Browse > Graphs > Node Classification

Node Classification

98 papers with code ยท Graphs

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.

State-of-the-art leaderboards

Trend Dataset Best Method Paper title Paper Code Compare

Latest papers without code

Constant Curvature Graph Convolutional Networks

ICLR 2020

Interest has been rising lately towards methods representing data in non-Euclidean spaces, e. g. hyperbolic or spherical.

NODE CLASSIFICATION

Attributed Graph Learning with 2-D Graph Convolution

ICLR 2020

Graph convolutional neural networks have demonstrated promising performance in attributed graph learning, thanks to the use of graph convolution that effectively combines graph structures and node features for learning node representations.

NODE CLASSIFICATION REPRESENTATION LEARNING

Transfer Active Learning For Graph Neural Networks

ICLR 2020

Moreover, we also studied how to learn a universal policy for labeling nodes on graphs with multiple training graphs and then transfer the learned policy to unseen graphs.

ACTIVE LEARNING NODE CLASSIFICATION TRANSFER LEARNING

Attacking Graph Convolutional Networks via Rewiring

ICLR 2020

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification.

GRAPH CLASSIFICATION NODE CLASSIFICATION

Neural Subgraph Isomorphism Counting

ICLR 2020

In this paper, we study a new graph learning problem: learning to count subgraph isomorphisms.

LINK PREDICTION NODE CLASSIFICATION REPRESENTATION LEARNING

DropEdge: Towards Deep Graph Convolutional Networks on Node Classification

ICLR 2020

Over-fitting and over-smoothing are two main obstacles of developing deep Graph Convolutional Networks (GCNs) for node classification.

NODE CLASSIFICATION

Chordal-GCN: Exploiting sparsity in training large-scale graph convolutional networks

ICLR 2020

Despite the impressive success of graph convolutional networks (GCNs) on numerous applications, training on large-scale sparse networks remains challenging.

NODE CLASSIFICATION

Active Learning for Graph Neural Networks via Node Feature Propagation

16 Oct 2019

Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data.

ACTIVE LEARNING NODE CLASSIFICATION

Dynamic Self-training Framework for Graph Convolutional Networks

7 Oct 2019

Graph neural networks (GNN) such as GCN, GAT, MoNet have achieved state-of-the-art results on semi-supervised learning on graphs.

MODEL SELECTION NODE CLASSIFICATION

Graph Few-shot Learning via Knowledge Transfer

7 Oct 2019

Towards the challenging problem of semi-supervised node classification, there have been extensive studies.

FEW-SHOT LEARNING NODE CLASSIFICATION TRANSFER LEARNING