TVNet: A Novel Time Series Analysis Method Based on Dynamic Convolution and 3D-Variation
This addresses the problem of improving CNN efficiency and performance for time series analysis, offering a competitive alternative to Transformer and MLP models, though it appears incremental as it builds on existing CNN frameworks.
The paper tackled the underperformance of CNvolutional Neural Networks (CNNs) in time series analysis by proposing TVNet, a dynamic convolutional network based on a novel 3D reshaping technique, which achieved state-of-the-art results in five key tasks while maintaining computational efficiency.
With the recent development and advancement of Transformer and MLP architectures, significant strides have been made in time series analysis. Conversely, the performance of Convolutional Neural Networks (CNNs) in time series analysis has fallen short of expectations, diminishing their potential for future applications. Our research aims to enhance the representational capacity of Convolutional Neural Networks (CNNs) in time series analysis by introducing novel perspectives and design innovations. To be specific, We introduce a novel time series reshaping technique that considers the inter-patch, intra-patch, and cross-variable dimensions. Consequently, we propose TVNet, a dynamic convolutional network leveraging a 3D perspective to employ time series analysis. TVNet retains the computational efficiency of CNNs and achieves state-of-the-art results in five key time series analysis tasks, offering a superior balance of efficiency and performance over the state-of-the-art Transformer-based and MLP-based models. Additionally, our findings suggest that TVNet exhibits enhanced transferability and robustness. Therefore, it provides a new perspective for applying CNN in advanced time series analysis tasks.