lhovon / GNNs-for-drought

GNNs to predict droughts in Kenya. COMP 599 Project with Gabriel Tseng and Sierra Schena.
0 stars 0 forks source link

Data we are passing to the adjacency learner [exp. 1] #9

Open gabrieltseng opened 3 years ago

gabrieltseng commented 3 years ago

Passing all the timesteps seems nuts.

i.e. I retrieve batch (x, y) from the dataloader. I pass (x) to the adjacency learner, and retrieve an adjacency matrix (A) I then use (x, A, y) in my classifier to predict VCI.

The intuition is that A can depend on the timestep. So you a model which outputs an adjacency matrix per training-instance.