FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910842946060288 |
|---|---|
| author | Bornstein, Marco Bedi, Amrit Singh Mohamed, Abdirisak Huang, Furong |
| author_facet | Bornstein, Marco Bedi, Amrit Singh Mohamed, Abdirisak Huang, Furong |
| contents | Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to solve the free-rider dilemma, none have addressed the issue of truthfulness. In practice, adversarial agents can provide false information to the server in order to cheat its way out of contributing to federated training. In an effort to make free-riding-averse federated mechanisms truthful, and consequently less prone to breaking down in practice, we propose FACT. FACT is the first federated mechanism that: (1) eliminates federated free riding by using a penalty system, (2) ensures agents provide truthful information by creating a competitive environment, and (3) encourages agent participation by offering better performance than training alone. Empirically, FACT avoids free-riding when agents are untruthful, and reduces agent loss by over 4x. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13879 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding? Bornstein, Marco Bedi, Amrit Singh Mohamed, Abdirisak Huang, Furong Computer Science and Game Theory Distributed, Parallel, and Cluster Computing Machine Learning Theoretical Economics Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to solve the free-rider dilemma, none have addressed the issue of truthfulness. In practice, adversarial agents can provide false information to the server in order to cheat its way out of contributing to federated training. In an effort to make free-riding-averse federated mechanisms truthful, and consequently less prone to breaking down in practice, we propose FACT. FACT is the first federated mechanism that: (1) eliminates federated free riding by using a penalty system, (2) ensures agents provide truthful information by creating a competitive environment, and (3) encourages agent participation by offering better performance than training alone. Empirically, FACT avoids free-riding when agents are untruthful, and reduces agent loss by over 4x. |
| title | FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding? |
| topic | Computer Science and Game Theory Distributed, Parallel, and Cluster Computing Machine Learning Theoretical Economics |
| url | https://arxiv.org/abs/2405.13879 |