medical-1

Graph Classification

3260 papers • 126 benchmarks • 313 datasets

Graph Classification is a task that involves classifying a graph-structured data into different classes or categories. Graphs are a powerful way to represent relationships and interactions between different entities, and graph classification can be applied to a wide range of applications, such as social network analysis, bioinformatics, and recommendation systems. In graph classification, the input is a graph, and the goal is to learn a classifier that can accurately predict the class of the graph. ( Image credit: Hierarchical Graph Pooling with Structure Learning )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in graph-classification-4

Trend

Dataset

Best Model

Actions

PROTEINS

MUTAG

NCI1

Libraries

Use these libraries to find graph-classification-4 models and implementations

benedekrozemberczki/karateclub

8 papers 2,092

Datasets

OGB

Subtasks

Isomorphism Testing Space group classification Crystal system classification

Most implemented papers

Graph Attention Networks

Adriana Romero, Yoshua Bengio, Petar Velickovic, Pietro Liò, Guillem Cucurull, Arantxa Casanova•Sun Oct 29 2017

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).