Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

TL;DR

This paper explores post-hoc interpretability of learning-to-rank models by training interpretable secondary models on labels from complex rankers, demonstrating that faithful explanations are possible under certain conditions.

Contribution

It introduces a method to explain black-box ranking models using secondary interpretable models trained on their outputs, advancing model transparency in ranking tasks.

Findings

Interpretable models can faithfully approximate complex rankers.

The effectiveness depends on training size and algorithm choice.

Post-hoc explanations are feasible with secondary training data.

Abstract

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency. Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models. In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner. We operate on the notion of interpretability based on explainability of rankings over an interpretable feature space. Furthermore we train a tree based model (inherently interpretable) using labels from the ranker, called secondary training data to provide explanations. Consequently, we attempt to study how well does a subset of features, potentially interpretable, explain the full model under different training sizes and algorithms. We do experiments on the learning to rank datasets with 30k queries and report results that serve show in certain settings we can learn a faithful interpretable ranker.