Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction

Abstract

Recent years have witnessed tremendous interest in understanding and predicting information spread on social media platforms such as Twitter, Facebook, etc. Existing diffusion prediction methods primarily exploit the sequential order of influenced users by projecting diffusion cascades onto their local social neighborhoods. However, this fails to capture global social structures that do not explicitly manifest in any of the cascades, resulting in poor performance for inactive users with limited historical activities. In this paper, we present a novel variational autoencoder framework (Inf-VAE) to jointly embed homophily and influence through proximity-preserving social and position-encoded temporal latent variables. To model social homophily, Inf-VAE utilizes powerful graph neural network architectures to learn social variables that selectively exploit the social connections of users. Given a sequence of seed user activations, Inf-VAE uses a novel expressive co-attentive fusion network that jointly attends over their social and temporal variables to predict the set of all influenced users. Our experimental results on multiple real-world social network datasets, including Digg, Weibo, and Stack-Exchanges demonstrate significant gains (22% MAP@10) for Inf-VAE over state-of-the-art diffusion prediction models; we achieve massive gains for users with sparse activities, and users who lack direct social neighbors in seed sets.

International Conference on Web Search and Data Mining (WSDM 2020)

References in corpus (16)

• Statistical mechanics of complex networks
• Auto-Encoding Variational Bayes
• Neural Machine Translation by Jointly Learning to Align and Translate
• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Variational Inference: A Review for Statisticians
• The Dynamics of Viral Marketing
• Homophily and Contagion Are Generically Confounded in Observational Social Network Studies
• Variational Graph Auto-Encoders
• DeepInf: Social Influence Prediction with Deep Learning
• Dynamic Coattention Networks For Question Answering
• SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity
• Dynamic Graph Representation Learning via Self-Attention Networks
• Motif-based Convolutional Neural Network on Graphs
• An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms

Cited by in corpus (9)

• GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation
• Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
• Capturing Dynamics of Information Diffusion in SNS: A Survey of Methodology and Techniques
• Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework
• Measuring Friendship Closeness: A Perspective of Social Identity Theory
• Discovering Strategic Behaviors for Collaborative Content-Production in Social Networks
• Information Diffusion Prediction with Latent Factor Disentanglement
• DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
• A Survey on Role-Oriented Network Embedding