TY - GEN
T1 - Towards better forecasting by fusing near and distant future visions
AU - Cheng, Jiezhu
AU - Huang, Kaizhu
AU - Zheng, Zibin
N1 - Funding Information:
This paper was supported by the National Key Research and Development Program (2016YFB1000101), the National Natural Science Foundation of China (61722214, U1811462, 61876155), the Guangdong Province Universities and Colleges Pearl River Scholar Funded Scheme (2016) and Key Program Special Fund in XJTLU under no. KSF-A-01, KSF-E-26 and KSF-P-02.
Publisher Copyright:
© 2020, Association for the Advancement of Artificial Intelligence.
PY - 2020
Y1 - 2020
N2 - Multivariate time series forecasting is an important yet challenging problem in machine learning. Most existing approaches only forecast the series value of one future moment, ignoring the interactions between predictions of future moments with different temporal distance. Such a deficiency probably prevents the model from getting enough information about the future, thus limiting the forecasting accuracy. To address this problem, we propose Multi-Level Construal Neural Network (MLCNN), a novel multi-task deep learning framework. Inspired by the Construal Level Theory of psychology, this model aims to improve the predictive performance by fusing forecasting information (i.e., future visions) of different future time. We first use the Convolution Neural Network to extract multi-level abstract representations of the raw data for near and distant future predictions. We then model the interplay between multiple predictive tasks and fuse their future visions through a modified Encoder-Decoder architecture. Finally, we combine traditional Autoregression model with the neural network to solve the scale insensitive problem. Experiments on three real-world datasets show that our method achieves statistically significant improvements compared to the most state-of-the-art baseline methods, with average 4.59% reduction on RMSE metric and average 6.87% reduction on MAE metric.
AB - Multivariate time series forecasting is an important yet challenging problem in machine learning. Most existing approaches only forecast the series value of one future moment, ignoring the interactions between predictions of future moments with different temporal distance. Such a deficiency probably prevents the model from getting enough information about the future, thus limiting the forecasting accuracy. To address this problem, we propose Multi-Level Construal Neural Network (MLCNN), a novel multi-task deep learning framework. Inspired by the Construal Level Theory of psychology, this model aims to improve the predictive performance by fusing forecasting information (i.e., future visions) of different future time. We first use the Convolution Neural Network to extract multi-level abstract representations of the raw data for near and distant future predictions. We then model the interplay between multiple predictive tasks and fuse their future visions through a modified Encoder-Decoder architecture. Finally, we combine traditional Autoregression model with the neural network to solve the scale insensitive problem. Experiments on three real-world datasets show that our method achieves statistically significant improvements compared to the most state-of-the-art baseline methods, with average 4.59% reduction on RMSE metric and average 6.87% reduction on MAE metric.
UR - http://www.scopus.com/inward/record.url?scp=85101489444&partnerID=8YFLogxK
U2 - 10.1609/aaai.v34i04.5766
DO - 10.1609/aaai.v34i04.5766
M3 - Conference Proceeding
AN - SCOPUS:85101489444
T3 - AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
SP - 3593
EP - 3600
BT - AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
PB - AAAI press
T2 - 34th AAAI Conference on Artificial Intelligence, AAAI 2020
Y2 - 7 February 2020 through 12 February 2020
ER -