Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.11378 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917170746753024 |
|---|---|
| author | Li, Yawen Li, Yan Du, Junping Shao, Yingxia Liang, Meiyu Ye, Guanhua |
| author_facet | Li, Yawen Li, Yan Du, Junping Shao, Yingxia Liang, Meiyu Ye, Guanhua |
| contents | Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust. Existing approaches typically rely on centralized coordinators or trusted peer groups, limiting their applicability in open, trust-averse environments. While recent decentralized methods explore anonymous knowledge sharing, they often lack global scalability and robust mechanisms against malicious peers. To bridge this gap, we propose TPFed, a \textit{Trust-free Personalized Decentralized Federated Learning} framework. TPFed replaces central aggregators with a blockchain-based bulletin board, enabling participants to dynamically select global communication partners based on Locality-Sensitive Hashing (LSH) and peer ranking. Crucially, we introduce an ``all-in-one'' knowledge distillation protocol that simultaneously handles knowledge transfer, model quality evaluation, and similarity verification via a public reference dataset. This design ensures secure, globally personalized collaboration without exposing local models or data. Extensive experiments demonstrate that TPFed significantly outperforms traditional federated baselines in both learning accuracy and system robustness against adversarial attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11378 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trust-free Personalized Decentralized Learning Li, Yawen Li, Yan Du, Junping Shao, Yingxia Liang, Meiyu Ye, Guanhua Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust. Existing approaches typically rely on centralized coordinators or trusted peer groups, limiting their applicability in open, trust-averse environments. While recent decentralized methods explore anonymous knowledge sharing, they often lack global scalability and robust mechanisms against malicious peers. To bridge this gap, we propose TPFed, a \textit{Trust-free Personalized Decentralized Federated Learning} framework. TPFed replaces central aggregators with a blockchain-based bulletin board, enabling participants to dynamically select global communication partners based on Locality-Sensitive Hashing (LSH) and peer ranking. Crucially, we introduce an ``all-in-one'' knowledge distillation protocol that simultaneously handles knowledge transfer, model quality evaluation, and similarity verification via a public reference dataset. This design ensures secure, globally personalized collaboration without exposing local models or data. Extensive experiments demonstrate that TPFed significantly outperforms traditional federated baselines in both learning accuracy and system robustness against adversarial attacks. |
| title | Trust-free Personalized Decentralized Learning |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2410.11378 |