Graphsgraph-ml

Node Classification

Node classification — assigning labels to vertices in a graph using both node features and neighborhood structure — is the flagship task for Graph Neural Networks. GCN (Kipf & Welling, 2017) established the Cora/Citeseer/PubMed benchmark trinity, but these datasets are tiny by modern standards and results have saturated well above 85% accuracy. The field has moved toward large-scale heterogeneous graphs (ogbn-arxiv, ogbn-products from OGB) and the unsettled debate over whether simple MLPs with neighborhood features can match GNNs, as shown by SIGN and SGC ablations.

2
Datasets
38
Results
accuracy
Canonical metric
Canonical Benchmark

Cora

Citation network of scientific papers. 2708 nodes, 5429 edges, 7 classes. Classic GNN benchmark.

Primary metric: accuracy
View full leaderboard

Top 10

Leading models on Cora.

RankModelaccuracyYearSource
1
TAPE + RevGAT
92.92024paper
2
AuGLM (T5-large)
91.52024paper
3
ENGINE
91.52024paper
4
InstructGLM
90.82024paper
5
GLEM + RevGAT
88.62024paper
6
GCNLLMEmb
88.22025paper
7
LLaGA (Mistral-7B)
87.52024paper
8
SDGAT
85.32024paper
9
GCN* (tuned)
85.12024paper
10
GAT* (tuned)
84.62024paper

What were you looking for on Node Classification?

Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.

All datasets

2 datasets tracked for this task.

Related tasks

Other tasks in Graphs.

Reply within 48 hours · No newsletter

Didn't find what you came for?

Still looking for something on Node Classification? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.

Real humans read every message. We track what people are asking for and prioritize accordingly.