User behavior understanding in real world settings
Weiqi Shao, Xu Chen, Jiashu Zhao, Long Xia, Dawei Yin

TL;DR
This paper introduces AutoRep, a novel model that adaptively generates dynamic user behavior representations, improving recommendation accuracy by handling diverse and changing item groups in user histories.
Contribution
AutoRep's innovative design automatically and adaptively constructs dynamic user behavior representations, surpassing fixed methods and enhancing recommendation performance.
Findings
AutoRep outperforms baseline models on five benchmark datasets.
The IRC module captures overall sequential user behavior characteristics.
The DRC module effectively allocates items into dynamic groups.
Abstract
How to extract meaningful information in user historical behavior plays a crucial role in recommendation. User behavior sequence often contains multiple conceptually distinct items that belong to different item groups and the number of the item groups is changing over time. It is necessary to learn a dynamic group of representations according the item groups in a user historical behavior. However, current works only learns a predefined and fixed number representations which includes single representation methods and multi representations methods from the user context that could lead to suboptimal recommendation quality. In this paper we propose a model that can automatically and adaptively generates a dynamic group of representations from the user behavior accordingly. To be specific, AutoRep is composed of an informative representation construct (IRC) module and a dynamic…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · Text and Document Classification Technologies · Sentiment Analysis and Opinion Mining
