Litcius/Paper detail

Causal Representation Learning for Out-of-Distribution Recommendation

Wenjie Wang, Xinyu Lin, Fuli Feng, Xiangnan He, Min Lin, Tat‐Seng Chua

2022Proceedings of the ACM Web Conference 202298 citationsDOIOpen Access PDF

Abstract

Modern recommender systems learn user representations from historical interactions, which suffer from the problem of user feature shifts, such as an income increase. Historical interactions will inject out-of-date information into the representation in conflict with the latest user feature, leading to improper recommendations. In this work, we consider the Out-Of-Distribution (OOD) recommendation problem in an OOD environment with user feature shifts. To pursue high fidelity, we set additional objectives for representation learning as: 1) strong OOD generalization and 2) fast OOD adaptation.

Topics & Concepts

Computer scienceRepresentation (politics)Recommender systemFeature (linguistics)Adaptation (eye)Feature learningGeneralizationSet (abstract data type)FidelityArtificial intelligenceMachine learningHuman–computer interactionInformation retrievalMathematicsProgramming languageTelecommunicationsOpticsPhysicsLinguisticsLawPolitical scienceMathematical analysisPhilosophyPoliticsRecommender Systems and TechniquesAdvanced Bandit Algorithms ResearchMachine Learning in Healthcare
Causal Representation Learning for Out-of-Distribution Recommendation | Litcius