Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank

TL;DR

The paper introduces GENSPEC, a counterfactual Learning to Rank method that adaptively balances generalization and memorization, achieving high performance and robustness across diverse query scenarios.

Contribution

The paper proposes GENSPEC, a novel algorithm that combines feature-based and tabular models using confidence bounds to optimize ranking performance per query.

Findings

GENSPEC outperforms purely feature-based models on well-data queries.

GENSPEC maintains robustness on noisy or data-scarce queries.

The approach effectively balances memorization and generalization in LTR.

Abstract

Existing work in counterfactual Learning to Rank (LTR) has focussed on optimizing feature-based models that predict the optimal ranking based on document features. LTR methods based on bandit algorithms often optimize tabular models that memorize the optimal ranking per query. These types of model have their own advantages and disadvantages. Feature-based models provide very robust performance across many queries, including those previously unseen, however, the available features often limit the rankings the model can predict. In contrast, tabular models can converge on any possible ranking through memorization. However, memorization is extremely prone to noise, which makes tabular models reliable only when large numbers of user interactions are available. Can we develop a robust counterfactual LTR method that pursues memorization-based optimization whenever it is safe to do? We introduce the Generalization and Specialization (GENSPEC) algorithm, a robust feature-based counterfactual LTR method that pursues per-query memorization when it is safe to do so. GENSPEC optimizes a single feature-based model for generalization: robust performance across all queries, and many tabular models for specialization: each optimized for high performance on a single query. GENSPEC uses novel relative high-confidence bounds to choose which model to deploy per query. By doing so, GENSPEC enjoys the high performance of successfully specialized tabular models with the robustness of a generalized feature-based model. Our results show that GENSPEC leads to optimal performance on queries with sufficient click data, while having robust behavior on queries with little or noisy data.