About

The node classification task is one where the algorithm has to determine the labelling of samples (represented as nodes) by looking at the labels of their neighbours.

( Image credit: Fast Graph Representation Learning With PyTorch Geometric )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Latest papers without code

VersaGNN: a Versatile accelerator for Graph neural networks

4 May 2021

As GNNs operate on non-Euclidean data, their irregular data access patterns cause considerable computational costs and overhead on conventional architectures, such as GPU and CPU.

GRAPH GENERATION GRAPH MATCHING NODE CLASSIFICATION

WGCN: Graph Convolutional Networks with Weighted Structural Features

29 Apr 2021

Based on nodes' geometrical relationships in the latent space, WGCN differentiates latent, in-, and out-neighbors with an attention-based geometrical aggregation.

NODE CLASSIFICATION

Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification

28 Apr 2021

In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.

CLASSIFICATION GRAPH LEARNING NODE CLASSIFICATION

LGD-GCN: Local and Global Disentangled Graph Convolutional Networks

24 Apr 2021

In this paper, we introduce a novel Local and Global Disentangled Graph Convolutional Network (LGD-GCN) to capture both local and global information for graph disentanglement.

NODE CLASSIFICATION

SAS: A Simple, Accurate and Scalable Node Classification Algorithm

19 Apr 2021

Recent works have sought to address this problem using a two-stage approach, which first aggregates data along graph edges, then trains a classifier without using additional graph information.

CLASSIFICATION NODE CLASSIFICATION

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

14 Apr 2021

Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation.

CLASSIFICATION GRAPH CLASSIFICATION HIERARCHICAL STRUCTURE LINK PREDICTION NODE CLASSIFICATION

Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood

12 Apr 2021

In this paper, we propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.

LINK PREDICTION NODE CLASSIFICATION REPRESENTATION LEARNING

Edge: Enriching Knowledge Graph Embeddings with External Text

11 Apr 2021

Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods.

KNOWLEDGE GRAPH EMBEDDINGS KNOWLEDGE GRAPHS LINK PREDICTION NODE CLASSIFICATION

Explainability-based Backdoor Attacks Against Graph Neural Networks

8 Apr 2021

Backdoor attacks represent a serious threat to neural network models.

NODE CLASSIFICATION

Modeling Graph Node Correlations with Neighbor Mixture Models

29 Mar 2021

We propose a new model, the Neighbor Mixture Model (NMM), for modeling node labels in a graph.

IMAGE DENOISING LINK PREDICTION NODE CLASSIFICATION REPRESENTATION LEARNING