Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.

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

[2]  Kristian Kersting,et al.  Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[3]  Yixin Chen,et al.  An End-to-End Deep Learning Architecture for Graph Classification , 2018, AAAI.

[4]  Sergey Ivanov,et al.  Anonymous Walk Embeddings , 2018, ICML.

[5]  Edwin R. Hancock,et al.  Attributed Graph Kernels Using the Jensen-Tsallis q-Differences , 2014, ECML/PKDD.

[6]  Donald F. Towsley,et al.  Diffusion-Convolutional Neural Networks , 2015, NIPS.

[7]  Pinar Yanardag,et al.  Deep Graph Kernels , 2015, KDD.

[8]  Karsten M. Borgwardt,et al.  The skew spectrum of graphs , 2008, ICML '08.

[9]  Edwin R. Hancock,et al.  Graph Characterization via Ihara Coefficients , 2011, IEEE Transactions on Neural Networks.

[10]  Mathias Niepert,et al.  Learning Convolutional Neural Networks for Graphs , 2016, ICML.

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Hisashi Kashima,et al.  Marginalized Kernels Between Labeled Graphs , 2003, ICML.

[13]  Edwin R. Hancock,et al.  Pattern Vectors from Algebraic Graph Theory , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Edwin R. Hancock,et al.  An Aligned Subtree Kernel for Weighted Graphs , 2015, ICML.

[15]  Nikos Komodakis,et al.  Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Ernest Valveny,et al.  Graph embedding in vector spaces by node attribute statistics , 2012, Pattern Recognit..

[17]  Martin Grohe,et al.  Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks , 2018, AAAI.

[18]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[19]  Nils M. Kriege,et al.  Subgraph Matching Kernels for Attributed Graphs , 2012, ICML.

[20]  Edwin R. Hancock,et al.  A Quantum-Inspired Similarity Measure for the Analysis of Complete Weighted Graphs , 2019, IEEE Transactions on Cybernetics.

[21]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[23]  Vincent Gripon,et al.  Generalizing the Convolution Operator to Extend CNNs to Irregular Domains , 2016, ArXiv.

[24]  Jingrui He,et al.  DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification , 2019, KDD.

[25]  Kurt Mehlhorn,et al.  Efficient graphlet kernels for large graph comparison , 2009, AISTATS.

[26]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.

[27]  Jian Sun,et al.  Accelerating Very Deep Convolutional Networks for Classification and Detection , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Edwin R. Hancock,et al.  Depth-based complexity traces of graphs , 2014, Pattern Recognit..

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

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

[31]  Zaïd Harchaoui,et al.  Image Classification with Segmentation Graph Kernels , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Alessandro Sperduti,et al.  Tree-Based Kernel for Graphs With Continuous Attributes , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Wenwu Zhu,et al.  Structural Deep Network Embedding , 2016, KDD.

[34]  Kaisheng Yao,et al.  Deep neural support vector machines for speech recognition , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[35]  Kurt Mehlhorn,et al.  Weisfeiler-Lehman Graph Kernels , 2011, J. Mach. Learn. Res..

[36]  Alexander Gammerman,et al.  Learning by Transduction , 1998, UAI.

[37]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Edwin R. Hancock,et al.  Learning Aligned-Spatial Graph Convolutional Networks for Graph Classification , 2019, ECML/PKDD.

[39]  Edwin R. Hancock,et al.  Local-global nested graph kernels using nested complexity traces , 2020, Pattern Recognit. Lett..

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

[41]  Michalis Vazirgiannis,et al.  A Degeneracy Framework for Graph Similarity , 2018, IJCAI.

[42]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[43]  Zhi-Li Zhang,et al.  Graph Capsule Convolutional Neural Networks , 2018, ArXiv.

[44]  Hans-Peter Kriegel,et al.  Shortest-path kernels on graphs , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[45]  Jaewoo Kang,et al.  Self-Attention Graph Pooling , 2019, ICML.

[46]  Lorenzo Livi,et al.  Concept Drift and Anomaly Detection in Graph Streams , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[47]  Jasper Snoek,et al.  Spectral Representations for Convolutional Neural Networks , 2015, NIPS.