DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification
Time series classification is an important problem in real world. Due to its nonstationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributions. In this paper, we propose to view the time series classification problem from the distribution perspective. We argue that the temporal complexity attributes to the unknown latent distributions within. To this end, we propose DIVERSIFY to learn generalized representations for time series classification. DIVERSIFY takes an iterative process: it first obtains the worst-case distribution scenario via adversarial training, then matches the distributions between all segments. We also present some theoretical insights. Extensive experiments on gesture recognition, speech commands recognition, and sensor-based human activity recognition demonstrate that DIVERSIFY significantly outperforms other baselines while effectively characterizing the latent distributions by qualitative and quantitative analysis.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity RecognitionClassificationGesture RecognitionHuman Activity RecognitionTime SeriesTime Series AnalysisTime Series ClassificationSimilar Papers 제목 키워드 기반
DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization
Time series remains one of the most challenging modalities in machine learning research. The out-of-distribution (OOD) detection and generalization on time series tend to suffer due to its non-stationary property, i.e., …
Activity RecognitionGesture RecognitionHuman Activity RecognitionOut-of-Distribution Detection+3Out-of-Distribution Representation Learning for Time Series Classification
Time series classification is an important problem in real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributi…
Activity RecognitionClassificationGesture RecognitionHuman Activity Recognition+4Generalized Gradient Learning on Time Series under Elastic Transformations
The majority of machine learning algorithms assumes that objects are represented as vectors. But often the objects we want to learn on are more naturally represented by other data structures such as sequences and time se…
Dynamic Time WarpingTime SeriesTime Series AnalysisWildNet: Learning Domain Generalized Semantic Segmentation from the Wild
We present a new domain generalized semantic segmentation network named WildNet, which learns domain-generalized features by leveraging a variety of contents and styles from the wild. In domain generalization, the low ge…
Domain GeneralizationSemantic SegmentationTransparent Networks for Multivariate Time Series
Transparent models, which are machine learning models that produce inherently interpretable predictions, are receiving significant attention in high-stakes domains. However, despite much real-world data being collected a…
Additive modelsTime Series