gentlezhu / egi Goto Github PK
View Code? Open in Web Editor NEWTransfer Learning of Graph Neural Networks with Ego-graph Information Maximization (NeurIPS 21')
Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization (NeurIPS 21')
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
Hi GentleZhu,
I found that the code does not handle the scenario when data-id and data-src are different. I am not sure whether I miss any key part in the code.
Thanks and Regards,
PonderLY
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.