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 ...
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

Semisupervised Cross-Scale Graph Prototypical Network for Hyperspectral Image Classification

Abstract: In practice, the acquirement of labeled samples for hyperspectral image (HSI) is time-consuming and labor-intensive. It frequently induces the trouble of model overfitting and performance ...
New York Magazine

I’m Also Very Picky About My Paper

As with my favorite pens, my list of favorite paper is entirely subjective. The quality of the products, however, is not. I ...
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 ...