Dynamic Topic Models for Temporal Document Networks

Delvin Ce Zhang, Hady Lauw
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:26281-26292, 2022.

Abstract

Dynamic topic models explore the time evolution of topics in temporally accumulative corpora. While existing topic models focus on the dynamics of individual documents, we propose two neural topic models aimed at learning unified topic distributions that incorporate both document dynamics and network structure. For the first model, by adding a time dimension, we propose Time-Aware Optimal Transport, which measures the probability of a link between two differently timestamped documents using their semantic distance. Since the gradually evolving topological structure of network may also influence the establishment of a new link, for the second model, we further design a Temporal Point Process to capture the impact of historical neighbors on the current link formation at the network level. Experiments on four dynamic document networks demonstrate the advantage of our models in jointly modeling document dynamics and network adjacency.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-zhang22n, title = {Dynamic Topic Models for Temporal Document Networks}, author = {Zhang, Delvin Ce and Lauw, Hady}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {26281--26292}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/zhang22n/zhang22n.pdf}, url = {https://proceedings.mlr.press/v162/zhang22n.html}, abstract = {Dynamic topic models explore the time evolution of topics in temporally accumulative corpora. While existing topic models focus on the dynamics of individual documents, we propose two neural topic models aimed at learning unified topic distributions that incorporate both document dynamics and network structure. For the first model, by adding a time dimension, we propose Time-Aware Optimal Transport, which measures the probability of a link between two differently timestamped documents using their semantic distance. Since the gradually evolving topological structure of network may also influence the establishment of a new link, for the second model, we further design a Temporal Point Process to capture the impact of historical neighbors on the current link formation at the network level. Experiments on four dynamic document networks demonstrate the advantage of our models in jointly modeling document dynamics and network adjacency.} }
Endnote
%0 Conference Paper %T Dynamic Topic Models for Temporal Document Networks %A Delvin Ce Zhang %A Hady Lauw %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-zhang22n %I PMLR %P 26281--26292 %U https://proceedings.mlr.press/v162/zhang22n.html %V 162 %X Dynamic topic models explore the time evolution of topics in temporally accumulative corpora. While existing topic models focus on the dynamics of individual documents, we propose two neural topic models aimed at learning unified topic distributions that incorporate both document dynamics and network structure. For the first model, by adding a time dimension, we propose Time-Aware Optimal Transport, which measures the probability of a link between two differently timestamped documents using their semantic distance. Since the gradually evolving topological structure of network may also influence the establishment of a new link, for the second model, we further design a Temporal Point Process to capture the impact of historical neighbors on the current link formation at the network level. Experiments on four dynamic document networks demonstrate the advantage of our models in jointly modeling document dynamics and network adjacency.
APA
Zhang, D.C. & Lauw, H.. (2022). Dynamic Topic Models for Temporal Document Networks. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:26281-26292 Available from https://proceedings.mlr.press/v162/zhang22n.html.

Related Material