Published on Mon Oct 14 2019

Adaptive Transfer Learning of Multi-View Time Series Classification

Donglin Zhan, Shiyu Yi, Dongli Xu, Xiao Yu, Denglin Jiang, Siqi Yu, Haoting Zhang, Wenfang Shangguan, Weihua Zhang

Time Series Classification (TSC) has been an important and challenging task in data mining. Transfer learning has been widely applied in computer vision and natural language processing applications to improve deep neurological network's generalization capabilities.

0
0
0
Abstract

Time Series Classification (TSC) has been an important and challenging task in data mining, especially on multivariate time series and multi-view time series data sets. Meanwhile, transfer learning has been widely applied in computer vision and natural language processing applications to improve deep neural network's generalization capabilities. However, very few previous works applied transfer learning framework to time series mining problems. Particularly, the technique of measuring similarities between source domain and target domain based on dynamic representation such as density estimation with importance sampling has never been combined with transfer learning framework. In this paper, we first proposed a general adaptive transfer learning framework for multi-view time series data, which shows strong ability in storing inter-view importance value in the process of knowledge transfer. Next, we represented inter-view importance through some time series similarity measurements and approximated the posterior distribution in latent space for the importance sampling via density estimation techniques. We then computed the matrix norm of sampled importance value, which controls the degree of knowledge transfer in pre-training process. We further evaluated our work, applied it to many other time series classification tasks, and observed that our architecture maintained desirable generalization ability. Finally, we concluded that our framework could be adapted with deep learning techniques to receive significant model performance improvements.

Sat Jun 26 2021
Machine Learning
Time-Series Representation Learning via Temporal and Contextual Contrasting
We propose an unsupervised representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data. The code is publicly available at https://github.com/emadeldeen24/TS- TCC.
0
0
0
Tue Sep 17 2019
Machine Learning
Self-boosted Time-series Forecasting with Multi-task and Multi-view Learning
A robust model for time series forecasting is highly important in many domains. To improve forecasting performance, traditional approaches usually require additional feature sets. In this paper, we propose a novel self-boosted mechanism in which the original time series is decomposed into multiple time series.
0
0
0
Fri Mar 26 2021
Machine Learning
Multi-source Transfer Learning with Ensemble for Financial Time Series Forecasting
0
0
0
Mon Nov 05 2018
Artificial Intelligence
Transfer learning for time series classification
Transfer learning for deep neural networks is the process of first training a network on a source dataset, and then transferring the learned features to a second network to be trained on a target dataset. This idea has been shown to improve deep neural network's generalization capabilities in many computer vision tasks such as image recognition.
0
0
0
Tue Oct 06 2020
Artificial Intelligence
A Transformer-based Framework for Multivariate Time Series Representation Learning
Pre-trained models can be potentially used for downstream tasks such as regression and classification, forecasting and missing value imputation. Unsupervised pre-training of our transformer models offers a substantial performance benefit over fully supervised learning.
1
2
25
Sun Feb 04 2018
Machine Learning
Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain Features
Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. We propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and clustering into a single end-to-end framework.
0
0
0