Graph Neural Lasso for Dynamic Network Regression

Abstract

The regression of multiple inter-connected sequence data is a problem in various disciplines. Formally, we name the regression problem of multiple inter-connected data entities as the "dynamic network regression" in this paper. Within the problem of stock forecasting or traffic speed prediction, we need to consider both the trends of the entities and the relationships among the entities. A majority of existing approaches can't capture that information together. Some of the approaches are proposed to deal with the sequence data, like LSTM. The others use the prior knowledge in a network to get a fixed graph structure and do prediction on some unknown entities, like GCN. To overcome the limitations in those methods, we propose a novel graph neural network, namely Graph Neural Lasso (GNL), to deal with the dynamic network problem. GNL extends the GDU (gated diffusive unit) as the base neuron to capture the information behind the sequence. Rather than using a fixed graph structure, GNL can learn the dynamic graph structure automatically. By adding the attention mechanism in GNL, we can learn the dynamic relations among entities within each network snapshot. Combining these two parts, GNL is able to model the dynamic network problem well. Experimental results provided on two networked sequence datasets, i.e., Nasdaq-100 and METR-LA, show that GNL can address the network regression problem very well and is also very competitive among the existing approaches.

arXiv comment9 pages

References in corpus (10)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Semi-Supervised Classification with Graph Convolutional Networks
• End to End Learning for Self-Driving Cars
• Discrete Signal Processing on Graphs
• Learning graphs from data: A signal representation perspective
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach
• On the Convexity of Latent Social Network Inference
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

Cited by in corpus (1)

• Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview