提出一种融合模糊聚类与对比学习的时序数据聚类方法，提升无监督学习效果。
Fuzzy Cluster-Aware Contrastive Clustering for Time Series
- 设计三视图数据增强和聚类感知负样本生成机制，增强特征表示能力。
- 在40个基准数据集上优于8种基线方法，平均性能提升显著。
- 适合处理物联网等场景下的海量无标签时序数据，可广泛用于异常检测与模式发现。
物联网（IoT）驱动下，未标注时序数据呈快速增长趋势，给挖掘潜在模式带来挑战。传统无监督聚类方法难以捕捉时序数据的复杂特性。近期基于深度学习的聚类方法虽有效，但在表征学习和聚类目标融合方面仍存在不足。为此，我们提出一种模糊聚类感知的对比聚类框架（FCACC），联合优化表征学习与聚类过程。该方法引入新颖的三视图数据增强策略，利用时序数据的多种特征提升特征提取能力；同时提出聚类感知的硬负样本生成机制，动态利用聚类结构信息构建高质量负样本，增强模型判别力。通过模糊聚类动态生成聚类结构以引导对比学习，实现更精准的聚类结果。在40个基准数据集上的大量实验表明，FCACC优于8种选定基线方法，为无监督时序学习提供了有效解决方案。
原文摘要 · Abstract (English)
The rapid growth of unlabeled time series data, driven by the Internet of Things (IoT), poses significant challenges in uncovering underlying patterns. Traditional unsupervised clustering methods often fail to capture the complex nature of time series data. Recent deep learning-based clustering approaches, while effective, struggle with insufficient representation learning and the integration of clustering objectives. To address these issues, we propose a fuzzy cluster-aware contrastive clustering framework (FCACC) that jointly optimizes representation learning and clustering. Our approach introduces a novel three-view data augmentation strategy to enhance feature extraction by leveraging various characteristics of time series data. Additionally, we propose a cluster-aware hard negative sample generation mechanism that dynamically constructs high-quality negative samples using clustering structure information, thereby improving the model's discriminative ability. By leveraging fuzzy clustering, FCACC dynamically generates cluster structures to guide the contrastive learning process, resulting in more accurate clustering. Extensive experiments on 40 benchmark datasets show that FCACC outperforms the selected baseline methods (eight in total), providing an effective solution for unsupervised time series learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。