IEEE

Direct Causal Inference for Out-of-Distribution Node Classification in Internet of Things

Abstract: Graph neural networks (GNNs) have achieved remarkable success in node classification tasks, yet their performance significantly degrades when encountering out-of-distribution (OOD) data due ...
UroToday

The Pelvic Rosetta Classification Project: An Interdisciplinary Proposal for a Lymph Node Map of the Pelvis in Prostate Cancer - Beyond the Abstract

Cross-sectional imaging is an essential component of the diagnostic work-up in patients with suspected or diagnosed prostate cancer (PCa). Commonly used tools like MRI, CT, and prostate-specific ...
Scientific Research Publishing

Perin, E. L. S., De Souza, M. C., De Andrade Silva, J., & Matsubara, E. T. (2025). DynGraph-BERT: Combining BERT and GNN Using Dynamic Graphs for Inductive Semi-Supervised Text ...

ABSTRACT: Government procurement contracts can be complicated, with extensive risk analysis and compliance reviews. The traditional methods of contract analytics are time-consuming and often inexact, ...
Microsoft

A collective learning framework to boost GNN expressiveness for node classification

Collective Inference (CI) is a procedure designed to boost weak relational classifiers, specially for node classification tasks. Graph Neural Networks (GNNs) are strong classifiers that have been used ...
Scientific Research Publishing

Zhang, Y., Xu, Y. and Zhang, Y. (2023) A Graph Neural Network Node Classification Application Model with Enhanced Node Association. Applied Sciences, 13, Article 7150.

ABSTRACT: Drug repositioning aims to identify new therapeutic applications for existing drugs offering a faster and more cost-effective alternative to traditional drug discovery. Since approved drugs ...
IEEE

GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning

Abstract: Microscopic assessment of histopathology images is vital for accurate cancer diagnosis and treatment. Whole Slide Image (WSI) classification and captioning have become crucial tasks in ...
GitHub

Question about the experiment setting on zero-shot node classification

I want to reproduce the result of 59.59, where ARXIV+PUBMED → CORA and prompt type is NODE EMBEDDING+TEXT ATTRIBUTES.