适用于稀疏隐式反馈数据的双重去偏协同过滤推荐算法
Dual Debiased Collaborative Filtering Recommendation Algorithm Suitable for Sparse Implicit Feedback Data
丁雨辰 1徐建军 2崔文泉1
作者信息
- 1. 中国科学技术大学管理学院,合肥 230026;中国科学技术大学国际金融研究院,合肥 230026
- 2. 合肥工业大学数学学院,合肥 230609
- 折叠
摘要
隐式反馈数据是推荐系统的重要数据来源,但通常是稀疏的,并且存在曝光偏差和从众偏差.已知的去偏方法往往只针对其中一种偏差,影响个性化推荐的效果,或者需要一个昂贵的无偏数据集作为多重去偏的辅助信息.为此,本文提出了一个适用于稀疏隐式反馈数据,同时对曝光偏差和从众偏差去偏的协同过滤推荐算法.该算法通过我们提出的双重逆倾向加权方法和对比学习辅助任务去除输入双塔自编码器的隐式反馈数据中包含的两种偏差,估计用户对物品的偏好概率.实验结果显示,本文的算法在公开无偏数据集Coat、Yahoo!R3 上,归一化折扣累积增益NDCG@K、均值平均精度MAP@K和召回率Recall@K优于对比的算法.
Abstract
Implicit feedback data plays a crucial role in recommender systems,but it often suffers from sparsity and biases,including exposure bias and conformity bias.Existing debiasing methods tend to address only one type of bias,which can impact personalized recommendation effectiveness,or require a expensive debiased dataset as auxiliary information for multiple debiasing.To address this issue,a collaborative filtering recommendation algorithm specifically designed for sparse implicit feedback data,which can simultaneously debias exposure bias and conformity bias,is proposed.The algorithm utilizes the proposed dual inverse propensity weighting method and a contrastive learning auxiliary task to remove the two biases contained in the implicit feedback data which are input into dual-tower autoencoders so that the complete algorithm can estimate users'preference probability to items.Experimental results demonstrate that the proposed algorithm outperforms comparative algorithms in terms of normalized discounted cumulative gain(NDCG@K),mean average precision(MAP@K),and recall(Recall@K)on publicly available debiased datasets such as Coat and Yahoo!R3.
关键词
推荐系统/协同过滤/去偏/逆倾向加权/对比学习/自编码器Key words
recommender system/collaborative filtering/debias/inverse propensity weighting/contrastive learning/autoencoder引用本文复制引用
基金项目
国家自然科学基金(12171451)
中国博士后科学基金(2023M733406)
出版年
2024
NETL
NSTL
万方数据