通过扩散生成正负样本，提升复杂时间序列分类性能
A Contrastive Diffusion-based Network (CDNet) for Time Series Classification
- 用卷积网络模拟反向扩散过程，学习类内类间样本转移
- 在噪声、相似和多模态数据下，显著超越现有SOTA模型
- 适合处理高噪声或分布复杂的时序分类任务
深度学习模型因可扩展性和高效性被广泛用于时间序列分类（TSC），但在类别相似、多模态分布和噪声环境下性能下降。为此，我们提出CDNet——一种基于对比扩散的网络，通过学习的扩散过程生成有信息量的正负样本，增强现有分类器。与传统扩散模型仅去噪单个样本不同，CDNet通过卷积近似反向扩散步骤，学习样本间的转移关系（类内与类间）。我们设计了一种理论支撑的基于CNN的机制，实现去噪与模式覆盖，并引入不确定性加权复合损失以实现鲁棒训练。在UCR Archive和模拟数据集上的大量实验表明，CDNet显著提升当前最优（SOTA）深度学习分类器性能，尤其在噪声、类别相似和多模态条件下表现突出。
原文摘要 · Abstract (English)
Deep learning models are widely used for time series classification (TSC) due to their scalability and efficiency. However, their performance degrades under challenging data conditions such as class similarity, multimodal distributions, and noise. To address these limitations, we propose CDNet, a Contrastive Diffusion-based Network that enhances existing classifiers by generating informative positive and negative samples via a learned diffusion process. Unlike traditional diffusion models that denoise individual samples, CDNet learns transitions between samples--both within and across classes--through convolutional approximations of reverse diffusion steps. We introduce a theoretically grounded CNN-based mechanism to enable both denoising and mode coverage, and incorporate an uncertainty-weighted composite loss for robust training. Extensive experiments on the UCR Archive and simulated datasets demonstrate that CDNet significantly improves state-of-the-art (SOTA) deep learning classifiers, particularly under noisy, similar, and multimodal conditions.
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。