Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Midterm Peer Review ty364 #10

Open
ghost opened this issue Nov 15, 2019 · 0 comments
Open

Midterm Peer Review ty364 #10

ghost opened this issue Nov 15, 2019 · 0 comments

Comments

@ghost
Copy link

ghost commented Nov 15, 2019

The project is to evaluate the limitation of Neural Network based methods for the minimum spanning tree problem by build a graph neural network architecture. The algorithm performance will be compared with Kruskal's or Prim's algorithm for solving minimum spanning trees, given a fixed amount of training time, a fixed number of examples, or other limited resources.

What do you like about the proposal?
The research idea is based on a paper around TSP
The research topic is clear and the evaluation method is feasible.

What concerns you?
What is the results? Does the GNN architecture perform better than the Kruskal's or Prim's algorithm for solving minimum spanning trees?

Do you think you could use the results of this study?
The new algorithm is advanced and has reference value.

What other aspects of the question do you think the group should consider?
How does the group achieve the preliminary results comparison with traditional architecture? Is there any benchmarks to quantify the results?

In conclusion, great project. The group developed the project in a clear research logic.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

0 participants