What does this research mean for the field?

Treating collaborative neighbors of an anchor node as positive samples within a supervised contrastive loss function significantly improves the performance of graph-based collaborative filtering models compared to standard self-supervised contrastive learning. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

September 19, 2023IEEE Transactions on Knowledge and Data EngineeringOpen Access

Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering

View Full Paper

Ask AI

Bookmark

Authors

PSPeijie SunHefei University of Technology LWLe WuHefei University of Technology KZKun ZhangUniversity of Science and Technology of China

Discussion

Member takes

Overview

Key Points

Key points are not available for this paper at this time.

Cite This Study

Sun et al. (2023) studied this question.

synapsesocial.com/papers/6a0a6700742cc54163378cd5 https://doi.org/10.1109/tkde.2023.3317068

View Full Paper

Ask AI

Bookmark

Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering

Discussion

Member takes

Overview

Key Points

Cite This Study

Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering

Discussion

Member takes

Overview

Key Points

Cite This Study

Also Consider

Also Consider