DeepInf: Social Influence Prediction with Deep Learning

By Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang. Knowledge Discovery and Data Mining, 2018

625 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Communication, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/9fa3e53b5937a0ec92499ed415e339ede6c92010

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Liqiang Nie
5. Fuli Feng
6. Meng Wang
7. Jie Tang
8. Yixin Cao

In Communication

1. Tat-seng Chua
2. Jie Tang

In Statistical and Nonlinear Physics

1. Jie Tang
2. Tat-seng Chua
3. Yuxiao Dong
4. Kuansan Wang
5. Hongxia Yang
6. Jaewoo Kang
7. Seongjun Yun
8. Xiangnan He

Citations in the corpus

• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation (2021, background): “Graph neural networks (GNNs) have received extensive attention from researchers due to their excellent performance on various graph learning tasks such as social analysis [24, 17, 29], drug discovery [12, 25], traffic forecasting [18, 3, 6], recommendation system [38, 32] and computer vision [39, 4]”
• Neural Graph Collaborative Filtering (2019, methodology): “It allows us to discard the node sampling procedure, which is commonly used to make graph convolution network runnable on large-scale graph [25].”
• Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems (2019, background): “Existing studies leverage GAT to tackle social inƒuence analysis[24], graph node classi€cation[6], conversation generation[44], relevence matching[41].”
• KGAT: Knowledge Graph Attention Network for Recommendation (2019, methodology): “Considering an entity h, we use Nh = {(h, r , t )|(h, r , t ) ∈ G} to denote the set of triplets where h is the head entity, termed egonetwork [21].”
• Graph convolutional networks: a comprehensive review (2019, background): “DeepInf [121] aims to predict social influences by learning users latent features.”
• DyGRAIN: An Incremental Learning Framework for Dynamic Graphs (2022, positive): “Over the last few years, graph-structured data has been widely used in diverse domains, including social network analysis [Qiu et al. , 2018], recommender systems [Berg et al. , 2017], computer vision [Qi et al. , 2017], and bioinformatics [De Cao and Kipf, 2018].”
• Simple and Deep Graph Convolutional Networks (2020, methodology): “…(Defferrard et al., 2016; Veliˇckovi´c et al., 2018) have been successfully applied to a wide range of applications, including social analysis (Qiu et al., 2018; Li & Goldwasser, 2019), traffic prediction (Guo et al., 2019; Li et al., 2019), biology (Fout et al., 2017; Shang et al., 2019),…”
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training (2020, methodology): “[42] to use 0.”
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation (2020, background): “Owing to its interpretability and efficiency, it quickly becomes a prevalent formulation of GNNs and is being widely used [11, 29, 47].”
• Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey (2020, background): “Particularly GNNs have been used in a wide variety of disciplines such as chemistry [47], [48], recommender systems [49], [50] and social networks [51], [52].”
• How Attentive are Graph Attention Networks? (2021, background): “’s original design of GAT has spread to a variety of domains (Wang et al., 2019a; Qiu et al., 2018; Yang et al., 2020; Wang et al., 2019c; Huang and Carley, 2019; Ma et al., 2020; Kosaraju et al., 2019; Nathani et al., 2019; Wu et al., 2020; Zhang et al., 2020) and has become the default implementat”
• Interest-aware Message-Passing GCN for Recommendation (2021, methodology): “It is a commonly used approach to make graph convolution network feasible for large-scale graph [26, 33].”