Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2020

Abstract

Oftentimes documents are linked to one another in a network structure,e.g., academic papers cite other papers, Web pages link to other pages. In this paper we propose a holistic topic model to learn meaningful and unified low-dimensional representations for networked documents that seek to preserve both textual content and network structure. On the basis of reconstructing not only the input document but also its adjacent neighbors, we develop two neural encoder architectures. Adjacent-Encoder, or AdjEnc, induces competition among documents for topic propagation, and reconstruction among neighbors for semantic capture. Adjacent-Encoder-X, or AdjEnc-X, extends this to also encode the network structure in addition to document content. We evaluate our models on real-world document networks quantitatively and qualitatively, outperforming comparable baselines comprehensively

Keywords

Encoder architecture, Low-dimensional representation, Network structures, Semantic capture, Textual content, Topic Modeling, Artificial intelligence

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of the 34th AAAI Conference on Artificial Intelligence 2020, New York, February 7-12

First Page

6737

Last Page

6745

ISBN

9781577358350

Identifier

10.1609/aaai.v34i04.6152

Publisher

AAAI Press

City or Country

Menlo Park, CA

Embargo Period

5-15-2020

Copyright Owner and License

Publisher

Additional URL

https://doi.org/10.1609/aaai.v34i04.6152

Download

Share

COinS