TY - GEN
T1 - InF-VAE
T2 - 13th ACM International Conference on Web Search and Data Mining, WSDM 2020
AU - Sankar, Aravind
AU - Zhang, Xinyang
AU - Krishnan, Adit
AU - Han, Jiawei
N1 - Funding Information:
Research was sponsored in part by U.S. Army Research Lab. under Cooperative Agreement No. W911NF-09-2-0053 (NSCTA), DARPA under Agreements No. W911NF-17-C-0099 and FA8750-19-2-1004, National Science Foundation IIS 16-18481, IIS 17-04532, and IIS-17-41317, and DTRA HDTRA11810026.
Publisher Copyright:
© 2020 Association for Computing Machinery.
PY - 2020/1/20
Y1 - 2020/1/20
N2 - 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.
AB - 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.
KW - Attention
KW - Autoencoder
KW - Deep learning
KW - Diffusion
KW - Social network
UR - http://www.scopus.com/inward/record.url?scp=85079549711&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079549711&partnerID=8YFLogxK
U2 - 10.1145/3336191.3371811
DO - 10.1145/3336191.3371811
M3 - Conference contribution
AN - SCOPUS:85079549711
T3 - WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining
SP - 510
EP - 518
BT - WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining
PB - Association for Computing Machinery, Inc
Y2 - 3 February 2020 through 7 February 2020
ER -