DeepInf: Social Influence Prediction with Deep Learning

Abstract

Social and information networking activities such as on Facebook, Twitter, WeChat, and Weibo have become an indispensable part of our everyday life, where we can easily access friends' behaviors and are in turn influenced by them. Consequently, an effective social influence prediction for each user is critical for a variety of applications such as online recommendation and advertising. Conventional social influence prediction approaches typically design various hand-crafted rules to extract user- and network-specific features. However, their effectiveness heavily relies on the knowledge of domain experts. As a result, it is usually difficult to generalize them into different domains. Inspired by the recent success of deep neural networks in a wide range of computing applications, we design an end-to-end framework, DeepInf, to learn users' latent feature representation for predicting social influence. In general, DeepInf takes a user's local network as the input to a graph neural network for learning her latent social representation. We design strategies to incorporate both network structures and user-specific features into convolutional neural and attention networks. Extensive experiments on Open Academic Graph, Twitter, Weibo, and Digg, representing different types of social and information networks, demonstrate that the proposed end-to-end model, DeepInf, significantly outperforms traditional feature engineering-based approaches, suggesting the effectiveness of representation learning for social applications.

arXiv comment10 pages, 5 figures, to appear in KDD 2018 proceedings

References in corpus (12)

• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Learning Convolutional Neural Networks for Graphs
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• An O(m) Algorithm for Cores Decomposition of Networks
• Social Influence in Social Advertising: Evidence from Field Experiments
• A Century of Science: Globalization of Scientific Collaborations, Citations, and Innovations
• Structural Diversity and Homophily: A Study Across More than One Hundred Big Networks

Cited by in corpus (74)

• A Comprehensive Survey on Graph Neural Networks
• Neural Graph Collaborative Filtering
• KGAT: Knowledge Graph Attention Network for Recommendation
• Self-supervised Learning: Generative or Contrastive
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems
• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• Graph Neural Networks: Taxonomy, Advances and Trends
• Graph Unlearning
• Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction
• Single Node Injection Attack against Graph Neural Networks
• A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization
• Scalable Graph Neural Networks via Bidirectional Propagation
• Self-supervised Consensus Representation Learning for Attributed Graph
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• Model Degradation Hinders Deep Graph Neural Networks
• How Attentive are Graph Attention Networks?
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• A DRL-based Multiagent Cooperative Control Framework for CAV Networks: a Graphic Convolution Q Network
• Deep Collaborative Embedding for information cascade prediction
• Graph Neural Networks: Methods, Applications, and Opportunities
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• Understanding WeChat User Preferences and "Wow" Diffusion
• Adap-$\tau$: Adaptively Modulating Embedding Magnitude for Recommendation
• Capturing Dynamics of Information Diffusion in SNS: A Survey of Methodology and Techniques
• DISCO: Influence Maximization Meets Network Embedding and Deep Learning
• Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
• A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation
• Relation-aware Heterogeneous Graph for User Profiling
• How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
• Predicting Information Pathways Across Online Communities
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• Comprehending Knowledge Graphs with Large Language Models for Recommender Systems
• Revisiting the role of heterophily in graph representation learning: An edge classification perspective
• RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training
• Modelling High-Order Social Relations for Item Recommendation
• Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
• Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach
• Adversarial Immunization for Certifiable Robustness on Graphs
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• Popularity Prediction on Social Platforms with Coupled Graph Neural Networks
• Graph Representation Learning for Popularity Prediction Problem: A Survey
• Cascade-BGNN: Toward Efficient Self-supervised Representation Learning on Large-scale Bipartite Graphs
• Geometric graphs from data to aid classification tasks with graph convolutional networks
• Cross-GCN: Enhancing Graph Convolutional Network with $k$-Order Feature Interactions
• Exploring the Representational Power of Graph Autoencoder
• Graph Representation learning for Audio & Music genre Classification
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
• Topological Regularization for Graph Neural Networks Augmentation
• A^2-GCN: An Attribute-aware Attentive GCN Model for Recommendation
• Network Diffusions via Neural Mean-Field Dynamics
• The Mass, Fake News, and Cognition Security
• A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification
• Interest-aware Message-Passing GCN for Recommendation
• Visual Object Tracking by Segmentation with Graph Convolutional Network
• Social Influence Prediction with Train and Test Time Augmentation for Graph Neural Networks
• Spotting Silent Buffer Overflows in Execution Trace through Graph Neural Network Assisted Data Flow Analysis
• Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks
• MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks
• Towards User Engagement Dynamics in Social Networks
• From Symbols to Embeddings: A Tale of Two Representations in Computational Social Science
• Before It's Too Late: A State Space Model for the Early Prediction of Misinformation and Disinformation Engagement
• GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end
• MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks
• Influence Maximization Based on Dynamic Personal Perception in Knowledge Graph
• From #Jobsearch to #Mask: Improving COVID-19 Cascade Prediction with Spillover Effects
• Influence Estimation and Maximization via Neural Mean-Field Dynamics
• Propagation-aware Social Recommendation by Transfer Learning
• Curvature Graph Neural Network