Learning Dual-Layer User Representation for Enhanced Item Recommendation
Source abstract
Abstract
User representation learning is crucial for capturing different user preferences, but it is also critical challenging because user intentions are latent and dispersed in complex and different patterns of user-generated data, and thus cannot be measured directly. Text-based data models can learn user representations by mining latent semantics, which is beneficial to enhancing the semantic function of user representations. However, these technologies only extract common features in historical records and cannot represent changes in user intentions. However, sequential feature can express the user’s interests and intentions that change time by time. But the sequential recommendation results based on the user representation of the item lack the interpretability of preference factors. To address these issues, we propose in this paper a novel model with Dual-Layer User Representation, named DLUR, where the user’s intention is learned based on two different layer representations. Specifically, the latent semantic layer adds an interactive layer based on Transformer to extract keywords and key sentences in the text and serve as a basis for interpretation. The sequence layer uses the Transformer model to encode the user’s preference intention to clarify changes in the user’s intention. Therefore, this dual-layer user mode is more comprehensive than a single text mode or sequence mode and can effectually improve the performance of recommendations. Our extensive experiments on five benchmark datasets demonstrate DLUR’s performance over state-of-the-art recommendation models. In addition, DLUR’s ability to explain recommendation results is also demonstrated through some specific cases.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Recommender Systems and Techniques · Advanced Graph Neural Networks · Topic Modeling
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (42)
Show source-provided references
1. Perceive your users in depth: Learning universal user representations from multiple e-commerce tasks
2. StackRec: Efficient training of very deep sequential recommender models by iterative stacking
3. A simple convolutional generative network for next item recommendation
4. S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization
5. When recurrent neural networks meet the neighborhood for session-based recommendation
6. Contextual and sequential user embeddings for large-scale music recommendation
7. Context-aware recommendations based on deep learning frameworks10.1145/3386243 ↗
8. Recommendation rating prediction based on attribute boosting with partial sampling
9. Research on collaborative filtering recommendation algorithm for improving user similarity calculation
10. Research on recommendation algorithm based on collaborative filtering
11. Research on collaborative filtering recommendation algorithm based on sentiment analysis and topic model
12. Matrix factorization techniques for recommender systems10.1109/MC.2009.263 ↗
13. Sigmoid function-based web service collaborative filtering recommendation algorithm
14. A recommender approach based on customer emotions10.1016/j.eswa.2018.12.035 ↗
15. Recommending human resources to project leaders using a collaborative filtering-based recommender system: Case study of gitHub10.1049/iet-sen.2018.5261 ↗
16. Self-attentive sequential recommendation
17. Deep interest evolution network for click-through rate prediction
18. Behavior sequence transformer for e-commerce recommendation in Alibaba
19. Learning deep structured semantic models for web search using clickthrough data
20. DeepFM: A factorization-machine based neural network for CTR prediction
21. Neural factorization machines for sparse predictive analytics
22. Distributed representations of sentences and documents
23. Learning distributed representations of sentences from unlabeled data
24. A simple but tough-to-beat baseline for sentence embeddings
25. Neural machine translation by jointly learning to align and translate
26. Attention is all you need
27. J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018. doi: 10.48550/arXiv.1810.04805.
28. Language models based on deep learning: A review
29. Task relation-aware continual user representation learning
30. Learning dual-view user representations for enhanced sequential recommendation
31. We are not so similar: Alleviating user representation collapse in social recommendation
32. RecGURU: Adversarial learning of generalized user representations for cross-domain recommendation
33. JNET: Learning user representations via joint network embedding and topic embedding
34. Learning dynamic user behavior based on error-driven event representation
35. M. Pagliardini, P. Gupta, and M. Jaggi, “Unsupervised learning of sentence embeddings using compositional n-gram features,” arXiv preprint arXiv:1703.02507, 2017. doi: 10.48550/arXiv.1703.02507.10.18653/v1/N18-1049 ↗
36. Research on personalized advertising recommendation systems and their applications
37. Open user profiles for adaptive news systems: Help or harm?
38. Joint deep modeling of users and items using reviews for recommendation
39. Attentive preference personalized recommendation with sentence-level explanations10.1016/j.neucom.2020.10.041 ↗
40. Session-based recommendations with recurrent neural networks
41. Next item recommendation with self-attentive metric learning
42. Set-sequence-graph: A multi-view approach towards exploiting reviews for recommendation