Does every data instance matter? Enhancing sequential recommendation by eliminating unreliable data

Yatong Sun, Bin Wang, Zhu Sun, Xiaochun Yang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Most sequential recommender systems (SRSs) predict next-item as target for each user given its preceding items as input, assuming that each input is related to its target. However, users may unintentionally click on items that are inconsistent with their preference. We empirically verify that SRSs can be misguided with such unreliable instances (i.e. targets mismatch inputs). This inspires us to design a novel SRS By Eliminating unReliable Data (BERD) guided with two observations: (1) unreliable instances generally have high training loss; and (2) high-loss instances are not necessarily unreliable but uncertain ones caused by blurry sequential pattern. Accordingly, BERD models both loss and uncertainty of each instance via a Gaussian distribution to better distinguish unreliable instances; meanwhile an uncertainty-aware graph convolution network is exploited to assist in mining unreliable instances by lowering uncertainty. Extensive experiments on four real-world datasets demonstrate the superiority of our proposed BERD.
Original languageEnglish
Title of host publicationProceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21)
EditorsZhi-Hua Zhou
Place of PublicationFreiburg, Germany
PublisherInternational Joint Conferences on Artificial Intelligence
Pages1579-1585
Number of pages7
ISBN (Electronic)9780999241196
DOIs
Publication statusPublished - 2021
Event30th International Joint Conference on Artificial Intelligence, IJCAI 2021 - Montreal, Canada
Duration: 19 Aug 202127 Aug 2021

Conference

Conference30th International Joint Conference on Artificial Intelligence, IJCAI 2021
CountryCanada
CityMontreal
Period19/08/2127/08/21

Fingerprint

Dive into the research topics of 'Does every data instance matter? Enhancing sequential recommendation by eliminating unreliable data'. Together they form a unique fingerprint.

Cite this