Analyzing the Evolution of Graphs and Texts
Xingzhi Guo

TL;DR
This paper explores the dynamic evolution of graphs and texts, proposing methods to model changes efficiently and analyze their underlying causes, with applications in social networks, news titles, and personal biographies.
Contribution
It introduces dynamic network embedding techniques using Personalized PageRank and analyzes textual changes and occupational identity disclosures over time.
Findings
Improved detection of network anomalies and entity meaning shifts.
Insights into news title edits and their impact on information integrity.
Quantitative analysis of job disclosure patterns over five years.
Abstract
With the recent advance of representation learning algorithms on graphs (e.g., DeepWalk/GraphSage) and natural languages (e.g., Word2Vec/BERT) , the state-of-the art models can even achieve human-level performance over many downstream tasks, particularly for the task of node and sentence classification. However, most algorithms focus on large-scale models for static graphs and text corpus without considering the inherent dynamic characteristics or discovering the reasons behind the changes. This dissertation aims to efficiently model the dynamics in graphs (such as social networks and citation graphs) and understand the changes in texts (specifically news titles and personal biographies). To achieve this goal, we utilize the renowned Personalized PageRank algorithm to create effective dynamic network embeddings for evolving graphs. Our proposed approaches significantly improve the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsLanguage and cultural evolution
MethodsFocus
