Hypergraph Neural Networks Based on Enclosing Subgraph Extraction for Link Prediction

Recently, the link prediction methods based on enclosing subgraph extraction and line graph transformation have been proven to achieve excellent prediction accuracy, but there are still some shortcomings, for examples, the time and space complexity of line graph transformation is too high and the gr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings - International Conference on Parallel and Distributed Systems s. 455 - 461
Hlavní autori: Chen, Liang, Zhao, Ying, Sajjanhar, Atul
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 10.10.2024
Predmet:
Accuracy
Complexity theory
Convolutional neural networks
dual hypergraph transformation
Feature extraction
Graph neural networks
hypergraph
hypergraph neural networks
link prediction
Memory management
Predictive models
Runtime
ISSN:2690-5965
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Recently, the link prediction methods based on enclosing subgraph extraction and line graph transformation have been proven to achieve excellent prediction accuracy, but there are still some shortcomings, for examples, the time and space complexity of line graph transformation is too high and the graph neural network it used ignores the high-order relationship and local clustering structure between nodes, which makes it difficult to be widely used in real life and may affect the prediction accuracy. To solve the above problems, a hypergraph neural network model based on enclosing subgraph extraction is proposed, which converts subgraph into hypergraph by dual hypergraph transformation, and uses the hypergraph convolutional neural network to learn the higher-order features of nodes and edges respectively. After three experiments, the results show that the proposed model not only has higher prediction accuracy, but also has shorter runtime and less memory usage.
ISSN:2690-5965
DOI:10.1109/ICPADS63350.2024.00066