LR-XFL: Logical Reasoning-based Explainable Federated Learning

TL;DR

LR-XFL introduces a logic-based explainability framework for federated learning, enabling local rule creation and server-side rule connection without raw data access, thereby improving transparency and robustness.

Contribution

This paper presents a novel approach integrating logical reasoning into federated learning to enhance explainability and model robustness while preserving data privacy.

Findings

LR-XFL outperforms baselines in accuracy, rule fidelity, and rule accuracy.

Explicit rule evaluation allows human validation and correction.

The approach enhances transparency for sensitive applications like healthcare and finance.

Abstract

Federated learning (FL) is an emerging approach for training machine learning models collaboratively while preserving data privacy. The need for privacy protection makes it difficult for FL models to achieve global transparency and explainability. To address this limitation, we incorporate logic-based explanations into FL by proposing the Logical Reasoning-based eXplainable Federated Learning (LR-XFL) approach. Under LR-XFL, FL clients create local logic rules based on their local data and send them, along with model updates, to the FL server. The FL server connects the local logic rules through a proper logical connector that is derived based on properties of client data, without requiring access to the raw data. In addition, the server also aggregates the local model updates with weight values determined by the quality of the clients' local data as reflected by their uploaded logic rules. The results show that LR-XFL outperforms the most relevant baseline by 1.19%, 5.81% and 5.41% in terms of classification accuracy, rule accuracy and rule fidelity, respectively. The explicit rule evaluation and expression under LR-XFL enable human experts to validate and correct the rules on the server side, hence improving the global FL model's robustness to errors. It has the potential to enhance the transparency of FL models for areas like healthcare and finance where both data privacy and explainability are important.