Contrastive Counterfactual Learning for Causality-aware Interpretable Recommender Systems

TL;DR

This paper introduces a contrastive counterfactual learning approach for causality-aware recommender systems, effectively reducing exposure bias and improving recommendation accuracy through novel sampling strategies.

Contribution

It proposes a new contrastive counterfactual learning method that leverages inverse propensity scores and innovative sampling to enhance causality-aware recommendations.

Findings

CCL outperforms state-of-the-art methods on real-world datasets

The proposed sampling strategies effectively reduce exposure bias

Contrastive learning improves causal interpretability in recommendations

Abstract

The field of generating recommendations within the framework of causal inference has seen a recent surge, with recommendations being likened to treatments. This approach enhances insights into the influence of recommendations on user behavior and helps in identifying the underlying factors. Existing research has often leveraged propensity scores to mitigate bias, albeit at the risk of introducing additional variance. Others have explored the use of unbiased data from randomized controlled trials, although this comes with assumptions that may prove challenging in practice. In this paper, we first present the causality-aware interpretation of recommendations and reveal how the underlying exposure mechanism can bias the maximum likelihood estimation (MLE) of observational feedback. Recognizing that confounders may be elusive, we propose a contrastive self-supervised learning to minimize exposure bias, employing inverse propensity scores and expanding the positive sample set. Building on this foundation, we present a novel contrastive counterfactual learning method (CCL) that incorporates three unique positive sampling strategies grounded in estimated exposure probability or random counterfactual samples. Through extensive experiments on two real-world datasets, we demonstrate that our CCL outperforms the state-of-the-art methods.