Epidemic Source Identification Based on Infection Graph Learning
Paper
Hong, Xingyun, Yu, Ting, Li, Zhao and Zhang, Ji. 2024. "Epidemic Source Identification Based on Infection Graph Learning." 7th International Joint Conference on Asia-Pacific Web and Web-Age Information Management (APWeb-WAIM 2023). Wuhan, China 06 - 08 Oct 2023 Singapore . Springer. https://doi.org/10.1007/978-981-97-2303-4_16
Paper/Presentation Title | Epidemic Source Identification Based on Infection Graph Learning |
---|---|
Presentation Type | Paper |
Authors | Hong, Xingyun, Yu, Ting, Li, Zhao and Zhang, Ji |
Journal or Proceedings Title | Proceedings of the 7th International Joint Conference on Asia-Pacific Web and Web-Age Information Management (APWeb-WAIM 2023) |
Journal Citation | 14331, pp. 236-251 |
Number of Pages | 16 |
Year | 2024 |
Publisher | Springer |
Place of Publication | Singapore |
ISBN | 9789819723027 |
9789819723034 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-981-97-2303-4_16 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-981-97-2303-4_16 |
Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-981-97-2303-4 |
Conference/Event | 7th International Joint Conference on Asia-Pacific Web and Web-Age Information Management (APWeb-WAIM 2023) |
Event Details | 7th International Joint Conference on Asia-Pacific Web and Web-Age Information Management (APWeb-WAIM 2023) Parent Joint International Conference on Asia-Pacific Web Conference (APWeb)/Web-Age Information Management (WAIM) Delivery In person Event Date 06 to end of 08 Oct 2023 Event Location Wuhan, China |
Abstract | Source identification plays a critical role in various domains, including patient zero tracing, social network rumor source detection, and more, as it enables tracing propagation processes and implementing effective measures to block transmission. However, most algorithms employed to identify propagation sources in networks heavily rely on prior knowledge of the underlying propagation models and associated parameters, as different propagation patterns yield diverse outcomes. To address this limitation, we present an approach called Infection Graph Learning for Sourcing (IGLS), which utilizes multiple snapshots to learn the propagation pattern. In this method, the source identification problem is redefined as a novel graph node classification scenario solved using Graph Convolutional Networks (GCN). The IGLS model takes both the state of nodes and the network’s structure into consideration while introducing a new loss function specifically designed for the task. Furthermore, to tackle the multiple source identification problem, multi-task learning is incorporated into the IGLS model structure, identifying the number of sources and their locations simultaneously. This represents the first application of a deep learning model to address problems involving an unknown number of sources. We conducted experiments on both synthetic and real-world networks, and the results demonstrate the effectiveness and superiority of our proposed method. |
Keywords | Graph Convolutional Network; Source identification; Infection graphlearning |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 460306. Image processing |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Series | Lecture Notes in Computer Science |
Byline Affiliations | Zhejiang Lab, China |
Hangzhou Yugu Technology, China | |
University of Southern Queensland |
Permalink -
https://research.usq.edu.au/item/z8615/epidemic-source-identification-based-on-infection-graph-learning
11
total views1
total downloads1
views this month0
downloads this month