Learning Opinions in Social Networks

Vincent Conitzer, Debmalya Panigrahi, Hanrui Zhang
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2122-2132, 2020.

Abstract

We study the problem of learning opinions in social networks. The learner observes the states of some sample nodes from a social network, and tries to infer the states of other nodes, based on the structure of the network. We show that sample-efficient learning is impossible when the network exhibits strong noise, and give a polynomial-time algorithm for the problem with nearly optimal sample complexity when the network is sufficiently stable.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-conitzer20a, title = {Learning Opinions in Social Networks}, author = {Conitzer, Vincent and Panigrahi, Debmalya and Zhang, Hanrui}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2122--2132}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/conitzer20a/conitzer20a.pdf}, url = {https://proceedings.mlr.press/v119/conitzer20a.html}, abstract = {We study the problem of learning opinions in social networks. The learner observes the states of some sample nodes from a social network, and tries to infer the states of other nodes, based on the structure of the network. We show that sample-efficient learning is impossible when the network exhibits strong noise, and give a polynomial-time algorithm for the problem with nearly optimal sample complexity when the network is sufficiently stable.} }
Endnote
%0 Conference Paper %T Learning Opinions in Social Networks %A Vincent Conitzer %A Debmalya Panigrahi %A Hanrui Zhang %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-conitzer20a %I PMLR %P 2122--2132 %U https://proceedings.mlr.press/v119/conitzer20a.html %V 119 %X We study the problem of learning opinions in social networks. The learner observes the states of some sample nodes from a social network, and tries to infer the states of other nodes, based on the structure of the network. We show that sample-efficient learning is impossible when the network exhibits strong noise, and give a polynomial-time algorithm for the problem with nearly optimal sample complexity when the network is sufficiently stable.
APA
Conitzer, V., Panigrahi, D. & Zhang, H.. (2020). Learning Opinions in Social Networks. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2122-2132 Available from https://proceedings.mlr.press/v119/conitzer20a.html.

Related Material