tNodeEmbed
tNodeEmbed copied to clipboard
How to predict links for new data other than the test data
I trained the model for the "temporal link prediction" task. Now I have a set of edges with time stamps. How can I use the trained model to predict whether the the two nodes will interact at the given time stamp or not? Thank You
Hi,
I would suggest changing the model to return the LSTM sequence prediction and then choose the desired timestamp you want to predict on.
technically, in the following line return_sequences=True: https://github.com/urielsinger/tNodeEmbed/blob/cf24644fc110bb8a0e3a1f8d9891f812c63edeca/src/models/tNodeEmbed.py#L97 and then continue by selecting the wanted timestamp.
Uriel