Enhancing Recommendation with Denoising Auxiliary Task

doi:10.1007/s11390-024-4069-5

	Enhancing Recommendation with Denoising Auxiliary Task
	Liu, Peng-Sheng 1; Zheng, Li-Nan 2,3; Chen, Jia-Le 2,3; Zhang, Guang-Fa 2,3; Xu, Yang 1; Fang, Jin-Yun 2
	2024-09-01
发表期刊	JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
ISSN	1000-9000
卷号	39 期号:5 页码:1123-1137
摘要	The historical interaction sequences of users play a crucial role in training recommender systems that can accurately predict user preferences. However, due to the arbitrariness of user behaviors, the presence of noise in these sequences poses a challenge to predicting their next actions in recommender systems. To address this issue, our motivation is based on the observation that training noisy sequences and clean sequences (sequences without noise) with equal weights can impact the performance of the model. We propose the novel self-supervised Auxiliary Task Joint Training (ATJT) method aimed at more accurately reweighting noisy sequences in recommender systems. Specifically, we strategically select subsets from users' original sequences and perform random replacements to generate artificially replaced noisy sequences. Subsequently, we perform joint training on these artificially replaced noisy sequences and the original sequences. Through effective reweighting, we incorporate the training results of the noise recognition model into the recommender model. We evaluate our method on three datasets using a consistent base model. Experimental results demonstrate the effectiveness of introducing the self-supervised auxiliary task to enhance the base model's performance.
关键词	auxiliary task learning recommender system sequence denoising
DOI	10.1007/s11390-024-4069-5
收录类别	SCI
语种	英语
资助项目	Program for Student Innovation Through Research and Training of Guizhou University[2023SRT071]
WOS研究方向	Computer Science
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Software Engineering
WOS记录号	WOS:001372618500004
出版者	SPRINGER SINGAPORE PTE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41123
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Fang, Jin-Yun
作者单位	1.Guizhou Univ, Coll Big Data & Informat Engn, Guiyang 550025, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Liu, Peng-Sheng,Zheng, Li-Nan,Chen, Jia-Le,et al. Enhancing Recommendation with Denoising Auxiliary Task[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2024,39(5):1123-1137.
APA	Liu, Peng-Sheng,Zheng, Li-Nan,Chen, Jia-Le,Zhang, Guang-Fa,Xu, Yang,&Fang, Jin-Yun.(2024).Enhancing Recommendation with Denoising Auxiliary Task.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,39(5),1123-1137.
MLA	Liu, Peng-Sheng,et al."Enhancing Recommendation with Denoising Auxiliary Task".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 39.5(2024):1123-1137.