Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916786344034304 |
|---|---|
| author | Mildner, Terje Hamelijnck, Oliver Giampouras, Paris Damoulas, Theodoros |
| author_facet | Mildner, Terje Hamelijnck, Oliver Giampouras, Paris Damoulas, Theodoros |
| contents | We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentist and Bayesian FL by providing unbiased predictions under model misspecification, with calibrated uncertainty quantification. Our approach generalises previous FL approaches, specifically Partitioned Variational Inference (Ashman et al., 2022), by allowing robust and conjugate updates, decreasing computational complexity at the clients. We offer theoretical analysis in terms of fixed-point convergence, optimality of the cavity distribution, and provable robustness to likelihood misspecification. Further, we empirically demonstrate the effectiveness of FedGVI in terms of improved robustness and predictive performance on multiple synthetic and real world classification data sets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00846 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework Mildner, Terje Hamelijnck, Oliver Giampouras, Paris Damoulas, Theodoros Machine Learning We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentist and Bayesian FL by providing unbiased predictions under model misspecification, with calibrated uncertainty quantification. Our approach generalises previous FL approaches, specifically Partitioned Variational Inference (Ashman et al., 2022), by allowing robust and conjugate updates, decreasing computational complexity at the clients. We offer theoretical analysis in terms of fixed-point convergence, optimality of the cavity distribution, and provable robustness to likelihood misspecification. Further, we empirically demonstrate the effectiveness of FedGVI in terms of improved robustness and predictive performance on multiple synthetic and real world classification data sets. |
| title | Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.00846 |