Deep Unified Representation for Heterogeneous Recommendation

  title={Deep Unified Representation for Heterogeneous Recommendation},
  author={Chengqiang Lu and Mingyang Yin and Shuheng Shen and Luo Ji and Qi Liu and Hongxia Yang},
  journal={Proceedings of the ACM Web Conference 2022},
Recommendation system has been a widely studied task both in academia and industry. Previous works mainly focus on homogeneous recommendation and little progress has been made for heterogeneous recommender systems. However, heterogeneous recommendations, e.g., recommending different types of items including products, videos, celebrity shopping notes, among many others, are dominant nowadays. State-of-the-art methods are incapable of leveraging attributes from different types of items and thus… 

Figures and Tables from this paper


Cross-Domain Recommendation: An Embedding and Mapping Approach
The proposed EMCDR framework distinguishes itself from existing crossdomain recommendation models in two aspects: a multi-layer perceptron is used to capture the nonlinear mapping function across domains, and only the entities with sufficient data are used to learn the mapping function, guaranteeing its robustness to noise caused by data sparsity in single domain.
Heterogeneous Information Network Embedding for Recommendation
A novel heterogeneous network embedding based approach for HIN based recommendation, called HERec is proposed, which shows the capability of the HERec model for the cold-start problem, and reveals that the transformed embedding information from HINs can improve the recommendation performance.
A General Cross-Domain Recommendation Framework via Bayesian Neural Network
This work proposes a general cross-domain recommendation framework via Bayesian neural network to incorporate auxiliary information, which takes advantage of both the hybrid recommendation methods and the cross- domain recommendation systems.
Deep Matrix Factorization Models for Recommender Systems
A novel matrix factorization model with neural network architecture is proposed that outperformed other state-of-the-art methods on several benchmark datasets and considers both explicit ratings and implicit feedback for a better optimization.
Selective Transfer Learning for Cross Domain Recommendation
This paper proposes a novel criterion based on empirical prediction error and its variance to better capture the consistency across domains in CF settings and embeds this criterion into a boosting framework to perform selective knowledge transfer.
Cross-Domain Recommendation via Cluster-Level Latent Factor Model
A novel cluster-level based latent factor model is proposed to enhance the cross-domain recommendation, which can not only learn the common rating pattern shared across domains with the flexibility in controlling the optimal level of sharing, but also learn the domain-specific rating patterns of users in each domain that involve the discriminative information propitious to performance improvement.
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
This paper designs a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors, and proposes a technique named label-aware attention to help the learning process of user representations.
Cross-Domain Recommendation for Cold-Start Users via Neighborhood Based Feature Mapping
A Cross-Domain Latent Feature Mapping (CDLFM) model for cold-start users in the target domain is proposed that takes the users' similarity relationship on rating behaviors into consideration and proposes the Matrix Factorization by incorporating User Similarities (MFUS) in which three similarity measures are proposed.
Representation Learning for Attributed Multiplex Heterogeneous Network
Results of the offline A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice, and the theoretical analysis of the proposed framework gives its connection with previous works and proving its better expressiveness.