TY - JOUR
T1 - Interpretable Deep Generative Recommendation Models
AU - Liu, Huafeng
AU - Jing, Liping
AU - Wen, Jingxuan
AU - Xu, Pengyu
AU - Wang, Jiaqi
AU - Yu, Jian
AU - Ng, Michael K.
N1 - Funding information:
This work was supported in part by This work was supported in part by the Beijing Natural Science Foundation (Z180006); the National Science Foundation of China (61822601, 61773050 and 61632004); Science and Technology Innovation Planning Foundation of Universities from Ministry of Education; the Open Project Program Foundation of the Key Laboratory of Opto-Electronics Information Processing, Chinese Academy of Sciences (OEIP-O202004). The research of Michale K. Ng is partially supported by the Research Grants Council of Hong Kong, General Research Fund (12300218, 12300519, 17201020 and 17300021).
Publisher Copyright:
© 2021 Huafeng Liu, Liping Jing, Jingxuan Wen, Pengyu Xu, Jiaqi Wang, Jian Yu and Michael K. Ng.
PY - 2021/8
Y1 - 2021/8
N2 - User preference modeling in recommendation system aims to improve customer experience through discovering users’ intrinsic preference based on prior user behavior data. This is a challenging issue because user preferences usually have complicated structure, such as inter-user preference similarity and intra-user preference diversity. Among them, inter-user similarity indicates different users may share similar preference, while intra-user diversity indicates one user may have several preferences. In literatures, deep generative models have been successfully applied in recommendation systems due to its flexibility on statistical distributions and strong ability for non-linear representation learning. However, they suffer from the simple generative process when handling complex user preferences. Meanwhile, the latent representations learned by deep generative models are usually entangled, and may range from observed-level ones that dominate the complex correlations between users, to latent-level ones that characterize a user’s preference, which makes the deep model hard to explain and unfriendly for recommendation. Thus, in this paper, we propose an Interpretable Deep Generative Recommendation Model (InDGRM) to characterize inter-user preference similarity and intra-user preference diversity, which will simultaneously disentangle the learned representation from observed-level and latent-level. In InDGRM, the observed-level disentanglement on users is achieved by modeling the user-cluster structure (i.e., inter-user preference similarity) in a rich multimodal space, so that users with similar preferences are assigned into the same cluster. The observed-level disentanglement on items is achieved by modeling the intra-user preference diversity in a prototype learning strategy, where different user intentions are captured by item groups (one group refers to one intention). To promote disentangled latent representations, InDGRM adopts structure and sparsity-inducing penalty and integrates them into the generative procedure, which has ability to enforce each latent factor focus on a limited subset of items (e.g., one item group) and benefit latent-level disentanglement. Meanwhile, it can be efficiently inferred by minimizing its penalized upper bound with the aid of local variational optimization technique. Theoretically, we analyze the generalization error bound of InDGRM to guarantee its performance. A series of experimental results on four widely-used benchmark datasets demonstrates the superiority of InDGRM on recommendation performance and interpretability.
AB - User preference modeling in recommendation system aims to improve customer experience through discovering users’ intrinsic preference based on prior user behavior data. This is a challenging issue because user preferences usually have complicated structure, such as inter-user preference similarity and intra-user preference diversity. Among them, inter-user similarity indicates different users may share similar preference, while intra-user diversity indicates one user may have several preferences. In literatures, deep generative models have been successfully applied in recommendation systems due to its flexibility on statistical distributions and strong ability for non-linear representation learning. However, they suffer from the simple generative process when handling complex user preferences. Meanwhile, the latent representations learned by deep generative models are usually entangled, and may range from observed-level ones that dominate the complex correlations between users, to latent-level ones that characterize a user’s preference, which makes the deep model hard to explain and unfriendly for recommendation. Thus, in this paper, we propose an Interpretable Deep Generative Recommendation Model (InDGRM) to characterize inter-user preference similarity and intra-user preference diversity, which will simultaneously disentangle the learned representation from observed-level and latent-level. In InDGRM, the observed-level disentanglement on users is achieved by modeling the user-cluster structure (i.e., inter-user preference similarity) in a rich multimodal space, so that users with similar preferences are assigned into the same cluster. The observed-level disentanglement on items is achieved by modeling the intra-user preference diversity in a prototype learning strategy, where different user intentions are captured by item groups (one group refers to one intention). To promote disentangled latent representations, InDGRM adopts structure and sparsity-inducing penalty and integrates them into the generative procedure, which has ability to enforce each latent factor focus on a limited subset of items (e.g., one item group) and benefit latent-level disentanglement. Meanwhile, it can be efficiently inferred by minimizing its penalized upper bound with the aid of local variational optimization technique. Theoretically, we analyze the generalization error bound of InDGRM to guarantee its performance. A series of experimental results on four widely-used benchmark datasets demonstrates the superiority of InDGRM on recommendation performance and interpretability.
KW - Collaborative filtering
KW - Deep generative model
KW - Interpretable machine learning
KW - Latent factor model
KW - Recommendation system
UR - http://www.scopus.com/inward/record.url?scp=85116943074&partnerID=8YFLogxK
M3 - Journal article
AN - SCOPUS:85116943074
SN - 1532-4435
VL - 22
SP - 1
EP - 54
JO - Journal of Machine Learning Research
JF - Journal of Machine Learning Research
ER -