2025
A Causal-Based Attribute Selection Strategy for Conversational Recommender Systems
Dianer Yu, Qian Li, Xiangmeng Wang, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2025
We introduce Causal Conversational Recommender (CCR), which applies causal inference to model the causality between user behaviors and time/user attribute, enabling deeper understanding of user behaviors’ causal drivers.
A Causal-Based Attribute Selection Strategy for Conversational Recommender Systems
Dianer Yu, Qian Li, Xiangmeng Wang, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2025
We introduce Causal Conversational Recommender (CCR), which applies causal inference to model the causality between user behaviors and time/user attribute, enabling deeper understanding of user behaviors’ causal drivers.
2024
Neural causal graph collaborative filtering
Xiangmeng Wang, Qian Li, Dianer Yu, Wei Huang, Qing Li, Guandong Xu
Information Sciences 2024
In this work, we propose integrating causal modeling with the learning process of GCN-based GCF models, leveraging causality-aware graph embeddings to capture complex dependencies in recommendations.
Neural causal graph collaborative filtering
Xiangmeng Wang, Qian Li, Dianer Yu, Wei Huang, Qing Li, Guandong Xu
Information Sciences 2024
In this work, we propose integrating causal modeling with the learning process of GCN-based GCF models, leveraging causality-aware graph embeddings to capture complex dependencies in recommendations.
Constrained off-policy learning over heterogeneous information for fairness-aware recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
ACM Transactions on Recommender Systems 2024
We propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy), which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network.
Constrained off-policy learning over heterogeneous information for fairness-aware recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
ACM Transactions on Recommender Systems 2024
We propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy), which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network.
Counterfactual Debasing for Multi-behavior Recommendations
Sirui Huang, Qian Li, Xiangmeng Wang, Dianer Yu, Guandong Xu, Qing Li
International Conference on Database Systems for Advanced Applications 2024
We debias the negative effects of unobserved confounders with stable counterfactual reasoning, which models the stable trend within the stratum of users and is enhanced with counterfactual examples.
Counterfactual Debasing for Multi-behavior Recommendations
Sirui Huang, Qian Li, Xiangmeng Wang, Dianer Yu, Guandong Xu, Qing Li
International Conference on Database Systems for Advanced Applications 2024
We debias the negative effects of unobserved confounders with stable counterfactual reasoning, which models the stable trend within the stratum of users and is enhanced with counterfactual examples.
Counterfactual explanation for fairness in recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
ACM Transactions on Information Systems 2024
In this work, we adopt counterfactual explanations from causal inference and propose to generate attribute-level counterfactual explanations, adapting to discrete attributes in recommendation models.
Counterfactual explanation for fairness in recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
ACM Transactions on Information Systems 2024
In this work, we adopt counterfactual explanations from causal inference and propose to generate attribute-level counterfactual explanations, adapting to discrete attributes in recommendation models.
Reinforced path reasoning for counterfactual explainable recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2024
We propose a novel Counterfactual Explainable Recommendation (CERec) to generate item attribute-based counterfactual explanations meanwhile to boost recommendation performance.
Reinforced path reasoning for counterfactual explainable recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Qing Li, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2024
We propose a novel Counterfactual Explainable Recommendation (CERec) to generate item attribute-based counterfactual explanations meanwhile to boost recommendation performance.
2023
Counterfactual explainable conversational recommendation
Dianer Yu, Qian Li, Xiangmeng Wang, Qing Li, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2023
In this paper, we are the first to incorporate the counterfactual techniques into CRS and propose a Counterfactual Explainable Conversational Recommender (CECR) to enhance the recommendation model from a counterfactual perspective.
Counterfactual explainable conversational recommendation
Dianer Yu, Qian Li, Xiangmeng Wang, Qing Li, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2023
In this paper, we are the first to incorporate the counterfactual techniques into CRS and propose a Counterfactual Explainable Conversational Recommender (CECR) to enhance the recommendation model from a counterfactual perspective.
Deconfounded recommendation via causal intervention
Dianer Yu, Qian Li, Xiangmeng Wang, Guandong Xu
Neurocomputing 2023
In this paper, we propose a novel deconfounded causal learning method called GCRec (Graph Causal Recommendetion) to debias two confounders: social network confounder and item group confounder.
Deconfounded recommendation via causal intervention
Dianer Yu, Qian Li, Xiangmeng Wang, Guandong Xu
Neurocomputing 2023
In this paper, we propose a novel deconfounded causal learning method called GCRec (Graph Causal Recommendetion) to debias two confounders: social network confounder and item group confounder.
Be causal: De-biasing social network confounding in recommendation
Qian Li*, Xiangmeng Wang*, Zhichao Wang, Guandong Xu (* equal contribution)
ACM Transactions on Knowledge Discovery from Data 2023
Little research has been done to reveal how the ratings are missing (Missing-Not-At-Random problem) from a causal perspective. To bridge the gap, we propose an unbiased and robust method called DENC (De-Bias Network Confounding in Recommendation), inspired by confounder analysis in causal inference.
