Node Clustering
62 papers with code • 19 benchmarks • 14 datasets
Benchmarks
These leaderboards are used to track progress in Node Clustering
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Node Clustering models and implementationsDatasets
IMDb Movie Reviews
Pubmed
Cora
Wiki Squirrel
Wiki-CS
Latest papers
PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning
Although graph mining research via heterogeneous graph neural networks has taken center stage, it remains unclear whether these approaches capture the heterogeneity of the PubMed database, a vast digital repository containing over 33 million articles.
Semantic-Fused Multi-Granularity Cross-City Traffic Prediction
zeonchen/sfmgtl
•
•
Accurate traffic prediction is essential for effective urban management and the improvement of transportation efficiency.
USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy.
Scalable Attributed-Graph Subspace Clustering
chakib401/SAGSC
•
•
Proceedings of the AAAI Conference on Artificial Intelligence, 37(6) 2023
Over recent years, graph convolutional networks emerged as powerful node clustering methods and have set state of the art results for this task.
AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network
pasalab/autoac
•
•
Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes.
Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
jianxiangyu/meow
•
•
In addition, we propose a variant model AdaMEOW that adaptively learns soft-valued weights of negative samples to further improve node representation.
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
Besides, we observe that learning from multiple philosophies enhances not only the task generalization but also the single task performances, demonstrating that PARETOGNN achieves better task generalization via the disjoint yet complementary knowledge learned from different philosophies.
MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian
sherylhyx/msgnn
•
•
In these experiments, we consider tasks related to signed information, tasks related to directional information, and tasks related to both signed and directional information.
A Representation Learning Framework for Property Graphs
yifan-h/pge
•
•
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2019
Representation learning on graphs, also called graph embedding, has demonstrated its significant impact on a series of machine learning applications such as classification, prediction and recommendation.
Geometry Contrastive Learning on Heterogeneous Graphs
hete-graph/cmhg
•
•
Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data.
