Graph U-Nets

We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operations are not natural on graph data. To address these challenges, we propose novel graph pooling (gPool) and unpooling (gUnpool) operations in this work. The gPool layer adaptively selects some nodes to form a smaller graph based on their scalar projection values on a trainable projection vector. We further propose the gUnpool layer as the inverse operation of the gPool layer. The gUnpool layer restores the graph into its original structure using the position information of nodes selected in the corresponding gPool layer. Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models.

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

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

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

[4]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[5]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Hans-Peter Kriegel,et al.  Protein function prediction via graph kernels , 2005, ISMB.

[7]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[8]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

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

[10]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[11]  Le Song,et al.  Discriminative Embeddings of Latent Variable Models for Structured Data , 2016, ICML.

[12]  Jure Leskovec,et al.  Predicting multicellular function through multi-layer tissue networks , 2017, Bioinform..

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

[14]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[15]  S. V. N. Vishwanathan,et al.  A Structural Smoothing Framework For Robust Graph Comparison , 2015, NIPS.

[16]  Yann LeCun,et al.  Stacked What-Where Auto-encoders , 2015, ArXiv.

[17]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[18]  P. Dobson,et al.  Distinguishing enzyme structures from non-enzymes without alignments. , 2003, Journal of molecular biology.

[19]  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).

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

[21]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[22]  Jonathan Masci,et al.  Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[25]  Han Zhao,et al.  Self-Adaptive Hierarchical Sentence Model , 2015, IJCAI.

[26]  Zhengyang Wang,et al.  Large-Scale Learnable Graph Convolutional Networks , 2018, KDD.

[27]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  한보형,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015 .

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

[30]  Yangqing Jia,et al.  Deep Convolutional Ranking for Multilabel Image Annotation , 2013, ICLR.

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

[32]  Heinrich Müller,et al.  SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[34]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[35]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[36]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[37]  Shuiwang Ji,et al.  Efficient and Invariant Convolutional Neural Networks for Dense Prediction , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[38]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

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

[40]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[41]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[42]  Sundeep Prabhakar Chepuri,et al.  Subsampling for graph power spectrum estimation , 2016, 2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM).

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

[44]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  Antonio G. Marques,et al.  Convolutional Neural Network Architectures for Signals Supported on Graphs , 2018, IEEE Transactions on Signal Processing.

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