History-Aware and Dynamic Client Contribution in Federated Learning
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_ | 1866915458165243904 |
|---|---|
| author | Ghosh, Bishwamittra Basu, Debabrota Huazhu, Fu Yuan, Wang Kanagavelu, Renuga Peng, Jiang Jin Yong, Liu Rick, Goh Siow Mong Qingsong, Wei |
| author_facet | Ghosh, Bishwamittra Basu, Debabrota Huazhu, Fu Yuan, Wang Kanagavelu, Renuga Peng, Jiang Jin Yong, Liu Rick, Goh Siow Mong Qingsong, Wei |
| contents | Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing their private data. Fair and accurate assessment of client contributions facilitates incentive allocation in FL and encourages diverse clients to participate in a unified model training. Existing methods for contribution assessment adopts a co-operative game-theoretic concept, called Shapley value, but under restricted assumptions, e.g., all clients' participating in all epochs or at least in one epoch of FL.
We propose a history-aware client contribution assessment framework, called FLContrib, where client-participation is dynamic, i.e., a subset of clients participates in each epoch. The theoretical underpinning of FLContrib is based on the Markovian training process of FL. Under this setting, we directly apply the linearity property of Shapley value and compute a historical timeline of client contributions. Considering the possibility of a limited computational budget, we propose a two-sided fairness criteria to schedule Shapley value computation in a subset of epochs. Empirically, FLContrib is efficient and consistently accurate in estimating contribution across multiple utility functions. As a practical application, we apply FLContrib to detect dishonest clients in FL based on historical Shaplee values. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07151 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | History-Aware and Dynamic Client Contribution in Federated Learning Ghosh, Bishwamittra Basu, Debabrota Huazhu, Fu Yuan, Wang Kanagavelu, Renuga Peng, Jiang Jin Yong, Liu Rick, Goh Siow Mong Qingsong, Wei Machine Learning Artificial Intelligence Cryptography and Security Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing their private data. Fair and accurate assessment of client contributions facilitates incentive allocation in FL and encourages diverse clients to participate in a unified model training. Existing methods for contribution assessment adopts a co-operative game-theoretic concept, called Shapley value, but under restricted assumptions, e.g., all clients' participating in all epochs or at least in one epoch of FL. We propose a history-aware client contribution assessment framework, called FLContrib, where client-participation is dynamic, i.e., a subset of clients participates in each epoch. The theoretical underpinning of FLContrib is based on the Markovian training process of FL. Under this setting, we directly apply the linearity property of Shapley value and compute a historical timeline of client contributions. Considering the possibility of a limited computational budget, we propose a two-sided fairness criteria to schedule Shapley value computation in a subset of epochs. Empirically, FLContrib is efficient and consistently accurate in estimating contribution across multiple utility functions. As a practical application, we apply FLContrib to detect dishonest clients in FL based on historical Shaplee values. |
| title | History-Aware and Dynamic Client Contribution in Federated Learning |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2403.07151 |