MGGCL: Motif-Guided Graph Contrastive Learning for Recommendation
Information · 01.07.2026 · 17 (7) · 645
DOI: 10.3390/info17070645 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 01.07.2026. Verfasst von Li Pang und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Graph motifs capture crucial structural patterns within user–item interaction graphs and offer meaningful semantics that are typically underutilised in conventional graph-based collaborative filtering. Existing contrastive learning methods in recommender systems rely primarily on simple perturbations, which limits their ability to leverage deeper motif-based structural information. To address this gap, we propose a novel motif-guided contrastive learning framework for recommender systems. To exploit complementary structural biases inherent to user–item interactions, our approach explicitly incorporates three distinct motifs into the construction of the contrastive view. By contrasting views that capture the structural differences among different motifs, our model learns meaningful group-level relationships and potentially suppresses noise arising from sparse or isolated interactions. Extensive experiments on four real-world recommendation datasets validate that our motif-based contrastive approach achieves the best overall performance, outperforming state-of-the-art baselines on three of the four benchmarks with statistically significant margins on the more skewed datasets, while remaining competitive on the fourth, which demonstrates notable robustness and improved accuracy.
Zitieren
APA
Pang, L., Zhang, Y., Wang, N., Yu, J., & Huang, D. (2026). MGGCL: Motif-Guided Graph Contrastive Learning for Recommendation. Information, 17(7), 645. https://doi.org/10.3390/info17070645
Vancouver
Pang L, Zhang Y, Wang N, Yu J, Huang D. MGGCL: Motif-Guided Graph Contrastive Learning for Recommendation. Information. 2026;17(7):645. doi:10.3390/info17070645
BibTeX
@article{Pang2026,
author = {Pang, Li and Zhang, Yuqi and Wang, Nancy and Yu, Jian and Huang, Deling},
title = {MGGCL: Motif-Guided Graph Contrastive Learning for Recommendation},
journal = {Information},
year = {2026},
volume = {17},
number = {7},
pages = {645},
doi = {10.3390/info17070645}
}
EUVIMED