Discovering Communication Pattern Shifts in Large-Scale Labeled Networks Using Encoder Embedding and Vertex Dynamics
| Author(s) | Shen, Cencheng | |
| Author(s) | Larson, Jonathan | |
| Author(s) | Trinh, Ha | |
| Author(s) | Qin, Xihan | |
| Author(s) | Park, Youngser | |
| Author(s) | Priebe, Carey E. | |
| Date Accessioned | 2024-03-06T20:09:20Z | |
| Date Available | 2024-03-06T20:09:20Z | |
| Publication Date | 2023-11-29 | |
| Description | This article was originally published in IEEE Transactions on Network Science and Engineering. The version of record is available at: https://doi.org/10.1109/TNSE.2023.3337600. © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This article will be embargoed until 11/29/2025 | |
| Abstract | Analyzing large-scale time-series network data, such as social media and email communications, poses a significant challenge in understanding social dynamics, detecting anomalies, and predicting trends. In particular, the scalability of graph analysis is a critical hurdle impeding progress in large-scale downstream inference. To address this challenge, we introduce a temporal encoder embedding method. This approach leverages ground-truth or estimated vertex labels, enabling an efficient embedding of large-scale graph data and the processing of billions of edges within minutes. Furthermore, this embedding unveils a temporal dynamic statistic capable of detecting communication pattern shifts across all levels, ranging from individual vertices to vertex communities and the overall graph structure. We provide theoretical support to confirm its soundness under random graph models, and demonstrate its numerical advantages in capturing evolving communities and identifying outliers. Finally, we showcase the practical application of our approach by analyzing an anonymized time-series communication network from a large organization spanning 2019–2020, enabling us to assess the impact of Covid-19 on workplace communication patterns. | |
| Sponsor | This work was supported in part by the National Science Foundation HDR TRIPODS 1934979, the National Science Foundation DMS-2113099, and by funding from Microsoft Research. | |
| Citation | C. Shen, J. Larson, H. Trinh, X. Qin, Y. Park and C. E. Priebe, "Discovering Communication Pattern Shifts in Large-Scale Labeled Networks Using Encoder Embedding and Vertex Dynamics," in IEEE Transactions on Network Science and Engineering, vol. 11, no. 2, pp. 2100-2109, March-April 2024, doi: 10.1109/TNSE.2023.3337600 | |
| ISSN | 2327-4697 | |
| URL | https://udspace.udel.edu/handle/19716/34103 | |
| Language | en_US | |
| Publisher | IEEE Transactions on Network Science and Engineering | |
| Keywords | graph embedding | |
| Keywords | time-series networks | |
| Keywords | outlier detection | |
| Title | Discovering Communication Pattern Shifts in Large-Scale Labeled Networks Using Encoder Embedding and Vertex Dynamics | |
| Type | Article |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- Discovering Communication Pattern Shifts in Large-Scale Labeled Networks Using Encoder Embedding and Vertex Dynamics.pdf
- Size:
- 6.04 MB
- Format:
- Adobe Portable Document Format
- Description:
- Main article
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 2.22 KB
- Format:
- Item-specific license agreed upon to submission
- Description: