Node Classification
782 papers with code • 122 benchmarks • 69 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 implementationsSubtasks
Latest papers
Entropy Aware Message Passing in Graph Neural Networks
Deep Graph Neural Networks struggle with oversmoothing.
OpenGraph: Towards Open Graph Foundation Models
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.
Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
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.
Pairwise Alignment Improves Graph Domain Adaptation
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.
Graph Parsing Networks
GPN benefits from the discrete assignments generated by the graph parsing algorithm, allowing good memory efficiency while preserving node information intact.
A Simple and Yet Fairly Effective Defense for Graph Neural Networks
Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results.
Can GNN be Good Adapter for LLMs?
In terms of efficiency, the GNN adapter introduces only a few trainable parameters and can be trained with low computation costs.
Endowing Pre-trained Graph Models with Provable Fairness
Furthermore, with GraphPAR, we quantify whether the fairness of each node is provable, i. e., predictions are always fair within a certain range of sensitive attribute semantics.
Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph
In this paper, we argue that properly fetching and condensing the background nodes from massive web graph data might be a more economical shortcut to tackle the obstacles fundamentally.
GraSSRep: Graph-Based Self-Supervised Learning for Repeat Detection in Metagenomic Assembly
Additionally, our experiments with synthetic metagenomic datasets reveal that incorporating the graph structure and the GNN enhances our detection performance.