IOCC: Aligning Semantic and Cluster Centers for Few-shot Short Text Clustering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916887580901376 |
|---|---|
| author | Yin, Jixuan Yao, Zhihao Huo, Wenshuai Yu, Xinmiao Feng, Xiaocheng Li, Bo |
| author_facet | Yin, Jixuan Yao, Zhihao Huo, Wenshuai Yu, Xinmiao Feng, Xiaocheng Li, Bo |
| contents | In clustering tasks, it is essential to structure the feature space into clear, well-separated distributions. However, because short text representations have limited expressiveness, conventional methods struggle to identify cluster centers that truly capture each category's underlying semantics, causing the representations to be optimized in suboptimal directions. To address this issue, we propose IOCC, a novel few-shot contrastive learning method that achieves alignment between the cluster centers and the semantic centers. IOCC consists of two key modules: Interaction-enhanced Optimal Transport (IEOT) and Center-aware Contrastive Learning (CACL). Specifically, IEOT incorporates semantic interactions between individual samples into the conventional optimal transport problem, and generate pseudo-labels. Based on these pseudo-labels, we aggregate high-confidence samples to construct pseudo-centers that approximate the semantic centers. Next, CACL optimizes text representations toward their corresponding pseudo-centers. As training progresses, the collaboration between the two modules gradually reduces the gap between cluster centers and semantic centers. Therefore, the model will learn a high-quality distribution, improving clustering performance. Extensive experiments on eight benchmark datasets show that IOCC outperforms previous methods, achieving up to 7.34\% improvement on challenging Biomedical dataset and also excelling in clustering stability and efficiency. The code is available at: https://anonymous.4open.science/r/IOCC-C438. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06126 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IOCC: Aligning Semantic and Cluster Centers for Few-shot Short Text Clustering Yin, Jixuan Yao, Zhihao Huo, Wenshuai Yu, Xinmiao Feng, Xiaocheng Li, Bo Methodology Machine Learning In clustering tasks, it is essential to structure the feature space into clear, well-separated distributions. However, because short text representations have limited expressiveness, conventional methods struggle to identify cluster centers that truly capture each category's underlying semantics, causing the representations to be optimized in suboptimal directions. To address this issue, we propose IOCC, a novel few-shot contrastive learning method that achieves alignment between the cluster centers and the semantic centers. IOCC consists of two key modules: Interaction-enhanced Optimal Transport (IEOT) and Center-aware Contrastive Learning (CACL). Specifically, IEOT incorporates semantic interactions between individual samples into the conventional optimal transport problem, and generate pseudo-labels. Based on these pseudo-labels, we aggregate high-confidence samples to construct pseudo-centers that approximate the semantic centers. Next, CACL optimizes text representations toward their corresponding pseudo-centers. As training progresses, the collaboration between the two modules gradually reduces the gap between cluster centers and semantic centers. Therefore, the model will learn a high-quality distribution, improving clustering performance. Extensive experiments on eight benchmark datasets show that IOCC outperforms previous methods, achieving up to 7.34\% improvement on challenging Biomedical dataset and also excelling in clustering stability and efficiency. The code is available at: https://anonymous.4open.science/r/IOCC-C438. |
| title | IOCC: Aligning Semantic and Cluster Centers for Few-shot Short Text Clustering |
| topic | Methodology Machine Learning |
| url | https://arxiv.org/abs/2508.06126 |