Balancing Speed and Quality in Online Learning to Rank for Information Retrieval

Abstract

In Online Learning to Rank (OLTR) the aim is to find an optimal ranking model by interacting with users. When learning from user behavior, systems must interact with users while simultaneously learning from those interactions. Unlike other Learning to Rank (LTR) settings, existing research in this field has been limited to linear models. This is due to the speed-quality tradeoff that arises when selecting models: complex models are more expressive and can find the best rankings but need more user interactions to do so, a requirement that risks frustrating users during training. Conversely, simpler models can be optimized on fewer interactions and thus provide a better user experience, but they will converge towards suboptimal rankings. This tradeoff creates a deadlock, since novel models will not be able to improve either the user experience or the final convergence point, without sacrificing the other. Our contribution is twofold. First, we introduce a fast OLTR model called Sim-MGD that addresses the speed aspect of the speed-quality tradeoff. Sim-MGD ranks documents based on similarities with reference documents. It converges rapidly and, hence, gives a better user experience but it does not converge towards the optimal rankings. Second, we contribute Cascading Multileave Gradient Descent (C-MGD) for OLTR that directly addresses the speed-quality tradeoff by using a cascade that enables combinations of the best of two worlds: fast learning and high quality final convergence. C-MGD can provide the better user experience of Sim-MGD while maintaining the same convergence as the state-of-the-art MGD model. This opens the door for future work to design new models for OLTR without having to deal with the speed-quality tradeoff.

arXiv commentCIKM 2017, Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

References in corpus (2)

• Introducing LETOR 4.0 Datasets
• Online Learning to Rank with Feedback at the Top

Cited by in corpus (7)

• Differentiable Unbiased Online Learning to Rank
• To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions
• Variance Reduction in Gradient Exploration for Online Learning to Rank
• Efficient Exploration of Gradient Space for Online Learning to Rank
• PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer
• Learning from User Interactions with Rankings: A Unification of the Field
• Optimizing Ranking Models in an Online Setting