fig4

Graph neural networks for molecular and materials representation

Figure 4. The GNNs with different methods. (A) spectral convolution; (B) spatial convolution; (C) recurrence; (D) skip connection; (E) subgraph embedding. GNNs: graph neural networks.

Journal of Materials Informatics
ISSN 2770-372X (Online)
Follow Us

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/