Comments (2)
Hi,
Thanks for your interest in our work. I'm not sure I understand the question, so I'll just give the answer a shot. Feel free to ask a follow-up question if anything remains unclear.
It seems that you're confused about A
, A_tilde
, and A_hat
in the proof of Eq. (17). Specifically, the confusion seems to be about the first full-row equation in the proof [A_hat_square]_{uv} = …
. The difference between A_tilde
and A
is subtle. As specified right below Eq. (1), A_tilde
is the adjacency matrix with added self-loops (via adding the identity matrix). A_hat
, on the other hand, is the degree-normalized version of A_tilde
(see below Eq. (2)).
In the proof we use at several places the fact that diagonal elements A_{uu}=0
as we consider graphs without self-loops, while A_tilde_{uu}=1
because we added the self-loops.
from nettack.
Oh thanks for the detailed explanation, I totally get it.
from nettack.
Related Issues (16)
- Dimension of Citeseer Dataset
- a problem about the node feature HOT 1
- About the pytorch version HOT 1
- Computation of score functions in feature attacks HOT 4
- Poster & Presentation Slides link is invalid HOT 1
- Question about surrogate model HOT 2
- How to perform structure perturbates on Polblogs?
- AttributeError: A1 not found in demo when perturb_structure = False HOT 1
- No Features for polblogs? HOT 3
- Regeneration of results from the paper HOT 5
- Indirect attack not working when influencers > num_neighbors
- why the model predict the correct label successfully after attack in demo HOT 1
- Have you tried transfering the attack generated by nettack to GAT? HOT 9
- Possibilities of extending the nettack to the task of graph classification HOT 2
- Will the default execution of the code exactly reproduce the example image? HOT 2
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 nettack.