Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
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_ | 1866929256645263360 |
|---|---|
| author | Yang, Hantao Liu, Xutong Wang, Zhiyong Xie, Hong Lui, John C. S. Lian, Defu Chen, Enhong |
| author_facet | Yang, Hantao Liu, Xutong Wang, Zhiyong Xie, Hong Lui, John C. S. Lian, Defu Chen, Enhong |
| contents | We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users. Existing works consider either a synchronous framework, necessitating full agent participation and global synchronization, or assume user homogeneity with identical behaviors. We overcome these limitations by considering (1) federated agents operating in an asynchronous communication paradigm, where no mandatory synchronization is required and all agents communicate independently with the server, (2) heterogeneous user behaviors, where users can be stratified into $J \le |\mathcal{U}|$ latent user clusters, each exhibiting distinct preferences. For this setting, we propose a UCB-type algorithm with delicate communication protocols. Through theoretical analysis, we give sub-linear regret bounds on par with those achieved in the synchronous framework, while incurring only logarithmic communication costs. Empirical evaluation on synthetic and real-world datasets validates our algorithm's superior performance in terms of regrets and communication costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16312 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users Yang, Hantao Liu, Xutong Wang, Zhiyong Xie, Hong Lui, John C. S. Lian, Defu Chen, Enhong Machine Learning Artificial Intelligence We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users. Existing works consider either a synchronous framework, necessitating full agent participation and global synchronization, or assume user homogeneity with identical behaviors. We overcome these limitations by considering (1) federated agents operating in an asynchronous communication paradigm, where no mandatory synchronization is required and all agents communicate independently with the server, (2) heterogeneous user behaviors, where users can be stratified into $J \le |\mathcal{U}|$ latent user clusters, each exhibiting distinct preferences. For this setting, we propose a UCB-type algorithm with delicate communication protocols. Through theoretical analysis, we give sub-linear regret bounds on par with those achieved in the synchronous framework, while incurring only logarithmic communication costs. Empirical evaluation on synthetic and real-world datasets validates our algorithm's superior performance in terms of regrets and communication costs. |
| title | Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.16312 |