RECORD
Learning Uniform Clusters on Hypersphere for Deep Graph-level Clustering
Machine Learning · Submitted 23 Nov 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Our empirical study on eight well-known datasets demonstrates that UDGC significantly outperforms the state-of-the-art models.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Graph clustering has been popularly studied in recent years. However, most existing graph clustering methods focus on node-level clustering, i.e., grouping nodes in a single graph into clusters. In contrast, graph-level clustering, i.e., grouping multiple graphs into clusters, remains largely unexplored. Graph-level clustering is critical in a variety of real-world applications, such as, properties prediction of molecules and community analysis in social networks. However, graph-level clustering is challenging due to the insufficient discriminability of graph-level representations, and the insufficient discriminability makes deep clustering be more likely to obtain degenerate solutions (cluster collapse). To address the issue, we propose a novel deep graph-level clustering method called Uniform Deep Graph Clustering (UDGC). UDGC assigns instances evenly to different clusters and then scatters those clusters on unit hypersphere, leading to a more uniform cluster-level distribution and a slighter cluster collapse. Specifically, we first propose Augmentation-Consensus Optimal Transport (ACOT) for generating uniformly distributed and reliable pseudo labels for partitioning clusters. Then we adopt contrastive learning to scatter those clusters. Besides, we propose Center Alignment Optimal Transport (CAOT) for guiding the model to learn better parameters, which further promotes the cluster performance. Our empirical study on eight well-known datasets demonstrates that UDGC significantly outperforms the state-of-the-art models.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Graph clustering has been popularly studied in recent years. | background 1.00 | 0.03 | 0.01 | asserted 1.00 |
| s1 | However, most existing graph clustering methods focus on node-level clustering, i.e., grouping nodes in a single graph into clusters. | background 0.68 | 0.05 | 0.01 | asserted 0.99 |
| s2 | In contrast, graph-level clustering, i.e., grouping multiple graphs into clusters, remains largely unexplored. | gap 0.99 | 0.06 | 0.02 | asserted 0.99 |
| s3 | Graph-level clustering is critical in a variety of real-world applications, such as, properties prediction of molecules and community analysis in social networks. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s4 | However, graph-level clustering is challenging due to the insufficient discriminability of graph-level representations, and the insufficient discriminability makes deep clustering be more likely to obtain degenerate solutions (cluster collapse). | background 0.60 | 0.12 | 0.04 | asserted 0.59 |
| s5 | To address the issue, we propose a novel deep graph-level clustering method called Uniform Deep Graph Clustering (UDGC). | contribution 0.96 | 0.85 | 0.07 | asserted 0.99 |
| s6 | UDGC assigns instances evenly to different clusters and then scatters those clusters on unit hypersphere, leading to a more uniform cluster-level distribution and a slighter cluster collapse. | method 0.86 | 0.79 | 0.18 | asserted 0.95 |
| s7 | Specifically, we first propose Augmentation-Consensus Optimal Transport (ACOT) for generating uniformly distributed and reliable pseudo labels for partitioning clusters. | method 0.90 | 0.91 | 0.03 | asserted 1.00 |
| s8 | Then we adopt contrastive learning to scatter those clusters. | method 0.99 | 0.90 | 0.03 | asserted 0.97 |
| s9 | Besides, we propose Center Alignment Optimal Transport (CAOT) for guiding the model to learn better parameters, which further promotes the cluster performance. | method 0.83 | 0.91 | 0.05 | asserted 0.97 |
| s10 | Our empirical study on eight well-known datasets demonstrates that UDGC significantly outperforms the state-of-the-art models. | result 1.00 | 0.97 | 0.83 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Graph clustering has been popularly studied in recent years. However, most existing graph clustering methods focus on node-level clustering, i.e., grouping nodes in a single graph into clusters. In contrast, graph-level clustering, i.e., grouping multiple graphs into clusters, remains largely unexplored. Graph-level clustering is critical in a variety of real-world applications, such as, properties prediction of molecules and community analysis in social networks. However, graph-level clustering is challenging due to the insufficient discriminability of graph-level representations, and the insufficient discriminability makes deep clustering be more likely to obtain degenerate solutions (cluster collapse). To address the issue, we propose a novel deep graph-level clustering method called Uniform Deep Graph Clustering (UDGC). UDGC assigns instances evenly to different clusters and then scatters those clusters on unit hypersphere, leading to a more uniform cluster-level distribution and a slighter cluster collapse. Specifically, we first propose Augmentation-Consensus Optimal Transport (ACOT) for generating uniformly distributed and reliable pseudo labels for partitioning clusters. Then we adopt contrastive learning to scatter those clusters. Besides, we propose Center Alignment Optimal Transport (CAOT) for guiding the model to learn better parameters, which further promotes the cluster performance. Our empirical study on eight well-known datasets demonstrates that UDGC significantly outperforms the state-of-the-art models.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.