Multi-Granularity Framework for Unsupervised Representation Learning of Time Series
Representation learning plays a critical role in the analysis of time series data and has high practical value across a wide range of applications. including trend analysis, time series data retrieval and forecasting. In practice, data confusion is a significant issue as it can considerably impact the effectiveness and accuracy of data analysis, machine learning models and decision-making processes. In general, previous studies did not consider the variability at various levels of granularity, thus resulting in inadequate information utilization, which further exacerbated the issue of data confusion. This paper proposes an unsupervised framework to realize multi-granularity representation learning for time series. Specifically, we employed a cross-granularity transformer to develop an association between fine- and coarse-grained representations. In addition, we introduced a retrieval task as an unsupervised training task to learn the multi-granularity representation of time series. Moreover, a novel loss function was designed to obtain the comprehensive multi-granularity representation of the time series via unsupervised learning. The experimental results revealed that the proposed framework demonstrates significant advantages over alternative representation learning models.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingRepresentation LearningRetrievalTime SeriesSimilar Papers 제목 키워드 기반
Revisiting Multi-Granularity Representation via Group Contrastive Learning for Unsupervised Vehicle Re-identification
Vehicle re-identification (Vehicle ReID) aims at retrieving vehicle images across disjoint surveillance camera views. The majority of vehicle ReID research is heavily reliant upon supervisory labels from specific human-c…
Contrastive LearningDomain AdaptationUnsupervised Domain AdaptationUnsupervised Vehicle Re-Identification+1Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning
The existing contrastive learning methods mainly focus on single-grained representation learning, e.g., part-level, object-level or scene-level ones, thus inevitably neglecting the transferability of representations on o…
Contrastive LearningInstance SegmentationKeypoint Detectionobject-detection+4Unsupervised Multi-Granularity Summarization
Text summarization is a user-preference based task. For one document, users often have different priorities for summary. Granularity level of the summary is a core component of these preferences. However, most existing s…
Abstractive Text SummarizationText SummarizationDivide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection
Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the gene…
Anomaly DetectionUnsupervised Anomaly DetectionUnsupervised Multi-Granularity Summarization
Text summarization is a user-preference based task, i.e., for one document, users often have different priorities for summary. As a key aspect of customization in summarization, granularity is used to measure the semanti…
Abstractive Text SummarizationText Summarization