中国科学院重庆绿色智能技术研究院机构知识库

QQ客服 官方微博 反馈留言

	Relieving Popularity Bias in Interactive Recommendation: A Diversity-Novelty-Aware Reinforcement Learning Approach
	Shi, Xiaoyu1; Liu, Quanliang1; Xie, Hong1; Wu, Di2; Peng, Bo1; Shang, Mingsheng1; Lian, Defu3
	2024-03-01
摘要	While personalization increases the utility of item recommendation, it also suffers from the issue of popularity bias. However, previous methods emphasize adopting supervised learning models to relieve popularity bias in the static recommendation, ignoring the dynamic transfer of user preference and amplification effects of the feedback loop in the recommender system (RS). In this paper, we focus on studying this issue in the interactive recommendation. We argue that diversification and novelty are both equally crucial for improving user satisfaction of IRS in the aforementioned setting. To achieve this goal, we propose a Diversity-Novelty-aware Interactive Recommendation framework (DNaIR) that augments offline reinforcement learning (RL) to increase the exposure rate of long-tail items with high quality. Its main idea is first to aggregate the item similarity, popularity, and quality into the reward model to help the planning of RL policy. It then designs a diversity-aware stochastic action generator to achieve an efficient and lightweight DNaIR algorithm. Extensive experiments are conducted on the three real-world datasets and an authentic RL environment (Virtual-Taobao). The experiments show that our model can better and full use of the long-tail items to improve recommendation satisfaction, especially those low popularity items with high-quality ones, thus achieving state-of-the-art performance.
关键词	Interactive recommendation popularity bias item fairness reinfor cement learning
DOI	10.1145/3618107
发表期刊	ACM TRANSACTIONS ON INFORMATION SYSTEMS
ISSN	1046-8188
卷号	42期号:2页码:30
通讯作者	Shang, Mingsheng(msshang@cigit.ac.cn)
收录类别	SCI
WOS记录号	WOS:001152702600020
语种	en