Use Transformer instead of RNN and test performance

barkincavdaroglu / Link-Prediction-Mesh-Network

PyTorch Implementation of a Deep Learning Model for Temporal Link Prediction in MANETs

2 stars 1 forks source link

Use Transformer instead of RNN and test performance #29

Open barkincavdaroglu opened 1 year ago

barkincavdaroglu commented 1 year ago

Transformer will take the output of GN block in sequence and output target predictions. It might make sense to test with both current convolutional layer (Graph Attention Network) and another (such as Sage).