# Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering

arXiv: https://arxiv.org/abs/2607.10548 · HTML: https://mlsanity.com/paper/2607.10548/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [Mixture Models for Diverse Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/1902.07816/) (2019)
- [ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding](https://mlsanity.com/paper/2109.04380/) (2021)
- [Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models](https://mlsanity.com/paper/2412.14528/) (2024)
- [Self-Taught Convolutional Neural Networks for Short Text Clustering](https://mlsanity.com/paper/1701.00185/) (2017)
- [Text Clustering with Large Language Model Embeddings](https://mlsanity.com/paper/2403.15112/) (2024)
- [Enhancement of Short Text Clustering by Iterative Classification](https://mlsanity.com/paper/2001.11631/) (2020)
- [Co-clustering through Optimal Transport](https://mlsanity.com/paper/1705.06189/) (2017)
- [P2OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering](https://mlsanity.com/paper/2401.09266/) (2024)
- [Robust clustering tools based on optimal transportation](https://mlsanity.com/paper/1607.01179/) (2016)
- [MN-DS: A Multilabeled News Dataset for News Articles Hierarchical Classification](https://mlsanity.com/paper/2212.12061/) (2022)
- [Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering](https://mlsanity.com/paper/2305.16335/) (2023)
- [A Large-Scale Real-World Evaluation of LLM-Based Virtual Teaching Assistant](https://mlsanity.com/paper/2506.17363/) (2025)
- [KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction](https://mlsanity.com/paper/2512.09365/) (2025)
- [Contrastive Learning Subspace for Text Clustering](https://mlsanity.com/paper/2408.14119/) (2024)
- [Discriminative Representation learning via Attention-Enhanced Contrastive Learning for Short Text Clustering](https://mlsanity.com/paper/2501.03584/) (2025)

## Abstract (arXiv)

Pseudo-labeling based on Optimal Transport (OT) has become an effective mechanism for enhancing short text clustering. Existing OT methods are short in modeling semantic consistencies between samples, which may assign different pseudo-labels to semantically similar samples. These erroneous pseudo-labels can cause the model to produce inferior clusters. This paper proposes a novel short text clustering framework, which remedies the neglect of semantic consistency in existing OT methods, generating reliable pseudo-labels to facilitate clustering. Specifically, the proposed approach first designs an instance-level attention mechanism to capture semantic relationships between samples, which are then integrated into the OT formulation to endow the transport process with neighborhood semantic awareness. By solving the proposed OT formulation, reliable pseudo-labels are obtained that simultaneously account for sample-to-sample semantic consistency and sample-to-cluster global structure information. These pseudo-labels are then used as supervisory signals to guide the model to achieve accurate clustering. Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art methods. The code is available at: hrefhttps://github.com/YZH0905/CAOT-STChttps://github.com/YZH0905/CAOT-STC.