Multitask Learning for Time Series Data with 2D Convolution
Multitask learning (MTL) aims to develop a unified model that can handle a set of closely related tasks simultaneously. By optimizing the model across multiple tasks, MTL generally surpasses its non-MTL counterparts in terms of generalizability. Although MTL has been extensively researched in various domains such as computer vision, natural language processing, and recommendation systems, its application to time series data has received limited attention. In this paper, we investigate the application of MTL to the time series classification (TSC) problem. However, when we integrate the state-of-the-art 1D convolution-based TSC model with MTL, the performance of the TSC model actually deteriorates. By comparing the 1D convolution-based models with the Dynamic Time Warping (DTW) distance function, it appears that the underwhelming results stem from the limited expressive power of the 1D convolutional layers. To overcome this challenge, we propose a novel design for a 2D convolution-based model that enhances the model's expressiveness. Leveraging this advantage, our proposed method outperforms competing approaches on both the UCR Archive and an industrial transaction TSC dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Dynamic Time WarpingRecommendation SystemsTime SeriesTime Series ClassificationSimilar Papers 제목 키워드 기반
A Time Series Multitask Framework Integrating a Large Language Model, Pre-Trained Time Series Model, and Knowledge Graph
Time series analysis is crucial in fields like finance, transportation, and industry. However, traditional models often focus solely on temporal features, limiting their ability to capture underlying information. This pa…
Anomaly DetectionDecoderImputationKnowledge Graphs+6Aspect-based Opinion Summarization with Convolutional Neural Networks
This paper considers Aspect-based Opinion Summarization (AOS) of reviews on particular products. To enable real applications, an AOS system needs to address two core subtasks, aspect extraction and sentiment classificati…
Aspect ExtractionClassificationGeneral ClassificationOpinion Summarization+4OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image video audio text depth point cloud ti…
3D Point Cloud ClassificationAction ClassificationAction RecognitionAudio Classification+6OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image, video, audio, text, depth, point cloud, …
Massively Multitask Networks for Drug Discovery
Massively multitask neural architectures provide a learning framework for drug discovery that synthesizes information from many distinct biological sources. To train these architectures at scale, we gather large amounts …
Drug Discovery