Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation

In the field of session-based recommendation, users’ interaction behaviors are affected by both popularity and surrounding environmental factors, such as item popularity, season, or salary, and so on. Utilizing causal learning techniques to mitigate the negative impact of hybrid confounde...

Full description

Saved in:
Bibliographic Details
Main Authors: Quan Li, Xinhua Xu, Jinjun Liu, Guangmin Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11053863/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427134604378112
author Quan Li
Xinhua Xu
Jinjun Liu
Guangmin Li
author_facet Quan Li
Xinhua Xu
Jinjun Liu
Guangmin Li
author_sort Quan Li
collection DOAJ
description In the field of session-based recommendation, users&#x2019; interaction behaviors are affected by both popularity and surrounding environmental factors, such as item popularity, season, or salary, and so on. Utilizing causal learning techniques to mitigate the negative impact of hybrid confounders on user preferences is a pressing challenge in session-based recommendation. Aiming at the above problems, this paper proposes a kind of causal session-based recommendation model for addressing hybrid confounder issue (HCCSRec). First, the conditional probability about user preference given a user sequence is solved by intervention and structural equation. Then, implicit environmental features are learned with observation sequence data. Next, user preference for the next item is estimated from the observation sequence, environmental feature and item popularity. Finally, the objective function is constructed by cross entropy and KL scatter, and the model parameters are learned. We perform extensive experiments on three real-world datasets from Beauty, MovieLens,<xref ref-type="fn" rid="fn2">2</xref> and Yelp. Empirical studies validate that compared with the state-of-art recommendation methods, the HCCSRec method is helpful to discover user real interests, and can further improve the recommendation accuracy.
format Article
id doaj-art-c7fb7d1dc64a4555b187faf705236e99
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c7fb7d1dc64a4555b187faf705236e992025-08-20T03:29:06ZengIEEEIEEE Access2169-35362025-01-011311205611206610.1109/ACCESS.2025.358385111053863Addressing Hybrid Confounder Issue for Causal Session-Based RecommendationQuan Li0https://orcid.org/0000-0001-6211-1046Xinhua Xu1Jinjun Liu2Guangmin Li3Department of Artificial Intelligence and Computer, Hubei Normal University, Huangshi, Hubei, ChinaDepartment of Artificial Intelligence and Computer, Hubei Normal University, Huangshi, Hubei, ChinaDepartment of Artificial Intelligence and Computer, Hubei Normal University, Huangshi, Hubei, ChinaDepartment of Artificial Intelligence and Computer, Hubei Normal University, Huangshi, Hubei, ChinaIn the field of session-based recommendation, users&#x2019; interaction behaviors are affected by both popularity and surrounding environmental factors, such as item popularity, season, or salary, and so on. Utilizing causal learning techniques to mitigate the negative impact of hybrid confounders on user preferences is a pressing challenge in session-based recommendation. Aiming at the above problems, this paper proposes a kind of causal session-based recommendation model for addressing hybrid confounder issue (HCCSRec). First, the conditional probability about user preference given a user sequence is solved by intervention and structural equation. Then, implicit environmental features are learned with observation sequence data. Next, user preference for the next item is estimated from the observation sequence, environmental feature and item popularity. Finally, the objective function is constructed by cross entropy and KL scatter, and the model parameters are learned. We perform extensive experiments on three real-world datasets from Beauty, MovieLens,<xref ref-type="fn" rid="fn2">2</xref> and Yelp. Empirical studies validate that compared with the state-of-art recommendation methods, the HCCSRec method is helpful to discover user real interests, and can further improve the recommendation accuracy.https://ieeexplore.ieee.org/document/11053863/Session-based recommendationcausal learninghybrid confoundercross entropy
spellingShingle Quan Li
Xinhua Xu
Jinjun Liu
Guangmin Li
Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation
IEEE Access
Session-based recommendation
causal learning
hybrid confounder
cross entropy
title Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation
title_full Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation
title_fullStr Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation
title_full_unstemmed Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation
title_short Addressing Hybrid Confounder Issue for Causal Session-Based Recommendation
title_sort addressing hybrid confounder issue for causal session based recommendation
topic Session-based recommendation
causal learning
hybrid confounder
cross entropy
url https://ieeexplore.ieee.org/document/11053863/
work_keys_str_mv AT quanli addressinghybridconfounderissueforcausalsessionbasedrecommendation
AT xinhuaxu addressinghybridconfounderissueforcausalsessionbasedrecommendation
AT jinjunliu addressinghybridconfounderissueforcausalsessionbasedrecommendation
AT guangminli addressinghybridconfounderissueforcausalsessionbasedrecommendation