Research map / Label-efficient and robust learning / Recognition and long-tail
Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering
Zhihao Yao, Yuxuan Gu, Jixuan Yin, Bo Li
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 sample-to-sample semantic consistency (attention + cosine) (ablation) | CAOT clustering framework · StackOverflow | ACC: 80.31 -> 85.96 | Improved |
| add sample-to-sample semantic consistency (attention + cosine) (ablation) | CAOT clustering framework · SearchSnippets | ACC: 78.93 -> 80.12 | Improved |
| add sample-to-sample semantic consistency (attention + cosine) (ablation) | CAOT clustering framework · GoogleNews-TS | ACC: 81.27 -> 83.53 | Improved |
| add attention similarity to consistency term (ablation) | CAOT clustering framework · StackOverflow | ACC: 79.11 -> 85.96 | Improved |
| add attention similarity to consistency term (ablation) | CAOT clustering framework · SearchSnippets | ACC: 76.86 -> 80.12 | Improved |
| add static cosine similarity to consistency term (ablation) | CAOT clustering framework · StackOverflow | ACC: 83.52 -> 85.96 | Improved |
| add contrastive learning (ablation) | CAOT clustering framework · SearchSnippets | ACC: 56.65 -> 80.12 | Improved |
| add contrastive learning (ablation) | CAOT clustering framework · StackOverflow | ACC: 80.51 -> 85.96 | Improved |
| add pseudo-label loss L_P (instead of K-means) (ablation) | CAOT clustering framework · StackOverflow | ACC: 61.89 -> 85.96 | Improved |
| add pseudo-label loss L_P (instead of K-means) (ablation) | CAOT clustering framework · SearchSnippets | ACC: 79.13 -> 80.12 | Improved |
| replace conventional OT with CAOT (ablation) | CAOT clustering framework · GoogleNews-TS | ACC: 62.03 -> 83.53 | Improved |
| replace conventional OT with CAOT (ablation) | CAOT clustering framework · Tweet | ACC: 47.09 -> 82.36 | Improved |
Closest papers by meaning
- RPSC: Robust Pseudo-Labeling for Semantic Clustering (AAAI 2024 · similarity 0.87)
- P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering (ICLR 2024 · similarity 0.85)
- Local Graph Clustering with Noisy Labels (ICLR 2024 · similarity 0.84)
- Image Clustering with External Guidance (ICML 2024 · similarity 0.83)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.83)
- Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters (NeurIPS 2024 · similarity 0.83)
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.
