Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
This addresses the challenge of debiasing learning in recommendations for systems where RCTs are impractical, though it appears incremental as it builds on existing information bottleneck methods.
The paper tackles the problem of counterfactual learning from missing-not-at-random feedback in recommender systems without requiring expensive randomized controlled trials, and shows that their CVIB method significantly enhances both shallow and deep models on real-world datasets.
Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems. Missing-at-random (MAR) data, namely randomized controlled trials (RCTs), are usually required by most previous counterfactual learning methods for debiasing learning. However, the execution of RCTs is extraordinarily expensive in practice. To circumvent the use of RCTs, we build an information-theoretic counterfactual variational information bottleneck (CVIB), as an alternative for debiasing learning without RCTs. By separating the task-aware mutual information term in the original information bottleneck Lagrangian into factual and counterfactual parts, we derive a contrastive information loss and an additional output confidence penalty, which facilitates balanced learning between the factual and counterfactual domains. Empirical evaluation on real-world datasets shows that our CVIB significantly enhances both shallow and deep models, which sheds light on counterfactual learning in recommendation that goes beyond RCTs.