Explaining Latent Factor Models for Recommendation with Influence Functions
This addresses the problem of interpretability in recommendation systems for users and developers, but it is incremental as it builds on existing influence function techniques.
The paper tackled the lack of explainability in latent factor models for recommendation by proposing a fast influence analysis method (FIA) that provides neighbor-style explanations using influence functions, demonstrating correctness, efficiency, and usefulness in experiments on real datasets.
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.