박성민 석박통합과정, 윤민철 박사과정, 김혜영 박사과정 SIGIR 2025 국제 학술대회 논문 채택

05 Apr 2025

DIAL 연구실 소속 인공지능학과 박성민(박사과정, 제1저자) 학생, 윤민철(박사과정, 제2저자) 학생, 김혜영(박사과정, 제3저자) 학생, 이종욱(교신저자) 교수가 참여한 논문 "Why is Normalization Necessary for Linear Recommenders?"이 데이터마이닝 분야 최우수 국제 학술대회인 ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2025)에 최종 게재가 승인되었으며 오는 7월에 발표될 예정입니다.

Abstract

Despite their simplicity, linear autoencoder (LAE)-based models have shown comparable or even better performance with faster inference speed than neural recommender models. However, LAEs face two critical challenges: (i) popularity bias, which tends to recommend popular items, and (ii) neighborhood bias, which overly focuses on capturing local item correlations. To address these issues, this paper first analyzes the effect of two existing normalization methods for LAEs, i.e., random-walk and symmetric normalization. Our theoretical analysis reveals that normalization highly affects the degree of popularity and neighborhood biases among items. Inspired by this analysis, we propose a versatile normalization solution, called Data-Adaptive Normalization (DAN), which flexibly controls the popularity and neighborhood biases by adjusting item- and user-side normalization to align with unique dataset characteristics. Owing to its model-agnostic property, DAN can be easily applied to various LAE-based models. Experimental results show that DAN-equipped LAEs consistently improve existing LAE-based models across six benchmark datasets, with significant gains of up to 128.57% and 12.36% for long-tail items and unbiased evaluations, respectively.