Learning Neural Ranking Models Online from Implicit User Feedback

TL;DR

This paper introduces an online learning to rank method using neural models trained from implicit user feedback, effectively capturing non-linear query-document relations and balancing exploration and exploitation.

Contribution

It presents the first neural OL2R approach with theoretical regret bounds and demonstrates superior performance over existing linear models.

Findings

Achieves $O( ext{log}^2 T)$ regret bound.

Outperforms state-of-the-art OL2R baselines.

Effectively balances exploration and exploitation.

Abstract

Existing online learning to rank (OL2R) solutions are limited to linear models, which are incompetent to capture possible non-linear relations between queries and documents. In this work, to unleash the power of representation learning in OL2R, we propose to directly learn a neural ranking model from users' implicit feedback (e.g., clicks) collected on the fly. We focus on RankNet and LambdaRank, due to their great empirical success and wide adoption in offline settings, and control the notorious explore-exploit trade-off based on the convergence analysis of neural networks using neural tangent kernel. Specifically, in each round of result serving, exploration is only performed on document pairs where the predicted rank order between the two documents is uncertain; otherwise, the ranker's predicted order will be followed in result ranking. We prove that under standard assumptions our OL2R solution achieves a gap-dependent upper regret bound of $O(\log^2(T))$, in which the regret is defined on the total number of mis-ordered pairs over $T$ rounds. Comparisons against an extensive set of state-of-the-art OL2R baselines on two public learning to rank benchmark datasets demonstrate the effectiveness of the proposed solution.