Temporal neighbourhood aggregation: predicting future links in temporal graphs via recurrent variational graph convolutions
Autor: | Philip T. Jackson, Georgios Theodoropoulos, Amir Atapour-Abarghouei, John Brennan, Andrew Stephen McGough, Stephen Bonner, Ibad Kureshi, Boguslaw Obara |
---|---|
Rok vydání: | 2019 |
Předmět: |
Social and Information Networks (cs.SI)
FOS: Computer and information sciences Theoretical computer science Computer science Inference Graph theory Computer Science - Social and Information Networks 02 engineering and technology 010501 environmental sciences 01 natural sciences Graph Vertex (geometry) 0202 electrical engineering electronic engineering information engineering Task analysis Symmetric matrix 020201 artificial intelligence & image processing Feature learning Neighbourhood (mathematics) Decoding methods 0105 earth and related environmental sciences |
Zdroj: | 2019 IEEE International Conference on Big Data (Big Data). Piscataway, NJ: IEEE, pp. 5336-5345 IEEE BigData |
DOI: | 10.1109/BigData47090.2019.9005545 |
Popis: | Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal infernce tasks. To combat this, we introduce Temporal Neighbourhood Aggregation (TNA), a novel vertex representation model architecture designed to capture both topological and temporal information to directly predict future graph states. Our model exploits hierarchical recurrence at different depths within the graph to enable exploration of changes in temporal neighbourhoods, whilst requiring no additional features or labels to be present. The final vertex representations are created using variational sampling and are optimised to directly predict the next graph in the sequence. Our claims are reinforced by extensive experimental evaluation on both real and synthetic benchmark datasets, where our approach demonstrates superior performance compared to competing methods, out-performing them at predicting new temporal edges by as much as 23% on real-world datasets, whilst also requiring fewer overall model parameters. Comment: IEEE International Conference on Big Data 2019 |
Databáze: | OpenAIRE |
Externí odkaz: |