E-GCN: graph convolution with estimated labels

G raph C onvolutional N etwork (GCN) has been commonly applied for semi-supervised learning tasks. However, the established GCN frequently only considers the given labels in the topology optimization, which may not deliver the best performance for semi-supervised learning tasks. In this paper, we propose a novel G raph C onvolutional N etwork with E stimated labels (E-GCN) for semi-supervised learning. The core design of E-GCN is to learn a suitable network topology for semi-supervised learning by linking both estimated labels and given labels in a centralized network framework. The major enhancement is that both given labels and estimated labels are utilized for the topology optimization in E-GCN, which assists the graph convolution implementation for unknown labels evaluation. Experimental results demonstrate that E-GCN is significantly better than s tate-o f-t he-a rt (SOTA) baselines without estimated labels.

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

[2]  Yun Fu,et al.  From Ensemble Clustering to Multi-View Clustering , 2017, IJCAI.

[3]  Chong Wang,et al.  Attention-based Graph Neural Network for Semi-supervised Learning , 2018, ArXiv.

[4]  Guido Montúfar,et al.  Haar Graph Pooling , 2019, ICML.

[5]  Joonseok Lee,et al.  N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification , 2018, UAI.

[6]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[7]  Qiang Ma,et al.  Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification , 2018, WWW.

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

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

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

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

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

[13]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[14]  Philip S. Yu,et al.  Cross View Link Prediction by Learning Noise-resilient Representation Consensus , 2017, WWW.

[15]  Xiaosheng Zhuang,et al.  Fast Haar Transforms for Graph Neural Networks , 2019, Neural Networks.

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

[17]  Santo Fortunato,et al.  Community detection in networks: A user guide , 2016, ArXiv.

[18]  Soummya Kar,et al.  Topology adaptive graph convolutional networks , 2017, ArXiv.

[19]  Jian Yang,et al.  Gaussian-Induced Convolution for Graphs , 2018, AAAI.

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

[21]  Lise Getoor,et al.  Link-Based Classification , 2003, Encyclopedia of Machine Learning and Data Mining.

[22]  Naiwen Liu,et al.  A multi-label text classification method via dynamic semantic representation model and deep neural network , 2020, Applied Intelligence.

[23]  Zheng Hu,et al.  Taxonomy-aware collaborative denoising autoencoder for personalized recommendation , 2019, Applied Intelligence.

[24]  Xiaochun Cao,et al.  Topology Optimization based Graph Convolutional Network , 2019, IJCAI.

[25]  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).

[26]  Bin Li,et al.  A link prediction algorithm based on low-rank matrix completion , 2018, Applied Intelligence.

[27]  Ian Davidson,et al.  Labels vs. Pairwise Constraints: A Unified View of Label Propagation and Constrained Spectral Clustering , 2012, 2012 IEEE 12th International Conference on Data Mining.