Reinforced Path Reasoning for Counterfactual Explainable Recommendation

Counterfactual explanations interpret the recommendation mechanism by exploring how minimal alterations on items or users affect recommendation decisions. Existing counterfactual explainable approaches face huge search space, and their explanations are either action-based (e.g., user click) or aspec...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on knowledge and data engineering 2024-07, Vol.36 (7), p.3443-3459
Hauptverfasser:	Wang, Xiangmeng, Li, Qian, Yu, Dianer, Li, Qing, Xu, Guandong
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Adaptive sampling Closed box Cognition Collaboration counterfactual explanation counterfactual reasoning Decision trees Explainable recommendation Knowledge graphs Knowledge representation Recommender systems Reinforcement learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!