sherrylone / m-mix Goto Github PK
View Code? Open in Web Editor NEWSIGKDD 2022 paper
SIGKDD 2022 paper
Hi, I have some question in node classification task.
(1)In line 53 of node/model.py, why shouldn't be like this:
out = self.to_v(torch.bmm(attention, out))
(2)and the object of trainning is set to be CrossEntropyLoss between 'new_label' and 'logits', which does not match the description in Section 3.3. Moreover, it is different from the implement of 'mvgrl'. I hope to know your consideration in this regard.
From table 8, I find that you reproduce GRACE and its variants with M-mix. I try to reproduce the results reported in the paper but can't get ideal result. Starting from base version of GRACE, I create two views based on node feature masking and generate hard
negatives Zห๐ by mp-Mix followed an MLP module. Then I use CE loss to train the model and test the model on the dataset DBLP. The accuracy is around 0.82 which is lower than GRACE(0.84). Did I miss something or could you provide the implementation code of this part? Thanks a lot.
Can you release full version of your code? There is no implement of 'load'.
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.