Adapting to the Stream: An Instance-Attention GNN Method for Irregular Multivariate Time Series Data
DynIMTS replaces static graphs with instance-attention that updates edge weights on the fly, delivering SOTA imputation and P12 classification ...
Graph Neural Networks (GNNs) are supposed to excel at graph-structured data. But on Elliptic++ Bitcoin fraud detection, a simple XGBoost model beats all GNN baselines by 49%. This repository ...
Graph neural networks in Alzheimer's disease diagnosis: a review of unimodal and multimodal advances
Alzheimer's Disease (AD), a leading neurodegenerative disorder, presents significant global health challenges. Advances in graph neural networks (GNNs) offer promising tools for analyzing multimodal ...
Abstract: Graph matching is a critical task with diverse real-world applications. Current cutting-edge methodologies incorporate GNN (Graph Neural Network) combined with incremental anchor refinement, ...
ABSTRACT: Missing data remains a persistent and pervasive challenge across a wide range of domains, significantly impacting data analysis pipelines, predictive modeling outcomes, and the reliability ...
ABSTRACT: Missing data remains a persistent and pervasive challenge across a wide range of domains, significantly impacting data analysis pipelines, predictive modeling outcomes, and the reliability ...
This repository contains code to reproduce the experiments in the KDD 2025 paper "Explaining GNN Explanations With Edge Gradients", including the Occlusion, Layerwise Occlusion, and Layerwise Gradient ...
1 School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China 2 School of Information Engineering, East University of Heilongjiang, Harbin, China Recognizing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback