Comments (9)
Not yet. It'd be interesting to see for sure!
from nettack.
I have finished the experiment and it shows that nettack can also work on GAT.
from nettack.
from nettack.
That's very interesting. Thank you very much for running these experiments! In order to draw conclusions we'd have to repeat this for different datasets and nodes but this is a good proof of concept.
from nettack.
Yeah, That's just a beginning. Could you share the code to evaluate on multi-nodes?(how to choose nodes and evaluate more efficiently.), That will help me a lot.
from nettack.
Hi, I'm not sure I understand your question fully but I'll try my best to answer.
First, set n_influencers
to the desired number, e.g. 5.
Then there are two scenarios when we attack with n
attacker nodes:
- the target node has degree
dā„n
: select then
neighbors of the target that would lead to the lowest value oflogit(correct_class) - max{logit(other_classes)}
as attackers - the target node has degree
d < n
: first connect to then-d
nodes that are most beneficial to the adversary, and then we have ourn
attacker nodes.
Then you can use the script to perform and evaluate the attacks.
Does this answer your question?
from nettack.
Thanks for your answer, but it's not really what I want to understand more. In fact, I have written the code for evaluating 10+10+20 nodes as described in your paper. Do we need to retrain model 5 times for attacking each node(just as your demo)?
from nettack.
Hi,
Yes, in order to mitigate the effect of the random initialization we retrain each model five separate times per attack. We also repeat our experiments on five different splits into train/test nodes, i.e. for each of these splits we get (possibly different) 10+10+20 nodes.
Let me know in case something else is unclear.
from nettack.
That really helps me! Thank you! If I meet other problems, I will contact you by email.
from nettack.
Related Issues (15)
- 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
- Question about deriving Eq.(17) HOT 2
- Poster & Presentation Slides link is invalid HOT 1
- Question about surrogate model HOT 2
- 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
- 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
š 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. ššš
-
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 ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nettack.