Pre-training and applying for node classification

[timilsinamohan]

Hi thanks for this great library :-) !

I have two graphs , I want to train large graph (A) and then do the transfer learning in target graph (B) for node classification task. It is something like you have shown in the paper: https://arxiv.org/pdf/2009.05204.pdf, at Table 7, for training in the European airport (source) and transferring it to USA(target) and Brazil airport(target).

I run the code like this to run EGI model:
python run_airport.py --data-id="data/europe-airports.edgelist" --data-src="data/europe-airports.edgelist" --file-path=data/usa-airports.edgelist --label-path=data/labels-usa-airports.txt --n-dgi-epochs=100 --n-hidden=32 --self-loop --gpu=0 --n-layers=1 --dgi-lr=0.01 --model-id=2 --model-type=2
It reports me the accuracy: Test Accuracy 0.6319, std 0.0161

I presume --data-src argument is for the source graph parameter. Is this correct? Don't we need the labels for the source graph? Did I miss something? If it is not could you kindly guide me which code is to use for the pre-training and then apply transfer learning ?

Thanks in advance,
Mohan

[Skyorca]

--label-path=data/labels-usa-airports.txt is the path for source labels which you have already loaded