Circuit Collapse in Federated Learning Under Non-IID Data

Published:Dec 28, 2025 19:03
1 min read
ArXiv

Analysis

This paper provides a mechanistic understanding of why Federated Learning (FL) struggles with Non-IID data. It moves beyond simply observing performance degradation to identifying the underlying cause: the collapse of functional circuits within the neural network. This is a significant step towards developing more targeted solutions to improve FL performance in real-world scenarios where data is often Non-IID.

Reference

The paper provides the first mechanistic evidence that Non-IID data distributions cause structurally distinct local circuits to diverge, leading to their degradation in the global model.