I am wondering if there are gnn explainable methods for a regression task (e.g., traffic forecasting) where nodes have numerical features and the predicted output is a numerical value. Most of research papers focus on node classification tasks (GNNexplainer etc) but do not specify if these techniques are fit for node-regression tasks.
$\begingroup$
$\endgroup$
1
-
$\begingroup$ Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. $\endgroup$– Community BotDec 6, 2022 at 20:42
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
1
There are several GNN-based approaches for tasks like traffic speed prediction or railway delay prediction, which are doing time-series regression on nodes.
For example:
T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
Railway Delay Prediction with Spatial-Temporal Graph Convolutional Networks
-
$\begingroup$ Thank you for your response, my question is actually for Explainable GNN frameworks for a temporal task like traffic forecasting such as GNNexplainer or GraphSVX. $\endgroup$ Jan 10 at 13:55