Aggregation on Learnable Manifolds for Asynchronous Federated Optimization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911202105360384 |
|---|---|
| author | Licudi, Archie Thakur, Anshul Molaei, Soheila Belgrave, Danielle Clifton, David |
| author_facet | Licudi, Archie Thakur, Anshul Molaei, Soheila Belgrave, Danielle Clifton, David |
| contents | Asynchronous federated learning (FL) with heterogeneous clients faces two key issues: curvature-induced loss barriers encountered by standard linear parameter interpolation techniques (e.g. FedAvg) and interference from stale updates misaligned with the server's current optimisation state. To alleviate these issues, we introduce a geometric framework that casts aggregation as curve learning in a Riemannian model space and decouples trajectory selection from update conflict resolution. Within this, we propose AsyncBezier, which replaces linear aggregation with low-degree polynomial (Bezier) trajectories to bypass loss barriers, and OrthoDC, which projects delayed updates via inner product-based orthogonality to reduce interference. We establish framework-level convergence guarantees covering each variant given simple assumptions on their components. On three datasets spanning general-purpose and healthcare domains, including LEAF Shakespeare and FEMNIST, our approach consistently improves accuracy and client fairness over strong asynchronous baselines; finally, we show that these gains are preserved even when other methods are allocated a higher local compute budget. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14396 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aggregation on Learnable Manifolds for Asynchronous Federated Optimization Licudi, Archie Thakur, Anshul Molaei, Soheila Belgrave, Danielle Clifton, David Machine Learning Asynchronous federated learning (FL) with heterogeneous clients faces two key issues: curvature-induced loss barriers encountered by standard linear parameter interpolation techniques (e.g. FedAvg) and interference from stale updates misaligned with the server's current optimisation state. To alleviate these issues, we introduce a geometric framework that casts aggregation as curve learning in a Riemannian model space and decouples trajectory selection from update conflict resolution. Within this, we propose AsyncBezier, which replaces linear aggregation with low-degree polynomial (Bezier) trajectories to bypass loss barriers, and OrthoDC, which projects delayed updates via inner product-based orthogonality to reduce interference. We establish framework-level convergence guarantees covering each variant given simple assumptions on their components. On three datasets spanning general-purpose and healthcare domains, including LEAF Shakespeare and FEMNIST, our approach consistently improves accuracy and client fairness over strong asynchronous baselines; finally, we show that these gains are preserved even when other methods are allocated a higher local compute budget. |
| title | Aggregation on Learnable Manifolds for Asynchronous Federated Optimization |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.14396 |