Chenxu Wang;Fuli Feng;Yang Zhang;Qifan Wang;Xunhan Hu;Xiangnan He
{"title":"Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation","authors":"Chenxu Wang;Fuli Feng;Yang Zhang;Qifan Wang;Xunhan Hu;Xiangnan He","doi":"10.1109/TBDATA.2023.3300547","DOIUrl":null,"url":null,"abstract":"Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions. In this way, some potential interactions are inevitably mislabeled during training, which will hurt the model fidelity, hindering the model to recall the mislabeled items, especially the long-tail ones. In this work, we investigate the mislabeling issue from a new perspective of \n<italic>aleatoric uncertainty</i>\n, which describes the inherent randomness of missing data. The randomness pushes us to go beyond merely the interaction likelihood and embrace aleatoric uncertainty modeling. Towards this end, we propose a new \n<italic>Aleatoric Uncertainty-aware Recommendation</i>\n (AUR) framework that consists of a new uncertainty estimator along with a normal recommender model. According to the theory of aleatoric uncertainty, we derive a new recommendation objective to learn the estimator. As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty, which is demonstrated to improve the recommendation performance of less popular items without sacrificing the overall performance. We instantiate AUR on three representative recommender models: Matrix Factorization (MF), LightGCN, and VAE from mainstream model architectures. Extensive results on four real-world datasets validate the effectiveness of AUR w.r.t. better recommendation results, especially on long-tail items.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"9 6","pages":"1607-1619"},"PeriodicalIF":7.5000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Big Data","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10198303/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 3
Abstract
Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions. In this way, some potential interactions are inevitably mislabeled during training, which will hurt the model fidelity, hindering the model to recall the mislabeled items, especially the long-tail ones. In this work, we investigate the mislabeling issue from a new perspective of
aleatoric uncertainty
, which describes the inherent randomness of missing data. The randomness pushes us to go beyond merely the interaction likelihood and embrace aleatoric uncertainty modeling. Towards this end, we propose a new
Aleatoric Uncertainty-aware Recommendation
(AUR) framework that consists of a new uncertainty estimator along with a normal recommender model. According to the theory of aleatoric uncertainty, we derive a new recommendation objective to learn the estimator. As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty, which is demonstrated to improve the recommendation performance of less popular items without sacrificing the overall performance. We instantiate AUR on three representative recommender models: Matrix Factorization (MF), LightGCN, and VAE from mainstream model architectures. Extensive results on four real-world datasets validate the effectiveness of AUR w.r.t. better recommendation results, especially on long-tail items.
期刊介绍:
The IEEE Transactions on Big Data publishes peer-reviewed articles focusing on big data. These articles present innovative research ideas and application results across disciplines, including novel theories, algorithms, and applications. Research areas cover a wide range, such as big data analytics, visualization, curation, management, semantics, infrastructure, standards, performance analysis, intelligence extraction, scientific discovery, security, privacy, and legal issues specific to big data. The journal also prioritizes applications of big data in fields generating massive datasets.