Regularizing Semi-supervised Graph Convolutional Networks with a Manifold Smoothness Loss

Existing graph convolutional networks focus on the neighborhood aggregation scheme. When applied to semi-supervised learning, they often suffer from the overfitting problem as the networks are trained with the cross-entropy loss on a small potion of labeled data. In this paper, we propose an unsupervised manifold smoothness loss defined with respect to the graph structure, which can be added to the loss function as a regularization. We draw connections between the proposed loss with an iterative diffusion process, and show that minimizing the loss is equivalent to aggregate neighbor predictions with infinite layers. We conduct experiments on multi-layer perceptron and existing graph networks, and demonstrate that adding the proposed loss can improve the performance consistently.

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

[2]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[3]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[4]  Xiao-Ming Wu,et al.  Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.

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

[6]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

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

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

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

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

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

[12]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[13]  Qi Tian,et al.  Regularized Diffusion Process for Visual Retrieval , 2017, AAAI.

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

[15]  Stephan Günnemann,et al.  Personalized Embedding Propagation: Combining Neural Networks on Graphs with Personalized PageRank , 2018, ArXiv.

[16]  Bin Luo,et al.  Data Representation and Learning With Graph Diffusion-Embedding Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

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

[19]  Stephan Günnemann,et al.  Predict then Propagate: Graph Neural Networks meet Personalized PageRank , 2018, ICLR.

[20]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[21]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[23]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[24]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[26]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[27]  Ken-ichi Kawarabayashi,et al.  Representation Learning on Graphs with Jumping Knowledge Networks , 2018, ICML.