Graph convolutional networks: analysis, improvements and results

In the current era of neural networks and big data, higher dimensional data is processed for automation of different application areas. Graphs represent a complex data organization in which dependencies between more than one object or activity occur. Due to the high dimensionality, this data creates challenges for machine learning algorithms. Graph convolutional networks were introduced to utilize the convolutional models concepts that shows good results. In this context, we enhanced two of the existing Graph convolutional network models by proposing four enhancements. These changes includes: hyper parameters optimization, convex combination of activation functions, topological information enrichment through clustering coefficients measure, and structural redesign of the network through addition of dense layers. We present extensive results on four state-of-art benchmark datasets. The performance is notable not only in terms of lesser computational cost compared to competitors, but also achieved competitive results for three of the datasets and state-of-the-art for the fourth dataset.

[1]  Hossein Mobahi,et al.  Deep Learning via Semi-supervised Embedding , 2012, Neural Networks: Tricks of the Trade.

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

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

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

[5]  Alessandro Rozza,et al.  Learning Combinations of Activation Functions , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[6]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

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

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

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

[10]  Arun Rajkumar,et al.  Lovasz Convolutional Networks , 2018, AISTATS.

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

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

[13]  Renjie Liao,et al.  Graph Partition Neural Networks for Semi-Supervised Classification , 2018, ICLR.

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

[15]  Stephan Günnemann,et al.  Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking , 2017, ICLR.

[16]  Nathan D. Cahill,et al.  Generalized relationships between characteristic path length, efficiency, clustering coefficients, and density , 2018, Social Network Analysis and Mining.

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

[18]  Koby Crammer,et al.  Graph-Based Transduction with Confidence , 2012, ECML/PKDD.

[19]  Jie Zhou,et al.  Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View , 2020, AAAI.

[20]  Stephan Günnemann,et al.  Dual-Primal Graph Convolutional Networks , 2018, ArXiv.

[21]  Prateek Yadav,et al.  Confidence-based Graph Convolutional Networks for Semi-Supervised Learning , 2019, AISTATS.

[22]  Tore Opsahl.  Triadic closure in two-mode networks: Redefining the global and local clustering coefficients , 2013, Soc. Networks.

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

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

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

[26]  Diego Marcheggiani,et al.  Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling , 2017, EMNLP.

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

[28]  Futao Zhang,et al.  FastGCN: A GPU Accelerated Tool for Fast Gene Co-Expression Networks , 2015, PloS one.