Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912056227135488 |
|---|---|
| author | Shin, Yujin Lee, Kichang Lee, Sungmin Choi, You Rim Kim, Hyung-Sin Ko, JeongGil |
| author_facet | Shin, Yujin Lee, Kichang Lee, Sungmin Choi, You Rim Kim, Hyung-Sin Ko, JeongGil |
| contents | While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients' resources and careful parameter aggregation to accommodate this heterogeneity. We propose HypeMeFed, a novel federated learning framework for supporting client heterogeneity by combining a multi-exit network architecture with hypernetwork-based model weight generation. This approach aligns the feature spaces of heterogeneous model layers and resolves per-layer information disparity during weight aggregation. To practically realize HypeMeFed, we also propose a low-rank factorization approach to minimize computation and memory overhead associated with hypernetworks. Our evaluations on a real-world heterogeneous device testbed indicate that \system enhances accuracy by 5.12% over FedAvg, reduces the hypernetwork memory requirements by 98.22%, and accelerates its operations by 1.86x compared to a naive hypernetwork approach. These results demonstrate HypeMeFed's effectiveness in leveraging and engaging heterogeneous clients for federated learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03086 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation Shin, Yujin Lee, Kichang Lee, Sungmin Choi, You Rim Kim, Hyung-Sin Ko, JeongGil Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients' resources and careful parameter aggregation to accommodate this heterogeneity. We propose HypeMeFed, a novel federated learning framework for supporting client heterogeneity by combining a multi-exit network architecture with hypernetwork-based model weight generation. This approach aligns the feature spaces of heterogeneous model layers and resolves per-layer information disparity during weight aggregation. To practically realize HypeMeFed, we also propose a low-rank factorization approach to minimize computation and memory overhead associated with hypernetworks. Our evaluations on a real-world heterogeneous device testbed indicate that \system enhances accuracy by 5.12% over FedAvg, reduces the hypernetwork memory requirements by 98.22%, and accelerates its operations by 1.86x compared to a naive hypernetwork approach. These results demonstrate HypeMeFed's effectiveness in leveraging and engaging heterogeneous clients for federated learning. |
| title | Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2407.03086 |