Link Inference via Heterogeneous Multi-view Graph Neural Networks

Graph Neural Network (GNN) has been attaching great attention along with its successful industry applications, such as social network, recommendation system and so on. Most existing GNN algorithms for link inference tasks mainly concentrate on homogeneous network where single typed nodes and edges are considered. Besides, they are transductive, incapable of handling unseen data, and are difficult to generalize to big graph data. In this paper, we introduce a new idea, i.e. Heterogeneous Multi-view Graph Neural Network (HMGNN), to remedy these problems. A more complex and unstudied heterogeneous network structure where multiple node and edge types co-exist, and each of them also contains specific attributes, is learned in this framework. The proposed HMGNN is end-to-end and two stages are designed: i) The first stage extends the widely-used GraphSAGE model to the studied heterogeneous scenario to generate the vector embedded representations for each type of nodes. ii) The second stage develops a novel and inductive subspace-based strategy for link inference by aggregating multi-typed node and edge feature views. Comprehensive experiments on large-scale spam detection and link prediction applications clearly verify the effectiveness of our model.

[1]  Mert R. Sabuncu,et al.  Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels , 2018, NeurIPS.

[2]  Bo An,et al.  Securing the Deep Fraud Detector in Large-Scale E-Commerce Platform via Adversarial Machine Learning Approach , 2019, WWW.

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

[4]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[5]  Yanfang Ye,et al.  Heterogeneous Graph Attention Network , 2019, WWW.

[6]  Jie Tang,et al.  Representation Learning for Attributed Multiplex Heterogeneous Network , 2019, KDD.

[7]  Yu Huang,et al.  FdGars: Fraudster Detection via Graph Convolutional Networks in Online App Review System , 2019, WWW.

[8]  Yongliang Li,et al.  Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation , 2019, KDD.

[9]  Nitesh V. Chawla,et al.  Heterogeneous Graph Neural Network , 2019, KDD.

[10]  Le Song,et al.  Heterogeneous Graph Neural Networks for Malicious Account Detection , 2018, CIKM.

[11]  Jian Li,et al.  AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN , 2019, IJCAI.

[12]  Jun Won Choi,et al.  Deep neural network-based automatic modulation classification technique , 2016, 2016 International Conference on Information and Communication Technology Convergence (ICTC).

[13]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

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

[15]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[16]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[17]  Liwei Qiu,et al.  Scalable Multiplex Network Embedding , 2018, IJCAI.

[18]  Jiajun Bu,et al.  ANRL: Attributed Network Representation Learning via Deep Neural Networks , 2018, IJCAI.

[19]  Xing Xie,et al.  Session-based Recommendation with Graph Neural Networks , 2018, AAAI.