Research map / Graph learning / Graph self-supervised learning
Graph-augmented and Over-smoothing-resistant Contrastive Clustering for Short Text
Zijian Zheng, Tao Ai, Yonghe Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add graph-augmented representation and over-smoothing resistance (ablation) | GOCC · SearchSnippets | ACC: 75.86 -> 85.27 | Improved |
| add graph-augmented sentence representation (ablation) | GOCC · SearchSnippets | ACC: 75.61 -> 85.27 | Improved |
| add graph-augmented sentence representation (ablation) | GOCC · AgNews | ACC: 86.35 -> 87.68 | Improved |
| add intermediate-layer negatives against over-smoothing (ablation) | GOCC · GoogleNews-S | ACC: 67.25 -> 78.36 | Improved |
| add intermediate-layer negatives against over-smoothing (ablation) | GOCC · Tweet | ACC: 81.51 -> 81.84 | No clear effect |
| add target-driven clustering optimization (ablation) | GOCC · Tweet | ACC: 60.24 -> 81.84 | Improved |
| add sentence-level graph view (ablation) | GOCC · SearchSnippets | ACC: 75.61 -> 83.23 | Improved |
| add cluster-level view on top of sentence-level view (ablation) | GOCC · SearchSnippets | ACC: 83.23 -> 85.27 | Improved |
| add cluster-level view on top of sentence-level view (ablation) | GOCC · GoogleNews-S | ACC: 77.98 -> 78.36 | No clear effect |
| GOCC vs RSTC (pseudo-label baseline) | GOCC · GoogleNews-S | ACC: 76.01 vs 78.36 ACC; 88.27 vs 88.63 NMI | Mixed |
| use BERT with 20% word substitution for contextual augmentation (ablation) | GOCC · augmentation study | ACC | Improved |
| use RoBERTa instead of BERT as contextual augmenter (ablation) | GOCC · augmentation study | ACC | No clear effect |
Closest papers by meaning
- Improved Graph Contrastive Learning for Short Text Classification (AAAI 2024 · similarity 0.90)
- A Simple Graph Contrastive Learning Framework for Short Text Classification (AAAI 2025 · similarity 0.88)
- Deep Contrastive Graph Learning with Clustering-Oriented Guidance (AAAI 2024 · similarity 0.88)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.88)
- Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification (ICML 2025 · similarity 0.87)
- GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
