"Minimum Entropy Principle Guided Graph Neural Networks" by Zhenyu Yang, Ge Zhang et al.
Graph neural networks (GNNs) are now the mainstream method for mining graph-structured data and learning low-dimensional node- and graph-level embeddings to serve downstream tasks. However, limited by the bottleneck of interpretability that deep neural networks present, existing GNNs have ignored the issue of estimating the appropriate number of dimensions for the embeddings. Hence, we propose a novel framework called Minimum Graph Entropy principle-guided Dimension Estimation, i.e. MGEDE, that ...
Minimum Graph Entropy Dimension Estimation Raph Embedding Raph Entropy Graph Neural Network Code Embedding
Source: uow.edu.au