LGOct 28, 2025

WBT-BGRL: A Non-Contrastive Weighted Bipartite Link Prediction Model for Inductive Learning

arXiv:2510.24927v1h-index: 132025 12th International Conference on Soft Computing & Machine Intelligence (ISCMI)
Originality Incremental advance
AI Analysis

It addresses inductive, weighted link prediction in bipartite graphs, an incremental improvement over existing methods.

The paper tackles link prediction in bipartite graphs for applications like recommendation systems by proposing WBT-BGRL, a non-contrastive framework with a weighting mechanism, showing competitive performance on real-world datasets.

Link prediction in bipartite graphs is crucial for applications like recommendation systems and failure detection, yet it is less studied than in monopartite graphs. Contrastive methods struggle with inefficient and biased negative sampling, while non-contrastive approaches rely solely on positive samples. Existing models perform well in transductive settings, but their effectiveness in inductive, weighted, and bipartite scenarios remains untested. To address this, we propose Weighted Bipartite Triplet-Bootstrapped Graph Latents (WBT-BGRL), a non-contrastive framework that enhances bootstrapped learning with a novel weighting mechanism in the triplet loss. Using a bipartite architecture with dual GCN encoders, WBT-BGRL is evaluated against adapted state-of-the-art models (T-BGRL, BGRL, GBT, CCA-SSG). Results on real-world datasets (Industry and E-commerce) show competitive performance, especially when weighting is applied during pretraining-highlighting the value of weighted, non-contrastive learning for inductive link prediction in bipartite graphs.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes