AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs

Yating Ren, Yikun Ban, Huobin Tan

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace InfoNCE with the GCL-OT loss (ablation)GCL-OT · Cora with perturbed edges and textsaccuracyImproved
add the GCL-OT contrastive loss (ablation)GCL-OT · Cora and other datasetsaccuracyImproved
add the alignment loss L_MHA (RealSoftMax and filter prompt) (ablation)GCL-OT · Texas and CornellaccuracyImproved
add the latent homophily mining loss L_LHM (ablation)GCL-OT · AmazonaccuracyImproved
swap DistilBERT for stronger PLMs (DeBERTa, RoBERTa) (ablation)GCL-OT · Wisconsin, Cornell, TexasaccuracyNo clear effect
add GCL-OT to GCN and GAT under edge deletion (-500 edges)GCN, GAT · Cora edge perturbationaccuracy: relative gains of 24.74% and 79.44%Improved
use GCL-OT with DistilBERT under text perturbationDistilBERT · Cora text perturbationaccuracy: retains nearly 85%Improved
vary lambda, beta and LRSinkhorn iterations (ablation)GCL-OT (GCN) · CoraaccuracyMixed
use unsupervised GCL-OT versus heterophilic GCL baselinesGCL-OT (GCN) · Wisconsin unsupervisedaccuracy (%): 71.93 -> 72.83Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy