[month] [year]

ACML-24

Dr. Sujit Prakash Gujar and his students Sambhav Solanki and Shweta Jain presented a paper on Fairness and Privacy Guarantees in Federated Contextual Bandits at the proceedings of the 16th Asian Conference of Machine Learning 2024 (ACML-24) held in Hanoi, Vietnam from 5 to 8 December.

Here is the summary of their research as explained by the authors:

This paper considers the contextual multi-armed bandit (CMAB) problem with fairness and privacy guarantees in a federated environment. We consider merit-based exposure as the desired fair outcome, which provides exposure to each action in proportion to the reward associated. We model the algorithm’s effectiveness using fairness regret, which captures the difference between fair optimal policy and the policy output by the algorithm. Applying a fair CMAB algorithm to each agent individually leads to fairness regret linear in the number of agents. We propose that collaborative — federated learning can be more effective and provide the algorithm Fed-FairX-LinUCB that also ensures differential privacy. The primary challenge in extending the existing privacy framework is designing the communication protocol for communicating required information across agents. A naive protocol can either lead to weaker privacy guarantees or higher regret. We design a novel communication protocol that allows for (i) Sub-linear theoretical bounds on fairness regret for Fed-FairX-LinUCB and comparable bounds for the private counterpart, Priv-FairX-LinUCB (relative to single-agent learning), (ii) Effective use of privacy budget in Priv-FairX-LinUCB. We demonstrate the efficacy of our proposed algorithm with extensive simulations-based experiments. We show that both Fed-FairX-LinUCB and Priv-FairX-LinUCB achieve near-optimal fairness regret.

Conference page: https://www.acml-conf.org/2024/

December 2024