Temporal Graph Neural Network
Temporal Graph Neural Networks (TGNNs) aim to analyze and predict the evolution of relationships within dynamic networks by incorporating both the structure of the graph and the temporal dynamics of its interactions. Current research emphasizes improving the efficiency and scalability of TGNNs, often through novel architectures like Transformers and optimized training strategies, as well as enhancing interpretability and addressing challenges like data sparsity and noise. This field is significant for its applications in diverse areas such as traffic forecasting, recommendation systems, and crime prediction, offering more accurate and insightful models for complex real-world phenomena.
Papers
Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction
Jhon A. Castro-Correa, Jhony H. Giraldo, Mohsen Badiey, Fragkiskos D. Malliaros
Exploiting Individual Graph Structures to Enhance Ecological Momentary Assessment (EMA) Forecasting
Mandani Ntekouli, Gerasimos Spanakis, Lourens Waldorp, Anne Roefs