Comments (4)
Hi thanks for the question! Currently it is normalized by the source node degree when self.deg_norm == 'rw'
. Can you explain a bit about "but actually we have to do relu(x1/degree_x1 + x2/degree_x1)" where x2 also gets normalized by degree_x1?
from botnet-detection.
Here is sketch what I meant, sorry for not good quality :)
from botnet-detection.
Hi I think based on your description, we first normalize the feature for each node based on it's outgoing degree, and then aggregate the features of different source nodes into a destination node. That's also what we did in the code. So for example in your above graph, we have sources of x1 being x0, x2, x4 (by looking at the 1st column of matrix A), then the resulted x1 = x0/2 + x2/2 + x4/4. Could you elaborate a bit more about the discrepancy? Sorry for my confusion.
from botnet-detection.
the line x_j = torch.index_select(x_j, 0, edge_index[0])
just duplicates the node features into each edge, which is sizing the source feature matrix (N x C) into a edge feature matrix (E x C) in order for aggregation. For example, if edge0 = (x_1, x_3), edge1 = (x_0, x_4), edge2 = (x_1, x_8), ..., then the resized matrix would be [feature of x_1; feature of x_0; feature of x_1; ...]. There is no normalization in this step.
from botnet-detection.
Related Issues (20)
- urllib.error.URLError: <urlopen error unknown url type: https> HOT 3
- Question about CAIDA account HOT 1
- Graphs have parallel edges HOT 1
- TypeError: scatter_add() takes from 2 to 5 positional arguments but 6 were given HOT 1
- Tips/sample code for visualizing graphs on the dataset HOT 1
- Questions about the Graph Dataset HOT 1
- torch_ scatter==1.3.1 installation was unsuccessful and torch_scatter==2.0.9 have a exception HOT 7
- I think there is a mistake HOT 2
- Could you provide the input data format? HOT 15
- Thank for your paper and repo. HOT 2
- xxxx Killed HOT 12
- I want draw architect model. Do you have any suggest for me? HOT 1
- Undirected or directed? And how creat a graph? HOT 2
- Question about result HOT 2
- Signed integer is greater than maximum HOT 2
- Synthetic data generation HOT 12
- Graph loading extremely slow? HOT 2
- Issues replicating on Jupyter notebook
- Running the training scripts in Jupyter: Issues with arguments HOT 23
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 botnet-detection.