An Efficient Embedding Framework for Uncertain Attribute Graph
Paper
Jiang, Ting, Yu, Ting, Qiao, Xueting and Zhang, Ji. 2023. "An Efficient Embedding Framework for Uncertain Attribute Graph." 34th International Conference on Database and Expert Systems Applications (DEXA 2023). Penang, Malaysia 28 - 30 Aug 2023 Switzerland . https://doi.org/10.1007/978-3-031-39821-6_18
Paper/Presentation Title | An Efficient Embedding Framework for Uncertain Attribute Graph |
---|---|
Presentation Type | Paper |
Authors | Jiang, Ting, Yu, Ting, Qiao, Xueting and Zhang, Ji |
Journal or Proceedings Title | Proceedings of 34th International Conference on Database and Expert Systems Applications (DEXA 2023) |
Journal Citation | 14147, pp. 219-229 |
Number of Pages | 11 |
Year | 2023 |
Place of Publication | Switzerland |
ISBN | 9783031398209 |
9783031398216 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-031-39821-6_18 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-031-39821-6_18 |
Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-3-031-39821-6 |
Conference/Event | 34th International Conference on Database and Expert Systems Applications (DEXA 2023) |
Event Details | 34th International Conference on Database and Expert Systems Applications (DEXA 2023) Parent International Conference on Database and Expert Systems Applications Delivery In person Event Date 28 to end of 30 Aug 2023 Event Location Penang, Malaysia |
Abstract | Graph data with uncertain connections between entities is commonly represented using uncertain graphs. This paper tackles the challenge of graph embedding within such uncertain attribute graphs. Current graph embedding techniques are typically oriented towards deterministic graphs, or uncertain graphs that lack attribute data. Furthermore, the majority of studies on uncertain graph learning simply adapt conventional algorithms for deterministic graphs to handle uncertainty, leading to compromised computational efficiency. To address these issues, we introduce an optimized embedding framework UAGE for uncertain attribute graphs. In UAGE, nodes are represented within a Gaussian distribution space to learn node attributes. We also propose a Probability Similarity Value (PSV) to manage relationship uncertainty and ensure that nodes with higher-order similar structures are located more closely in the latent space. Real-world dataset experiments confirm that UAGE surpasses contemporary methods in performance for downstream tasks. |
Keywords | encoder-decoder; Gaussian embedding; Uncertain graph |
ANZSRC Field of Research 2020 | 460299. Artificial intelligence not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Zhejiang Lab, China |
University of Southern Queensland |
Permalink -
https://research.usq.edu.au/item/z2768/an-efficient-embedding-framework-for-uncertain-attribute-graph
100
total views1
total downloads6
views this month0
downloads this month