Explaining Latent Factor Models for Recommendation with Influence Functions

Abstract

Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue to be resolved is the lack of explainability. Extensive efforts have been made in the literature to incorporate explainability into LFMs. However, they either rely on auxiliary information which may not be available in practice, or fail to provide easy-to-understand explanations. In this paper, we propose a fast influence analysis method named FIA, which successfully enforces explicit neighbor-style explanations to LFMs with the technique of influence functions stemmed from robust statistics. We first describe how to employ influence functions to LFMs to deliver neighbor-style explanations. Then we develop a novel influence computation algorithm for matrix factorization with high efficiency. We further extend it to the more general neural collaborative filtering and introduce an approximation algorithm to accelerate influence analysis over neural network models. Experimental results on real datasets demonstrate the correctness, efficiency and usefulness of our proposed method.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Understanding Black-box Predictions via Influence Functions
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• Learning over Knowledge-Base Embeddings for Recommendation
• Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
• Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews
• Explainable Recommendation via Multi-Task Learning in Opinionated Text Data

Cited by in corpus (8)

• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• Counterfactual Explanations for Neural Recommenders
• Recommendation Unlearning via Influence Function
• Debiased Explainable Pairwise Ranking from Implicit Feedback
• ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models
• Causal Interpretability for Machine Learning -- Problems, Methods and Evaluation
• Out-of-Distribution Generalization Analysis via Influence Function
• Hierarchical Matrix Factorization for Interpretable Collaborative Filtering