GitHub

Vision Graph Prompting via Semantic Low-Rank Decomposition

Official implementation of 'Vision Graph Prompting via Semantic Low-Rank Decomposition'. The paper has been accepted by ICML 2025. Vision GNN (ViG) demonstrates superior performance by representing ...

Did Edison accidentally make graphene in 1879?

To reproduce what Thomas Edison did, with the tools and knowledge we have now, is very exciting,” said co-author James Tour, ...
GitHub

Graph Positional Autoencoders as Self-supervised Learners (GraphPAE)

accelerate==0.33.0 numpy==1.24.4 ogb==1.3.6 pandas==2.2.3 PyYAML==6.0.2 rdkit_pypi==2022.9.5 scikit_learn==1.3.2 scipy==1.8.1 torch==2.1.2+cu121 torch_geometric==2.6.1 torch_scatter==2.1.2+pt21cu121 ...
IEEE

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

Abstract: Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series ...
IEEE

Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure

Abstract: Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely leveraged ...