Be causal: De-biasing social network confounding in recommendation
Qian Li*, Xiangmeng Wang*, Zhichao Wang, Guandong Xu (* equal contribution)
ACM Transactions on Knowledge Discovery from Data 2023
Little research has been done to reveal how the ratings are missing (Missing-Not-At-Random problem) from a causal perspective. To bridge the gap, we propose an unbiased and robust method called DENC (De-Bias Network Confounding in Recommendation), inspired by confounder analysis in causal inference.
2022
MGPolicy: Meta Graph Enhanced Off-policy Learning for Recommendations
Xiangmeng Wang, Qian Li, Dianer Yu, Zhichao Wang, Hongxu Chen, Guandong Xu
the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2022
This paper proposes a framework termed meta graph enhanced off-policy learning (MGPolicy), which is the first recommendation model for correcting the off-policy bias via contextual information.
MGPolicy: Meta Graph Enhanced Off-policy Learning for Recommendations
Xiangmeng Wang, Qian Li, Dianer Yu, Zhichao Wang, Hongxu Chen, Guandong Xu
the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2022
This paper proposes a framework termed meta graph enhanced off-policy learning (MGPolicy), which is the first recommendation model for correcting the off-policy bias via contextual information.
Semantics-guided disentangled learning for recommendation
Dianer Yu, Qian Li, Xiangmeng Wang, Zhichao Wang, Guandong Xu
Pacific-Asia Conference on Knowledge Discovery and Data Mining 2022
Recent disentangled learning methods emphasize on untangling users’ true interests from historical interaction records, which however overlook auxiliary information to correct bias. In this paper, we design a novel method called SeDLR (Semantics Disentangled Learning Recommendation) to bridge this gap.
Semantics-guided disentangled learning for recommendation
Dianer Yu, Qian Li, Xiangmeng Wang, Zhichao Wang, Guandong Xu
Pacific-Asia Conference on Knowledge Discovery and Data Mining 2022
Recent disentangled learning methods emphasize on untangling users’ true interests from historical interaction records, which however overlook auxiliary information to correct bias. In this paper, we design a novel method called SeDLR (Semantics Disentangled Learning Recommendation) to bridge this gap.
Off-policy learning over heterogeneous information for recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Guandong Xu
the ACM Web Conference 2022 2022
We are the first to propose a novel off-policy learning augmented by meta-paths for the recommendation. We argue that the Heterogeneous information network (HIN), which provides rich contextual information of items and user aspects, could scale the logged data contribution for unbiased target policy learning.
Off-policy learning over heterogeneous information for recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Guandong Xu
the ACM Web Conference 2022 2022
We are the first to propose a novel off-policy learning augmented by meta-paths for the recommendation. We argue that the Heterogeneous information network (HIN), which provides rich contextual information of items and user aspects, could scale the logged data contribution for unbiased target policy learning.
Causal disentanglement for semantic-aware intent learning in recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Peng Cui, Zhichao Wang, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2022
The first to propose an unbiased and semantic-aware disentanglement learning called CaDSI (Causal Disentanglement for Semantics-Aware Intent Learning) from a causal perspective. Particularly, CaDSI explicitly models the causal relations underlying recommendation task, and thus produces semantic-aware representations via disentangling users’ true intents aware of specific item context.
Causal disentanglement for semantic-aware intent learning in recommendation
Xiangmeng Wang, Qian Li, Dianer Yu, Peng Cui, Zhichao Wang, Guandong Xu
IEEE Transactions on Knowledge and Data Engineering 2022
The first to propose an unbiased and semantic-aware disentanglement learning called CaDSI (Causal Disentanglement for Semantics-Aware Intent Learning) from a causal perspective. Particularly, CaDSI explicitly models the causal relations underlying recommendation task, and thus produces semantic-aware representations via disentangling users’ true intents aware of specific item context.
2020
Joint relational dependency learning for sequential recommendation
Xiangmeng Wang, Qian Li, Wu Zhang, Guandong Xu, Shaowu Liu, Wenhao Zhu
Advances in Knowledge Discovery and Data Mining: 24th Pacific-Asia Conference 2020
We proposed a Joint Relational Dependency learning (JRD-L) for sequential recommendation that exploits both long-term and short-term preferences at individual-level and union-level.
Joint relational dependency learning for sequential recommendation
Xiangmeng Wang, Qian Li, Wu Zhang, Guandong Xu, Shaowu Liu, Wenhao Zhu
Advances in Knowledge Discovery and Data Mining: 24th Pacific-Asia Conference 2020
We proposed a Joint Relational Dependency learning (JRD-L) for sequential recommendation that exploits both long-term and short-term preferences at individual-level and union-level.