Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Jingmao, Zhao, Zhiting, Lin, Yunqi, Ma, Jianghong, Wei, Tianjun, Zhang, Haijun, Zhang, Xiaofeng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.17733
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915686556631040
author Zhang, Jingmao
Zhao, Zhiting
Lin, Yunqi
Ma, Jianghong
Wei, Tianjun
Zhang, Haijun
Zhang, Xiaofeng
author_facet Zhang, Jingmao
Zhao, Zhiting
Lin, Yunqi
Ma, Jianghong
Wei, Tianjun
Zhang, Haijun
Zhang, Xiaofeng
contents Beyond user-item modeling, item-to-item relationships are increasingly used to enhance recommendation. However, common methods largely rely on co-occurrence, making them prone to item popularity bias and user attributes, which degrades embedding quality and performance. Meanwhile, although diversity is acknowledged as a key aspect of recommendation quality, existing research offers limited attention to it, with a notable lack of causal perspectives and theoretical grounding. To address these challenges, we propose Cadence: Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure - a plug-and-play framework built upon LightGCN as the backbone, primarily designed to enhance recommendation diversity while preserving accuracy. First, we compute the Unbiased Asymmetric Co-purchase Relationship (UACR) between items - excluding item popularity and user attributes - to construct a deconfounded directed item graph, with an aggregation mechanism to refine embeddings. Second, we leverage UACR to identify diverse categories of items that exhibit strong causal relevance to a user's interacted items but have not yet been engaged with. We then simulate their behavior under high-exposure scenarios, thereby significantly enhancing recommendation diversity while preserving relevance. Extensive experiments on real-world datasets demonstrate that our method consistently outperforms state-of-the-art diversity models in both diversity and accuracy, and further validates its effectiveness, transferability, and efficiency over baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17733
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure
Zhang, Jingmao
Zhao, Zhiting
Lin, Yunqi
Ma, Jianghong
Wei, Tianjun
Zhang, Haijun
Zhang, Xiaofeng
Information Retrieval
Artificial Intelligence
Beyond user-item modeling, item-to-item relationships are increasingly used to enhance recommendation. However, common methods largely rely on co-occurrence, making them prone to item popularity bias and user attributes, which degrades embedding quality and performance. Meanwhile, although diversity is acknowledged as a key aspect of recommendation quality, existing research offers limited attention to it, with a notable lack of causal perspectives and theoretical grounding. To address these challenges, we propose Cadence: Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure - a plug-and-play framework built upon LightGCN as the backbone, primarily designed to enhance recommendation diversity while preserving accuracy. First, we compute the Unbiased Asymmetric Co-purchase Relationship (UACR) between items - excluding item popularity and user attributes - to construct a deconfounded directed item graph, with an aggregation mechanism to refine embeddings. Second, we leverage UACR to identify diverse categories of items that exhibit strong causal relevance to a user's interacted items but have not yet been engaged with. We then simulate their behavior under high-exposure scenarios, thereby significantly enhancing recommendation diversity while preserving relevance. Extensive experiments on real-world datasets demonstrate that our method consistently outperforms state-of-the-art diversity models in both diversity and accuracy, and further validates its effectiveness, transferability, and efficiency over baselines.
title Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2512.17733