A Plug-and-play Model-agnostic Embedding Enhancement Approach for Explainable Recommendation

2025/09/03 by Yunqi Mi, Mi, Yunqi, Yan, Boyang +6
Computer Science · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Multimodal Machine Learning Applications #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2509.03130

openalex publication_date 2025/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Existing multimedia recommender systems provide users with suggestions of media by evaluating the similarities, such as games and movies. To enhance the semantics and explainability of embeddings, it is a consensus to apply additional information (e.g., interactions, contexts, popularity). However, without systematic consideration of representativeness and value, the utility and explainability of embedding drops drastically. Hence, we introduce RVRec, a plug-and-play model-agnostic embedding enhancement approach that can improve both personality and explainability of existing systems. Specifically, we propose a probability-based embedding optimization method that uses a contrastive loss based on negative 2-Wasserstein distance to learn to enhance the representativeness of the embeddings. In addtion, we introduce a reweighing method based on multivariate Shapley values strategy to evaluate and explore the value of interactions and embeddings. Extensive experiments on multiple backbone recommenders and real-world datasets show that RVRec can improve the personalization and explainability of existing recommenders, outperforming state-of-the-art baselines.

Citations

• Explainable Session-based Recommendation via Path Reasoning
• Disentangled Graph Variational Auto-Encoder for Multimodal Recommendation with Interpretability
• PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation
• TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems
• Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
• Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation
• Reinforced Path Reasoning for Counterfactual Explainable Recommendation
• AutoField: Automating Feature Selection in Deep Recommender Systems
• Sequential Recommendation via Stochastic Self-Attention
• Near-Optimal No-Regret Learning in General Games
• Joint Shapley values: a measure of joint feature importance
• Deep Deterministic Uncertainty: A Simple Baseline
• Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
• Data Uncertainty Learning in Face Recognition
• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
• Deep Residual Learning for Image Recognition
• Matrix Factorization Techniques for Recommender Systems
• An axiomatic approach to the concept of interaction among players in cooperative games

Related

• Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems
• Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
• Embedding in Recommender Systems: A Survey
• Explainable Recommendation: Theory and Applications
• Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities