arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.18057cs.LG
收藏

面向时间序列分类的排序监督对比学习

Rank Supervised Contrastive Learning for Time Series Classification

School of Computing University of Connecticut Storrs, United States;Knight Foundation School of Computing;Information Sciences Florida International University Florida, United States;School of Computing University of Connecticut Storrs, United Statse

Qianying Ren, Dongsheng Luo, Dongjin Song

AI总结:

针对现有对比学习忽略正样本细粒度排序相似性的问题,提出RankSCL框架,通过嵌入空间定向增强、样本对筛选及排序损失实现时间序列分类,在UCR、UEA共158个数据集上取得SOTA性能。

摘要:

近年来,各类对比学习技术已被开发用于时间序列数据分类,且展现出可观的性能。其通用范式是利用合适的增强方式、构建合理的正样本,使编码器能在特征空间中将相似数据点映射得更近,同时将不相似数据点推得更远,从而生成鲁棒且具判别性的表征。尽管该方法有效,但正样本的细粒度相对相似性(如排序)信息在很大程度上被忽略,在标记样本有限的情况下尤其如此。为此,我们提出排序监督对比学习(Rank Supervised Contrastive Learning,RankSCL)用于时间序列分类。与传统对比学习框架不同,RankSCL在嵌入空间中对原始数据进行针对性增强,并采用特定过滤规则选择信息量更大的正负样本对。此外,我们设计了一种新颖的排序损失,为不同层级的正样本分配不同权重,使编码器能够提取同一类别的细粒度信息,并在不同类别间生成清晰的边界。在128个UCR数据集和30个UEA数据集上开展的全面实证研究表明,与现有基线方法相比,所提出的RankSCL可达到当前最优性能。

英文摘要:

Recently, various contrastive learning techniques have been developed to categorize time series data and exhibit promising performance. A general paradigm is to utilize appropriate augmentations and construct feasible positive samples such that the encoder can yield robust and discriminative representations by mapping similar data points closer together in the feature space while pushing dissimilar data points farther apart. Despite its efficacy, the fine-grained relative similarity (e.g., rank) information of positive samples is largely ignored, especially when labeled samples are limited. To this end, we present Rank Supervised Contrastive Learning (RankSCL) to perform time series classification. Different from conventional contrastive learning frameworks, RankSCL augments raw data in a targeted way in the embedding space and adopts certain filtering rules to select more informative positive and negative pairs of samples. Moreover, a novel rank loss is developed to assign different weights for different levels of positive samples, enable the encoder to extract the fine-grained information of the same class, and produce a clear boundary among different classes. Thoroughly empirical studies on 128 UCR datasets and 30 UEA datasets demonstrate that the proposed RankSCL can achieve state-of-the-art performance compared to existing baseline methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