Explainable Recommender with Geometric Information Bottleneck
This work addresses the need for more interpretable and trust-enhancing recommender systems in e-commerce, though it is incremental as it builds on existing variational methods.
The paper tackled the problem of generating explanations in recommender systems without expensive human annotations by incorporating a geometric prior from user-item interactions into a variational network, achieving comparable recommendation performance to existing content-based systems while significantly improving interpretability using Wasserstein distance.
Explainable recommender systems can explain their recommendation decisions, enhancing user trust in the systems. Most explainable recommender systems either rely on human-annotated rationales to train models for explanation generation or leverage the attention mechanism to extract important text spans from reviews as explanations. The extracted rationales are often confined to an individual review and may fail to identify the implicit features beyond the review text. To avoid the expensive human annotation process and to generate explanations beyond individual reviews, we propose to incorporate a geometric prior learnt from user-item interactions into a variational network which infers latent factors from user-item reviews. The latent factors from an individual user-item pair can be used for both recommendation and explanation generation, which naturally inherit the global characteristics encoded in the prior knowledge. Experimental results on three e-commerce datasets show that our model significantly improves the interpretability of a variational recommender using the Wasserstein distance while achieving performance comparable to existing content-based recommender systems in terms of recommendation behaviours.