Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

By Jaspreet Singh, Avishek Anand. 2018

48 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Roberto Confalonieri
2. Benedikt Wagner
3. Ludovik Çoba
4. Tarek R. Besold
5. Jaspreet Singh
6. Avishek Anand

Citations in the corpus

• A historical perspective of explainable Artificial Intelligence (2020, methodology): “Besides, the black-box can be approximated by an interpretable version of the recommender engine, for example, association rules or similarity-based models, that can preserve high accuracy while being intrinsically interpretable (Singh & Anand, 2018).”
• EXS: Explainable Search Using Local Model Agnostic Interpretability (2018, background): “Interpreting Ranking Models Recently there has been work on global interpretability of ranking models [15] but little on explaining black box retrieval models for a given query, i.”