Decoding Federated Learning: The FedNAM+ Conformal Revolution

TL;DR

FedNAM+ is a federated learning framework that combines Neural Additive Models with conformal prediction to provide interpretable, reliable uncertainty estimates and improve transparency in decentralized models.

Contribution

It introduces a novel conformal prediction method with dynamic level adjustment and gradient-based sensitivity for interpretability and uncertainty quantification in federated learning.

Findings

High prediction accuracy with minimal loss on multiple datasets

Provides visual, pixel-wise uncertainty estimates

More efficient than Monte Carlo Dropout for uncertainty estimation

Abstract

Federated learning has significantly advanced distributed training of machine learning models across decentralized data sources. However, existing frameworks often lack comprehensive solutions that combine uncertainty quantification, interpretability, and robustness. To address this, we propose FedNAM+, a federated learning framework that integrates Neural Additive Models (NAMs) with a novel conformal prediction method to enable interpretable and reliable uncertainty estimation. Our method introduces a dynamic level adjustment technique that utilizes gradient-based sensitivity maps to identify key input features influencing predictions. This facilitates both interpretability and pixel-wise uncertainty estimates. Unlike traditional interpretability methods such as LIME and SHAP, which do not provide confidence intervals, FedNAM+ offers visual insights into prediction reliability. We validate our approach through experiments on CT scan, MNIST, and CIFAR datasets, demonstrating high prediction accuracy with minimal loss (e.g., only 0.1% on MNIST), along with transparent uncertainty measures. Visual analysis highlights variable uncertainty intervals, revealing low-confidence regions where model performance can be improved with additional data. Compared to Monte Carlo Dropout, FedNAM+ delivers efficient and global uncertainty estimates with reduced computational overhead, making it particularly suitable for federated learning scenarios. Overall, FedNAM+ provides a robust, interpretable, and computationally efficient framework that enhances trust and transparency in decentralized predictive modeling.