A Context-Aware User-Item Representation Learning for Item Recommendation

By Libing Wu, Cong Quan, Chenliang Li, Qian Wang, Bolong Zheng. 2017

226 citations recorded by the source corpus.

Both reviews and user-item interactions (i.e., rating scores) have been widely adopted for user rating prediction. However, these existing techniques mainly extract the latent representations for users and items in an independent and static manner. That is, a single static feature vector is derived to encode user preference without considering the particular characteristics of each candidate item. We argue that this static encoding scheme is incapable of fully capturing users’ preferences, because users usually exhibit different preferences when interacting with different items. In this article, we propose a novel context-aware user-item representation learning model for rating prediction, named CARL. CARL derives a joint representation for a given user-item pair based on their individual latent features and latent feature interactions. Then, CARL adopts Factorization Machines to further model higher order feature interactions on the basis of the user-item pair for rating prediction. Specifically, two separate learning components are devised in CARL to exploit review data and interaction data, respectively: review-based feature learning and interaction-based feature learning. In the review-based learning component, with convolution operations and attention mechanism, the pair-based relevant features for the given user-item pair are extracted by jointly considering their corresponding reviews. However, these features are only reivew-driven and may not be comprehensive. Hence, an interaction-based learning component further extracts complementary features from interaction data alone, also on the basis of user-item pairs. The final rating score is then derived with a dynamic linear fusion mechanism. Experiments on seven real-world datasets show that CARL achieves significantly better rating prediction accuracy than existing state-of-the-art alternatives. Also, with the attention mechanism, we show that the pair-based relevant information (i.e., context-aware information) in reviews can be highlighted to interpret the rating prediction for different user-item pairs.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Chen
2. Yongfeng Zhang
3. Zheng Qin
4. Hongyuan Zha
5. Hongteng Xu
6. Hanxiong Chen
7. Yixin Cao
8. Xiangnan He

In Information Systems

1. Xu Chen
2. Yongfeng Zhang
3. Zheng Qin
4. Hongyuan Zha
5. Hongteng Xu
6. Hanxiong Chen
7. Yixin Cao
8. Xiangnan He

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “For example, the Explicit Factor Model (EFM) for explainable recommendation proposed in Zhang et al. [2014a] developed a multi-matrix factorization model for explainable recommendation, and based on this model, it provides a piece of explanation sentence to the user as recommendation explanation, as”
• Dynamic Explainable Recommendation Based on Neural Attentive Models (2019, methodology): “Previous methods (Chen et al. 2018a; Seo et al. 2017; Wu et al. 2017) usually interpret a recommendation in userindependent manners.”
• Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation (2019, methodology): “Motivated from the intuition that a user’s attentions on her previous reviews should be dependent on the item she is going to buy, CARL [40] andMPCN [36] utilized "Dynamic fusion" and "Co-attention" techniques to "extract" tailored explanations for the target item.”