Adapting to Fragmented and Evolving Data: A Fisher Information Perspective
This addresses robust learning under evolving data distributions for machine learning systems in dynamic settings, offering a novel approach with theoretical guarantees.
The paper tackles the problem of sequential covariate shift in dynamic environments by introducing FADE, a lightweight framework that uses Fisher information for adaptation, achieving up to 19% higher accuracy on benchmarks compared to existing methods.
Modern machine learning systems operating in dynamic environments often face \textit{sequential covariate shift} (SCS), where input distributions evolve over time while the conditional distribution remains stable. We introduce FADE (Fisher-based Adaptation to Dynamic Environments), a lightweight and theoretically grounded framework for robust learning under SCS. FADE employs a shift-aware regularization mechanism anchored in Fisher information geometry, guiding adaptation by modulating parameter updates based on sensitivity and stability. To detect significant distribution changes, we propose a Cramer-Rao-informed shift signal that integrates KL divergence with temporal Fisher dynamics. Unlike prior methods requiring task boundaries, target supervision, or experience replay, FADE operates online with fixed memory and no access to target labels. Evaluated on seven benchmarks spanning vision, language, and tabular data, FADE achieves up to 19\% higher accuracy under severe shifts, outperforming methods such as TENT and DIW. FADE also generalizes naturally to federated learning by treating heterogeneous clients as temporally fragmented environments, enabling scalable and stable adaptation in decentralized settings. Theoretical analysis guarantees bounded regret and parameter consistency, while empirical results demonstrate FADE's robustness across modalities and shift intensities.