Improved Session Recommendation Using Contrastive Learning based Tail Adjusted Repeat Aware Graph Neural Network
Computer Science and Information Systems, Tome 22 (2025) no. 1
Cet article a éte moissonné depuis la source Computer Science and Information Systems website
Purpose: Session-based recommendation using graph neural networks (GNN) is a popular approach to model users’ behaviors and attributes of items from the perspective of user-item interaction sequence. However, current researches seldom incorporate the unique attributes of items to delve into a comprehensive analysis of user behaviors. In addition, GNN faces three problems when encounting complex modeling scenarios: long-range dependencies, order information loss, and data sparsity, which are essential to modeling long-tail items. Methods: We study the interactions between users and items from a new perspective. A novel Contrastive Learning based Tail Adjusted Repeat Aware Graph Neural Network (CLTAR-GNN) is proposed to tackle the problems. A Tail Adjusted Repeat (TAR) mechanism captures users’ repeat-explore behaviors in both short-head and long-tail session items based on graph neural networks. Through the TAR, we are able to further understand the underlying graph-based mechanisms that influence user-item interactions. A Self-Attention (SA) network with position embedding is incorporated to overcome the sequence information loss issues, which may be caused by the complex user behaviors and item characteristics modeling. Finally, a mutli-task learning framework is employed to combine TAR, SA and a contrastive learning model into a unified framework to enhance model performance by collaboratively training graph and sequence-based embeddings. Results: Experimental results show that CLTAR-GNN outperforms the state-of-the-art session-based recommendation methods significantly. The average improvement compared with all baselines are 17.5% (HR@20) and 22.5% (MRR@20) on both experimental datasets.
Keywords:
Session-based Recommendation, Contrastive Learning, Self-Attention Networks, Tail Adjusted Repeat
@article{CSIS_2025_22_1_a16,
author = {Daifeng Li and Tianjunzi Tian and Zhaohui Huang and Xiaowen Lin and Dingquan Chen and Andrew Madden},
title = {Improved {Session} {Recommendation} {Using} {Contrastive} {Learning} based {Tail} {Adjusted} {Repeat} {Aware} {Graph} {Neural} {Network}},
journal = {Computer Science and Information Systems},
year = {2025},
volume = {22},
number = {1},
url = {http://geodesic.mathdoc.fr/item/CSIS_2025_22_1_a16/}
}
TY - JOUR AU - Daifeng Li AU - Tianjunzi Tian AU - Zhaohui Huang AU - Xiaowen Lin AU - Dingquan Chen AU - Andrew Madden TI - Improved Session Recommendation Using Contrastive Learning based Tail Adjusted Repeat Aware Graph Neural Network JO - Computer Science and Information Systems PY - 2025 VL - 22 IS - 1 UR - http://geodesic.mathdoc.fr/item/CSIS_2025_22_1_a16/ ID - CSIS_2025_22_1_a16 ER -
%0 Journal Article %A Daifeng Li %A Tianjunzi Tian %A Zhaohui Huang %A Xiaowen Lin %A Dingquan Chen %A Andrew Madden %T Improved Session Recommendation Using Contrastive Learning based Tail Adjusted Repeat Aware Graph Neural Network %J Computer Science and Information Systems %D 2025 %V 22 %N 1 %U http://geodesic.mathdoc.fr/item/CSIS_2025_22_1_a16/ %F CSIS_2025_22_1_a16
Daifeng Li; Tianjunzi Tian; Zhaohui Huang; Xiaowen Lin; Dingquan Chen; Andrew Madden. Improved Session Recommendation Using Contrastive Learning based Tail Adjusted Repeat Aware Graph Neural Network. Computer Science and Information Systems, Tome 22 (2025) no. 1. http://geodesic.mathdoc.fr/item/CSIS_2025_22_1_a16/