DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915414129246208 |
|---|---|
| author | Zhang, Shuaipeng Kong, Lanju Zhang, Yixin He, Wei Zheng, Yongqing Yu, Han Cui, Lizhen |
| author_facet | Zhang, Shuaipeng Kong, Lanju Zhang, Yixin He, Wei Zheng, Yongqing Yu, Han Cui, Lizhen |
| contents | Due to the distributed nature of federated learning (FL), the vulnerability of the global model and the need for coordination among many client devices pose significant challenges. As a promising decentralized, scalable and secure solution, blockchain-based FL methods have attracted widespread attention in recent years. However, traditional consensus mechanisms designed for Proof of Work (PoW) similar to blockchain incur substantial resource consumption and compromise the efficiency of FL, particularly when participating devices are wireless and resource-limited. To address asynchronous client participation and data heterogeneity in FL, while limiting the additional resource overhead introduced by blockchain, we propose the Directed Acyclic Graph-based Asynchronous Federated Learning (DAG-AFL) framework. We develop a tip selection algorithm that considers temporal freshness, node reachability and model accuracy, with a DAG-based trusted verification strategy. Extensive experiments on 3 benchmarking datasets against eight state-of-the-art approaches demonstrate that DAG-AFL significantly improves training efficiency and model accuracy by 22.7% and 6.5% on average, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20571 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning Zhang, Shuaipeng Kong, Lanju Zhang, Yixin He, Wei Zheng, Yongqing Yu, Han Cui, Lizhen Machine Learning Artificial Intelligence Due to the distributed nature of federated learning (FL), the vulnerability of the global model and the need for coordination among many client devices pose significant challenges. As a promising decentralized, scalable and secure solution, blockchain-based FL methods have attracted widespread attention in recent years. However, traditional consensus mechanisms designed for Proof of Work (PoW) similar to blockchain incur substantial resource consumption and compromise the efficiency of FL, particularly when participating devices are wireless and resource-limited. To address asynchronous client participation and data heterogeneity in FL, while limiting the additional resource overhead introduced by blockchain, we propose the Directed Acyclic Graph-based Asynchronous Federated Learning (DAG-AFL) framework. We develop a tip selection algorithm that considers temporal freshness, node reachability and model accuracy, with a DAG-based trusted verification strategy. Extensive experiments on 3 benchmarking datasets against eight state-of-the-art approaches demonstrate that DAG-AFL significantly improves training efficiency and model accuracy by 22.7% and 6.5% on average, respectively. |
| title | DAG-AFL:Directed Acyclic Graph-based Asynchronous Federated Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.20571 |