Dynamic Graph Convolutional Networks

Abstract In many different classification tasks it is required to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change over time. The goal is to exploit existing neural network architectures to model datasets that are best represented with graph structures that change over time. To the best of the authors’ knowledge, this task has not been addressed using these kinds of architectures. Two novel approaches are proposed, which combine Long Short-Term Memory networks and Graph Convolutional Networks to learn long short-term dependencies together with graph structure. The advantage provided by the proposed methods is confirmed by the results achieved on four real world datasets: an increase of up to 12 percentage points in Accuracy and F1 scores for vertex-based semi-supervised classification and up to 2 percentage points in Accuracy and F1 scores for graph-based supervised classification.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Lakhmi C. Jain,et al.  Recurrent Neural Networks: Design and Applications , 1999 .

[3]  Tido Röder,et al.  Documentation Mocap Database HDM05 , 2007 .

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

[5]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[6]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[7]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[9]  Yujiu Yang,et al.  Node Classification in Social Network via a Factor Graph Model , 2013, PAKDD.

[10]  Alessandro Rozza,et al.  Automated Pruning for Deep Neural Network Compression , 2017, 2018 24th International Conference on Pattern Recognition (ICPR).

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[13]  Xavier Bresson,et al.  Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks , 2017, NIPS.

[14]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[15]  Alessandro Rozza,et al.  A Novel Graph-Based Fisher Kernel Method for Semi-supervised Learning , 2014, 2014 22nd International Conference on Pattern Recognition.

[16]  Kevin G. Stanley,et al.  Temporal aggregation impacts on epidemiological simulations employing microcontact data , 2012, BMC Medical Informatics and Decision Making.

[17]  Franco Scarselli,et al.  Recursive neural networks learn to localize faces , 2005, Pattern Recognit. Lett..

[18]  Abhinav Gupta,et al.  Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Philip S. Yu,et al.  Inferring social roles and statuses in social networks , 2013, KDD.

[20]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[23]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[24]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Bo Wang,et al.  Dynamic Label Propagation for Semi-supervised Multi-class Multi-label Classification , 2013, 2013 IEEE International Conference on Computer Vision.

[26]  Yulong Pei,et al.  Node classification in dynamic social networks , 2016 .

[27]  Silvio Savarese,et al.  Structural-RNN: Deep Learning on Spatio-Temporal Graphs , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Xavier Bresson,et al.  Structured Sequence Modeling with Graph Convolutional Recurrent Networks , 2016, ICONIP.

[29]  Nitesh V. Chawla,et al.  Inferring user demographics and social strategies in mobile social networks , 2014, KDD.

[30]  Siome Goldenstein,et al.  Graph-based bag-of-words for classification , 2018, Pattern Recognit..

[31]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[32]  Lawrence B. Holder,et al.  Scalable SVM-Based Classification in Dynamic Graphs , 2014, 2014 IEEE International Conference on Data Mining.

[33]  Jing Liu,et al.  Image annotation via graph learning , 2009, Pattern Recognit..

[34]  Pierre Vandergheynst,et al.  Wavelets on Graphs via Spectral Graph Theory , 2009, ArXiv.

[35]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[36]  Jing Gao,et al.  Learning, Analyzing and Predicting Object Roles on Dynamic Networks , 2013, 2013 IEEE 13th International Conference on Data Mining.

[37]  Julie Fournet,et al.  Data on face-to-face contacts in an office building suggest a low-cost vaccination strategy based on community linkers , 2014, Network Science.

[38]  Hema Swetha Koppula,et al.  Learning human activities and object affordances from RGB-D videos , 2012, Int. J. Robotics Res..

[39]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.