Interpretable Signed Link Prediction With Signed Infomax Hyperbolic Graph

Signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes) given their existing positive and negative interactions observed. Most of the prior efforts are devoted to learning node embeddings with graph neural networks (GNNs), which preserve the signed network topology by message-passing along edges to facilitate the downstream link prediction task. Nevertheless, the existing graph-based approaches could hardly provide human-intelligible explanations for the following three questions: (1) which neighbors to aggregate, (2) which path to propagate along, and (3) which social theory to follow in the learning process. To answer the aforementioned questions, in this paper, we investigate how to reconcile the \textit{balance} and \textit{status} social rules with information theory and develop a unified framework, termed as Signed Infomax Hyperbolic Graph (\textbf{SIHG}). By maximizing the mutual information between edge polarities and node embeddings, one can identify the most representative neighboring nodes that support the inference of edge sign. Different from existing GNNs that could only group features of friends in the subspace, the proposed SIHG incorporates the signed attention module, which is also capable of pushing hostile users far away from each other to preserve the geometry of antagonism. The polarity of the learned edge attention maps, in turn, provide interpretations of the social theories used in each aggregation. In order to model high-order user relations and complex hierarchies, the node embeddings are projected and measured in a hyperbolic space with a lower distortion. Extensive experiments on four signed network benchmarks demonstrate that the proposed SIHG framework significantly outperforms the state-of-the-arts in signed link prediction.

[1]  Takuya Akiba,et al.  Optuna: A Next-generation Hyperparameter Optimization Framework , 2019, KDD.

[2]  Hongning Wang,et al.  JNET: Learning User Representations via Joint Network Embedding and Topic Embedding , 2019, WSDM.

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

[4]  Feng Liu,et al.  How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches? , 2020, AAAI.

[5]  Douwe Kiela,et al.  Poincaré Embeddings for Learning Hierarchical Representations , 2017, NIPS.

[6]  Junghwan Kim,et al.  SIDE: Representation Learning in Signed Directed Networks , 2018, WWW.

[7]  Douwe Kiela,et al.  Hyperbolic Graph Neural Networks , 2019, NeurIPS.

[8]  Naftali Tishby,et al.  The information bottleneck method , 2000, ArXiv.

[9]  Bonaventure C. Molokwu Event Prediction in Complex Social Graphs using One-Dimensional Convolutional Neural Network , 2019, IJCAI.

[10]  Ramanathan V. Guha,et al.  Propagation of trust and distrust , 2004, WWW '04.

[11]  Sheng-De Wang,et al.  Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Jinhong Jung,et al.  Signed Graph Diffusion Network , 2020, ArXiv.

[13]  Inderjit S. Dhillon,et al.  Low rank modeling of signed networks , 2012, KDD.

[14]  Wenqing Lin,et al.  Initialization for Network Embedding: A Graph Partition Approach , 2020, WSDM.

[15]  Stefan M. Herzog,et al.  The Structure of Social Influence in Recommender Networks , 2020, WWW.

[16]  Zi Huang,et al.  Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learning , 2018, CIKM.

[17]  Jiliang Tang,et al.  Signed Graph Convolutional Networks , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

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

[19]  Amit P. Sheth,et al.  Knowledge Graph Enhanced Community Detection and Characterization , 2019, WSDM.

[20]  Alexander A. Alemi,et al.  Deep Variational Information Bottleneck , 2017, ICLR.

[21]  Bo Yuan,et al.  Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation , 2020, IJCAI.

[22]  S. Varadhan,et al.  Asymptotic evaluation of certain Markov process expectations for large time , 1975 .

[23]  Jian Pei,et al.  ProGAN: Network Embedding via Proximity Generative Adversarial Network , 2019, KDD.

[24]  Udi Weinsberg,et al.  Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks , 2020, WWW.

[25]  Minyi Guo,et al.  SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction , 2017, WSDM.

[26]  Jure Leskovec,et al.  Hyperbolic Graph Convolutional Neural Networks , 2019, NeurIPS.

[27]  Alexander A. Alemi,et al.  Uncertainty in the Variational Information Bottleneck , 2018, ArXiv.

[28]  Zhaochun Ren,et al.  Multi-Dimensional Network Embedding with Hierarchical Structure , 2018, WSDM.

[29]  Jure Leskovec,et al.  Signed networks in social media , 2010, CHI.

[30]  Jure Leskovec,et al.  Predicting positive and negative links in online social networks , 2010, WWW '10.

[31]  David B. Skillicorn,et al.  Spectral Embedding of Signed Networks , 2015, SDM.

[32]  Richard Weber,et al.  Overlapping Community Detection in Static and Dynamic Social Networks , 2019, WSDM.

[33]  Inderjit S. Dhillon,et al.  Scalable clustering of signed networks using balance normalized cut , 2012, CIKM.

[34]  Xueqi Cheng,et al.  Signed Graph Attention Networks , 2019, ICANN.

[35]  Tao Zhang,et al.  Recommendation in Heterogeneous Information Networks Based on Generalized Random Walk Model and Bayesian Personalized Ranking , 2018, WSDM.

[36]  Jian Li,et al.  Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec , 2017, WSDM.

[37]  C. Eckart,et al.  The approximation of one matrix by another of lower rank , 1936 .

[38]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[39]  Yang Xiang,et al.  SNE: Signed Network Embedding , 2017, PAKDD.

[40]  F. Harary,et al.  STRUCTURAL BALANCE: A GENERALIZATION OF HEIDER'S THEORY1 , 1977 .

[41]  Xueqi Cheng,et al.  SDGNN: Learning Node Representation for Signed Directed Networks , 2021, AAAI.

[42]  Yoshua Bengio,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[43]  Mohammad Raihanul Islam,et al.  SIGNet: Scalable Embeddings for Signed Networks , 2017, PAKDD.

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

[45]  Eric P. Xing,et al.  Spatial compactness meets topical consistency: jointly modeling links and content for community detection , 2014, WSDM.

[46]  Yu Li,et al.  Learning Signed Network Embedding via Graph Attention , 2020, AAAI.

[47]  Christos Faloutsos,et al.  Edge Weight Prediction in Weighted Signed Networks , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[48]  Ralph Linsker,et al.  Self-organization in a perceptual network , 1988, Computer.

[49]  Christos Faloutsos,et al.  REV2: Fraudulent User Prediction in Rating Platforms , 2018, WSDM.

[50]  Yoshua Bengio,et al.  Mutual Information Neural Estimation , 2018, ICML.

[51]  Xiao Huang,et al.  Exploring Expert Cognition for Attributed Network Embedding , 2018, WSDM.

[52]  Feng Liu,et al.  Open Set Domain Adaptation: Theoretical Bound and Algorithm , 2019, IEEE Transactions on Neural Networks and Learning Systems.