Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models

Qunwei Li, Bhavya Kailkhura, Jayaraman Thiagarajan, Zhenliang Zhang, Pramod Varshney
; Proceedings of the Time Series Workshop at NIPS 2016, PMLR 55:27-37, 2017.

Abstract

Influential node detection is a central research topic in social network analysis. Many existing methods rely on the assumption that the network structure is completely known a priori. However, in many applications, network structure is unavailable to explain the underlying information diffusion phenomenon. To address the challenge of information diffusion analysis with incomplete knowledge of network structure, we develop a multi-task low rank linear influence model. By exploiting the relationships between contagions, our approach can simultaneously predict the volume (i.e. time series prediction) for each contagion (or topic) and automatically identify the most influential nodes for each contagion. The proposed model is validated using synthetic data and an ISIS twitter dataset. In addition to improving the volume prediction performance significantly, we show that the proposed approach can reliably infer the most influential users for specific contagions.

Cite this Paper


BibTeX
@InProceedings{pmlr-v55-li16, title = {Influential Node Detection in Implicit Social Networks using Multi-task {G}aussian Copula Models}, author = {Qunwei Li and Bhavya Kailkhura and Jayaraman Thiagarajan and Zhenliang Zhang and Pramod Varshney}, booktitle = {Proceedings of the Time Series Workshop at NIPS 2016}, pages = {27--37}, year = {2017}, editor = {Oren Anava and Azadeh Khaleghi and Marco Cuturi and Vitaly Kuznetsov and Alexander Rakhlin}, volume = {55}, series = {Proceedings of Machine Learning Research}, address = {Barcelona, Spain}, month = {09 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v55/li16.pdf}, url = {http://proceedings.mlr.press/v55/li16.html}, abstract = {Influential node detection is a central research topic in social network analysis. Many existing methods rely on the assumption that the network structure is completely known a priori. However, in many applications, network structure is unavailable to explain the underlying information diffusion phenomenon. To address the challenge of information diffusion analysis with incomplete knowledge of network structure, we develop a multi-task low rank linear influence model. By exploiting the relationships between contagions, our approach can simultaneously predict the volume (i.e. time series prediction) for each contagion (or topic) and automatically identify the most influential nodes for each contagion. The proposed model is validated using synthetic data and an ISIS twitter dataset. In addition to improving the volume prediction performance significantly, we show that the proposed approach can reliably infer the most influential users for specific contagions.} }
Endnote
%0 Conference Paper %T Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models %A Qunwei Li %A Bhavya Kailkhura %A Jayaraman Thiagarajan %A Zhenliang Zhang %A Pramod Varshney %B Proceedings of the Time Series Workshop at NIPS 2016 %C Proceedings of Machine Learning Research %D 2017 %E Oren Anava %E Azadeh Khaleghi %E Marco Cuturi %E Vitaly Kuznetsov %E Alexander Rakhlin %F pmlr-v55-li16 %I PMLR %J Proceedings of Machine Learning Research %P 27--37 %U http://proceedings.mlr.press %V 55 %W PMLR %X Influential node detection is a central research topic in social network analysis. Many existing methods rely on the assumption that the network structure is completely known a priori. However, in many applications, network structure is unavailable to explain the underlying information diffusion phenomenon. To address the challenge of information diffusion analysis with incomplete knowledge of network structure, we develop a multi-task low rank linear influence model. By exploiting the relationships between contagions, our approach can simultaneously predict the volume (i.e. time series prediction) for each contagion (or topic) and automatically identify the most influential nodes for each contagion. The proposed model is validated using synthetic data and an ISIS twitter dataset. In addition to improving the volume prediction performance significantly, we show that the proposed approach can reliably infer the most influential users for specific contagions.
RIS
TY - CPAPER TI - Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models AU - Qunwei Li AU - Bhavya Kailkhura AU - Jayaraman Thiagarajan AU - Zhenliang Zhang AU - Pramod Varshney BT - Proceedings of the Time Series Workshop at NIPS 2016 PY - 2017/02/16 DA - 2017/02/16 ED - Oren Anava ED - Azadeh Khaleghi ED - Marco Cuturi ED - Vitaly Kuznetsov ED - Alexander Rakhlin ID - pmlr-v55-li16 PB - PMLR SP - 27 DP - PMLR EP - 37 L1 - http://proceedings.mlr.press/v55/li16.pdf UR - http://proceedings.mlr.press/v55/li16.html AB - Influential node detection is a central research topic in social network analysis. Many existing methods rely on the assumption that the network structure is completely known a priori. However, in many applications, network structure is unavailable to explain the underlying information diffusion phenomenon. To address the challenge of information diffusion analysis with incomplete knowledge of network structure, we develop a multi-task low rank linear influence model. By exploiting the relationships between contagions, our approach can simultaneously predict the volume (i.e. time series prediction) for each contagion (or topic) and automatically identify the most influential nodes for each contagion. The proposed model is validated using synthetic data and an ISIS twitter dataset. In addition to improving the volume prediction performance significantly, we show that the proposed approach can reliably infer the most influential users for specific contagions. ER -
APA
Li, Q., Kailkhura, B., Thiagarajan, J., Zhang, Z. & Varshney, P.. (2017). Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models. Proceedings of the Time Series Workshop at NIPS 2016, in PMLR 55:27-37

Related Material