Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yicong, Sun, Xiangguo, Chen, Hongxu, Zhang, Sixiao, Yang, Yu, Xu, Guandong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.05744
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909125705728000
author Li, Yicong
Sun, Xiangguo
Chen, Hongxu
Zhang, Sixiao
Yang, Yu
Xu, Guandong
author_facet Li, Yicong
Sun, Xiangguo
Chen, Hongxu
Zhang, Sixiao
Yang, Yu
Xu, Guandong
contents Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on three real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05744
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
Li, Yicong
Sun, Xiangguo
Chen, Hongxu
Zhang, Sixiao
Yang, Yu
Xu, Guandong
Information Retrieval
Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on three real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method.
title Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2401.05744