DeepInf: Social Influence Prediction with Deep Learning

TL;DR

DeepInf is a deep learning framework that predicts social influence by learning users' latent features from local network structures, outperforming traditional methods across multiple social media datasets.

Contribution

This paper introduces DeepInf, an end-to-end deep neural network model that automatically learns social influence features, overcoming limitations of hand-crafted feature engineering.

Findings

DeepInf significantly outperforms traditional approaches.

The model effectively integrates network structure and user features.

Experiments on multiple social networks validate its generalizability.

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.