing improved robustness.

Enhanced interpretability of client-specific data distributions.

Demonstrated effectiveness in handling non-IID data.

Abstract

Tackling non-IID data is an open challenge in federated learning research. Existing FL methods, including robust FL and personalized FL, are designed to improve model performance without consideration of interpreting non-IID across clients. This paper aims to design a novel FL method to robust and interpret the non-IID data across clients. Specifically, we interpret each client's dataset as a mixture of conceptual vectors that each one represents an interpretable concept to end-users. These conceptual vectors could be pre-defined or refined in a human-in-the-loop process or be learnt via the optimization procedure of the federated learning system. In addition to the interpretability, the clarity of client-specific personalization could also be applied to enhance the robustness of the training process on FL system. The effectiveness of the proposed method have been validated on benchmark datasets.