Comments (2)
Hello, thanks for your interest in our paper!
The gradients will be accumulated for model parameters and perturbations M times in our algorithm. To way to realize it is to loss.backward() M times, but we only do gradient ascent for perturbations in the loop, without optimizing the model parameters. After we go outside the loop we optmize model parameter once. These match both our Algorithm 1 in the paper and our code.
Hope this makes sense!
from flag.
from flag.
Related Issues (11)
- no code for DeepGCN+FLAG on ogbg-molpcba and ogbg-code HOT 2
- default batch-size is too small HOT 1
- what is flag_product? HOT 2
- Evaluate on ogbg-code2 HOT 2
- Multi-gpu version HOT 4
- RuntimeError: [enforce fail at CPUAllocator.cpp:71] HOT 1
- Why not normalizing the gradient of perturbation HOT 1
- Augmentation types HOT 1
- Experiment on Cora HOT 3
- Add perturb before or after node encoder? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from flag.