Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917303002595328 |
|---|---|
| author | Park, Heewon Joe, Mugon Kim, Miru Im, Kyungjin Kwon, Minhae |
| author_facet | Park, Heewon Joe, Mugon Kim, Miru Im, Kyungjin Kwon, Minhae |
| contents | Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge is learning rate selection under client-specific, time-varying distribution shifts, where fixed learning rates often lead to underfitting or divergence. We propose Fed-ADE (Federated Adaptation with Distribution Shift Estimation), an unsupervised federated adaptation framework that leverages lightweight estimators of distribution dynamics. Specifically, Fed-ADE employs uncertainty dynamics estimation to capture changes in predictive uncertainty and representation dynamics estimation to detect covariate-level feature drift, combining them into a per-client, per-timestep adaptive learning rate. We provide theoretical analyses showing that our dynamics estimation approximates the underlying distribution shift and yields dynamic regret and convergence guarantees. Experiments on image and text benchmarks under diverse distribution shifts (label and covariate) demonstrate consistent improvements over strong baselines. These results highlight that distribution shift-aware adaptation enables effective and robust federated post-adaptation under real-world non-stationarity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01040 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift Park, Heewon Joe, Mugon Kim, Miru Im, Kyungjin Kwon, Minhae Machine Learning Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge is learning rate selection under client-specific, time-varying distribution shifts, where fixed learning rates often lead to underfitting or divergence. We propose Fed-ADE (Federated Adaptation with Distribution Shift Estimation), an unsupervised federated adaptation framework that leverages lightweight estimators of distribution dynamics. Specifically, Fed-ADE employs uncertainty dynamics estimation to capture changes in predictive uncertainty and representation dynamics estimation to detect covariate-level feature drift, combining them into a per-client, per-timestep adaptive learning rate. We provide theoretical analyses showing that our dynamics estimation approximates the underlying distribution shift and yields dynamic regret and convergence guarantees. Experiments on image and text benchmarks under diverse distribution shifts (label and covariate) demonstrate consistent improvements over strong baselines. These results highlight that distribution shift-aware adaptation enables effective and robust federated post-adaptation under real-world non-stationarity. |
| title | Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.01040 |