Cascading Bandits Robust to Adversarial Corruptions

TL;DR

This paper introduces robust algorithms for cascading bandits that can withstand adversarial feedback corruptions, maintaining low regret in the presence of manipulation, which is crucial for reliable online ranking systems.

Contribution

The paper formulates the CBAC problem and proposes two algorithms that are robust to adversarial corruptions, with proven regret bounds and empirical validation.

Findings

Algorithms achieve logarithmic regret without attack.

Regret increases linearly with corruption level.

Experimental results confirm robustness.

Abstract

Online learning to rank sequentially recommends a small list of items to users from a large candidate set and receives the users' click feedback. In many real-world scenarios, users browse the recommended list in order and click the first attractive item without checking the rest. Such behaviors are usually formulated as the cascade model. Many recent works study algorithms for cascading bandits, an online learning to rank framework in the cascade model. However, the performance of existing methods may drop significantly if part of the user feedback is adversarially corrupted (e.g., click fraud). In this work, we study how to resist adversarial corruptions in cascading bandits. We first formulate the ``\textit{Cascading Bandits with Adversarial Corruptions}" (CBAC) problem, which assumes that there is an adaptive adversary that may manipulate the user feedback. Then we propose two robust algorithms for this problem, which assume the corruption level is known and agnostic, respectively. We show that both algorithms can achieve logarithmic regret when the algorithm is not under attack, and the regret increases linearly with the corruption level. The experimental results also verify the robustness of our methods.