Overall architecture of RADGCN. (IMAGE)

Tsinghua University Press

Overall architecture of RADGCN.

Caption

The key modules of RADGCN include K-order subgraph sampling, encoder of observed nodes, attention-based relation diffusion (ABR-DGCN), relation-augmented feature diffusion (RAF-DGCN), edge-prediction module, as well as decoder.

Credit

Communications in Transportation Research

Usage Restrictions

Credit must be given to the creator.

License

CC BY

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.