Learning Contrastive Multi-View Graphs for Recommendation (Student Abstract)

Zhangtao Cheng, Ting Zhong, Kunpeng Zhang, Joojo Walker, Fan Zhou

AAAI 2022 pp. 12927-12928

doi:10.1609/AAAI.V36I11.21600 /aaai/2022/cheng2022aaai-learning/

Abstract

This paper exploits self-supervised learning (SSL) to learn more accurate and robust representations from the user-item interaction graph. Particularly, we propose a novel SSL model that effectively leverages contrastive multi-view learning and pseudo-siamese network to construct a pre-training and post-training framework. Moreover, we present three graph augmentation techniques during the pre-training stage and explore the effects of combining different augmentations, which allow us to learn general and robust representations for the GNN-based recommendation. Simple experimental evaluations on real-world datasets show that the proposed solution significantly improves the recommendation accuracy, especially for sparse data, and is also noise resistant.

PDF AAAI Semantic Scholar

Cite

Text

Cheng et al. "Learning Contrastive Multi-View Graphs for Recommendation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21600

Markdown

[Cheng et al. "Learning Contrastive Multi-View Graphs for Recommendation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/cheng2022aaai-learning/) doi:10.1609/AAAI.V36I11.21600

BibTeX

@inproceedings{cheng2022aaai-learning,
  title     = {{Learning Contrastive Multi-View Graphs for Recommendation (Student Abstract)}},
  author    = {Cheng, Zhangtao and Zhong, Ting and Zhang, Kunpeng and Walker, Joojo and Zhou, Fan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {12927-12928},
  doi       = {10.1609/AAAI.V36I11.21600},
  url       = {https://mlanthology.org/aaai/2022/cheng2022aaai-learning/}
}