Missing Data Estimation in Temporal Multilayer Position-aware Graph Neural Network (TMP-GNN)

GNNs have been proven to perform highly effective in various node-level, edge-level, and graph-level prediction tasks in several domains. Existing approaches mainly focus on static graphs. However, many graphs change over time with their edge may disappear, or node / edge attribute may alter from one time to the other. It’s essential to consider such evolution in representation learning of nodes in time varying graphs. In this paper, we propose a Temporal Multi-layered Position-aware Graph Neural Network (TMP-GNN), a node embedding approach for dynamic graph that incorporate the interdependence of temporal relations into embedding computation. We evaluate the performance of TMP-GNN on two different representations of temporal multilayered graphs. The performance is assessed against most popular GNNs on node-level prediction task. Then, we incorporate TMP-GNN into a deep learning framework to estimate missing data and compare the performance with their corresponding competent GNNs from our former experiment, and a baseline method. Experimental results on four real-world datasets yields up to 58% of lower ROC AUC for pairwise node classification task, and 96% of lower MAE in missing feature estimation, particularly for graphs with relatively high number of nodes and lower mean degree of connectivity.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Stark C. Draper,et al.  Node-Centric Graph Learning From Data for Brain State Identification , 2020, IEEE Transactions on Signal and Information Processing over Networks.

[3]  Song Gao,et al.  Multiscale dynamic human mobility flow dataset in the U.S. during the COVID-19 epidemic , 2020, Scientific data.

[4]  Badri Adhikari.  DEEPCON: Protein Contact Prediction using Dilated Convolutional Neural Networks with Dropout , 2019 .

[5]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[6]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[7]  Yinhai Wang,et al.  Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting , 2018, IEEE Transactions on Intelligent Transportation Systems.

[8]  David F. Gleich,et al.  PageRank beyond the Web , 2014, SIAM Rev..

[9]  Saeedeh Parsaeefard,et al.  Estimation of Missing Data in Intelligent Transportation System , 2021, ArXiv.

[10]  V. Burris.  The Academic Caste System: Prestige Hierarchies in PhD Exchange Networks , 2004 .

[11]  Yixin Chen,et al.  Link Prediction Based on Graph Neural Networks , 2018, NeurIPS.

[12]  Robert E. Tarjan,et al.  Depth-First Search and Linear Graph Algorithms , 1972, SIAM J. Comput..

[13]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[14]  Li Li,et al.  Pattern Sensitive Prediction of Traffic Flow Based on Generative Adversarial Framework , 2019, IEEE Transactions on Intelligent Transportation Systems.

[15]  Zhiyong Cui,et al.  Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction , 2018, ArXiv.

[16]  J. Bourgain.  On lipschitz embedding of finite metric spaces in Hilbert space , 1985 .

[17]  Mason A. Porter,et al.  Eigenvector-Based Centrality Measures for Temporal Networks , 2015, Multiscale Model. Simul..

[18]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[19]  Jure Leskovec,et al.  Position-aware Graph Neural Networks , 2019, ICML.

[20]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[21]  Dane Taylor,et al.  Case studies in network community detection , 2017, The Oxford Handbook of Social Networks.

[22]  Jinsung Yoon,et al.  Estimating Missing Data in Temporal Data Streams Using Multi-Directional Recurrent Neural Networks , 2017, IEEE Transactions on Biomedical Engineering.