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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quispe, Joel Frank Huarayo, Berton, Lilian, Vega-Oliveros, Didier
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909875380944896
author Quispe, Joel Frank Huarayo
Berton, Lilian
Vega-Oliveros, Didier
author_facet Quispe, Joel Frank Huarayo
Berton, Lilian
Vega-Oliveros, Didier
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WBT-BGRL: A Non-Contrastive Weighted Bipartite Link Prediction Model for Inductive Learning
Quispe, Joel Frank Huarayo
Berton, Lilian
Vega-Oliveros, Didier
Machine Learning
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.
title WBT-BGRL: A Non-Contrastive Weighted Bipartite Link Prediction Model for Inductive Learning
topic Machine Learning
url https://arxiv.org/abs/2510.24927