Performing Interpretability Analysis in Federated Learning Context
Keywords: Federated Learning, Interpretability, Neural Additive Models, Optimization
TL;DR: Performing Interpretability Analysis in Federated Learning Context
Abstract: Federated learning continues to evolve but faces challenges in interpretability and explainability. We introduce a creative approach employing Neural Additive Models (NAMs) within a federated learning framework to address these challenges. These models referred to as Federated Neural Additive Models (FedNAMs), merge the advantages of NAMs, where individual networks concentrate on specific input features, with the decentralized approach of federated learning, ultimately producing interpretable analysis results. This integration enhances privacy by training on local data across multiple devices, thereby minimizing the risks of data centralization and enhancing model robustness and generalizability. FedNAMs maintain detailed feature-specific learning, making them especially valuable in sectors like finance and healthcare. They facilitate training client-specific models that integrate local updates, preserving privacy and reducing centralization concerns. Our studies on various text and image classification tasks, using datasets such as OpenFetch ML Wine, UCI Heart Disease, and Iris, show that FedNAMs deliver strong interpretability with minimal accuracy loss compared to traditional Federated Deep Neural Networks (DNNs). The research involves notable findings, including the identification of key predictive features at the client level as well as at the global level. Volatile acidity, sulfates, and chlorides for wine quality. Chest pain type, maximum heart rate, and number of vessels for heart disease. Petal length and width for iris classification. This approach strengthens privacy and model efficiency and improves interpretability and robustness across diverse datasets. Finally, FedNAMs generate insights on causes of highly and low interpretable features.
Primary Area: interpretability and explainable AI
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8339
Loading