.png){kind=icon}
返回
Self-supervised generative learning for sequential data prediction
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-023-04578-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
For many real world applications, such as stock price prediction and video frame synthesis, sequential data prediction is a fundamental and challenging task. Considering the temporal features of sequential data, existing approaches generally adopt recurrent neural network and its variants for the prediction. However, for sequences with complex structure, these approaches cannot guarantee to obtain promising results. In this paper, to address the above issue, we formulate sequential data prediction as a self-supervised generative learning problem. Concretely, we design a generator to learn the distribution of the sequential data and generate the predicted values, as well as a discriminator to judge whether or not the input sequential data are real or fake. Based on this proposed framework and the adversarial learning scheme, we develop the corresponding networks for vector inputs and high-order tensor inputs, respectively, which are respectively named vector generative network (VGN) and high-order tensor generative network (HTGN). Extensive experiments on five stock price prediction datasets and two video frame prediction datasets demonstrate the effectiveness of our framework, and its advantages over the state-of-the-art approaches. Our main code and the used data have been shared at https://github.com/xsavagek/SSGL.
Keyword:
Sequential data prediction
Self-supervised learning
Generative learning
Vector Generative Network (VGN)
High-order Tensor Generative Network (HTGN)
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
On the Development and Applications of Cellulosic Nanofibrillar and Nanocrystalline Materials纤维素纳米原纤和纳米晶材料的发展与应用
PREAI
分享收藏
GRU-based capsule network with an improved loss for personnel performance prediction基于改进损失的GRU胶囊网络用于人员绩效预测.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏
Features injected recurrent neural networks for short-term traffic speed predictionNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容