김혜영 박사과정, 최민진 박사 졸업생, 이선경 박사과정, 백일웅 석박통합과정 SIGIR 2025 국제 학술대회 논문 채택

05 Apr 2025

DIAL 연구실 소속 인공지능학과 김혜영(박사과정, 제1저자) 학생, 최민진(박사 졸업생, 제2저자), 이선경(박사과정, 제3저자) 학생, 백일웅(석박통합과정, 제4저자) 학생, 이종욱(교신저자) 교수가 참여한 논문 "DIFF: Dual Side-Information Filtering and Fusion for Sequential Recommendation"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

Side information Integrated Sequential Recommendation (SISR) benefits from auxiliary item information to infer hidden user preferences, which is particularly effective for sparse interactions and cold-start item settings. However, existing studies face two main challenges. (i) They fail to remove noisy signals from the item sequence, and (ii) they do not fully exploit the potential of side information integration. To tackle these issues, we propose a novel SISR model, Dual Side Information Filtering and Fusion (DIFF), which employs frequency-based noise filtering and dual multi-sequence fusion. Specifically, we convert the item sequence to the frequency domain to filter out noisy short-term fluctuations in user interests. We then combine complementary early and intermediate fusion to capture diverse relationships across item IDs and attributes. Thanks to our innovative filtering and fusion strategy, DIFF is more robust in learning subtle and complex item correlations in the sequence. Experimental results show that DIFF outperforms state-of-the-art SISR models, achieving improvements of up to 14.1% and 12.5% in Recall@20 and NDCG@20 across four benchmark datasets.