mlsanityData to 7 Oct 2026

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

arXiv 2108.03400 ↗First posted 7 Aug 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 is 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 incorporates 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 the most popular GNNs on node-level prediction tasks. 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 yield 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 a relatively high number of nodes and lower mean degree of connectivity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 7 Aug 2021.

Builds on

19 of 32 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2018Link Prediction Based on Graph Neural Networkscited by 829
  5. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  6. 2019Position-aware Graph Neural Networkscited by 203
  7. 2018Deep Multi-View Spatial-Temporal Network for Taxi Demand Predictioncited by 162
  8. 2018Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecastingcited by 145
  9. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  10. 2018Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Predictioncited by 61
  11. 2014PageRank beyond the Webcited by 51
  12. 2017Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networkscited by 35
7 more
  1. 2020Multiscale Dynamic Human Mobility Flow Dataset in the U.S. during the COVID-19 Epidemiccited by 27
  2. 2020Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNNcited by 23
  3. 2020A Survey on Dynamic Network Embeddingcited by 11
  4. 2015Eigenvector-Based Centrality Measures for Temporal Networkscited by 4
  5. 2020Node-Centric Graph Learning from Data for Brain State Identificationcited by 3
  6. 2017Case studies in network community detectioncited by 1
  7. 2021Estimation of Missing Data in Intelligent Transportation Systemcited by 1

Built on by

Not cited yet.