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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mi, Yunqi, Yan, Boyang, Zhao, Guoshuai, Shen, Jialie, Qian, Xueming
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915477608988672
author Mi, Yunqi
Yan, Boyang
Zhao, Guoshuai
Shen, Jialie
Qian, Xueming
author_facet Mi, Yunqi
Yan, Boyang
Zhao, Guoshuai
Shen, Jialie
Qian, Xueming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03130
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Plug-and-play Model-agnostic Embedding Enhancement Approach for Explainable Recommendation
Mi, Yunqi
Yan, Boyang
Zhao, Guoshuai
Shen, Jialie
Qian, Xueming
Information Retrieval
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.
title A Plug-and-play Model-agnostic Embedding Enhancement Approach for Explainable Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2509.03130