Node Classification

769 papers with code • 122 benchmarks • 68 datasets

Node Classification is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.

Node Classification models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like Cora, Citeseer, and Pubmed, among others, typically using Accuracy and F1.

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

Libraries

Use these libraries to find Node Classification models and implementations

Open-World Semi-Supervised Learning for Node Classification

ruckbreasoning/openima 18 Mar 2024

Open-world semi-supervised learning (Open-world SSL) for node classification, that classifies unlabeled nodes into seen classes or multiple novel classes, is a practical but under-explored problem in the graph community.

3
18 Mar 2024

L$^2$GC: Lorentzian Linear Graph Convolutional Networks For Node Classification

llqy123/LLGC-master 10 Mar 2024

Specifically, we map the learned features of graph nodes into hyperbolic space, and then perform a Lorentzian linear feature transformation to capture the underlying tree-like structure of data.

1
10 Mar 2024

Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling

cods-gcs/kgtosa 9 Mar 2024

We refer to this subgraph as a task-oriented subgraph (TOSG), which contains a subset of task-related node and edge types in G. Training the task using TOSG instead of G alleviates the excessive computation required for a large KG.

0
09 Mar 2024

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

wondergo2017/sild NeurIPS 2023

In this paper, we discover that there exist cases with distribution shifts unobservable in the time domain while observable in the spectral domain, and propose to study distribution shifts on dynamic graphs in the spectral domain for the first time.

3
08 Mar 2024

Entropy Aware Message Passing in Graph Neural Networks

oliver-lemke/entropy_aware_message_passing 7 Mar 2024

Deep Graph Neural Networks struggle with oversmoothing.

2
07 Mar 2024

OpenGraph: Towards Open Graph Foundation Models

hkuds/opengraph 2 Mar 2024

By effectively capturing the graph's underlying structure, these GNNs have shown great potential in enhancing performance in graph learning tasks, such as link prediction and node classification.

106
02 Mar 2024

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time

cornell-zhang/polynormer 2 Mar 2024

To enable the base model permutation equivariant, we integrate it with graph topology and node features separately, resulting in local and global equivariant attention models.

15
02 Mar 2024

Pairwise Alignment Improves Graph Domain Adaptation

graph-com/pair-align 2 Mar 2024

Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing.

6
02 Mar 2024

Graph Parsing Networks

lumia-group/graphparsingnetworks 22 Feb 2024

GPN benefits from the discrete assignments generated by the graph parsing algorithm, allowing good memory efficiency while preserving node information intact.

3
22 Feb 2024

A Simple and Yet Fairly Effective Defense for Graph Neural Networks

sennadir/noisygnn 21 Feb 2024

Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results.

1
21 Feb 2024