graphpku / jacobiconv Goto Github PK
View Code? Open in Web Editor NEWHow Powerful are Spectral Graph Neural Networks
How Powerful are Spectral Graph Neural Networks
Dear authors,
Thanks for sharing the code of the excellent work.
I notice that the implementation of Jacobi basis is different from the gold form of recurrence relations of Jacobi polynomials, as it introduces extra two parameters l and r. Although the two versions are equivalent when fixing l=-1 and r=1, I wonder what the source of the recurrence formula corresponding to the implementation.
Besides, I aslo notice that in line 148 of the file impl/PolyConv.py, the variable tmp2_2 has a negative before it. If simply considering the a parameter as beta of Jacobi polynomials and the b parameter as alpha, the coef1 (line 134) should have a negative also. I wonder if this is my misunderstanding on the implementation.
Very thanks for your attention and reply!
First of all, thank you for your great work. After reading your paper, I have a question: How are the proportions of multiple eigenvalues in Table 7 in the appendix calculated? I used the same data set to calculate the proportion of multiple eigenvalues, and the results far exceeded those in Table 7. If it's convenient, can you provide the relevant code?
Dear authors,
Thanks for sharing the code of the excellent work JacobiConv.
Recently, I try to re-implement the model and met a question on the implementation of JacobiConv.
The recurrence relations of Jacobi polynomials have the form
where
However, I notice that in line 148 of the file impl/PolyConv.py, the variable tmp2_2
, which in my opinion represents
I wonder if this is my misunderstanding on the implementation, or just a mistake in the code?
Very thanks for your attention and reply!
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.