NeuralGraphPDE

Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks

https://github.com/yichengdwu/neuralgraphpde.jl

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Committers with academic emails
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (12.0%) to scientific vocabulary

Keywords

deep-learning equivariant-representations gnn graph-neural-networks julia partial-differential-equations

Keywords from Contributors

pde parallelism numerics probability-distributions uncertainties pinns neural-operator numerical-methods neural-ode jax

Last synced: 9 months ago · JSON representation ·

Repository

Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks

Basic Info

Host: GitHub
Owner: YichengDWu
License: mit
Language: Julia
Default Branch: main
Homepage: https://yichengdwu.github.io/NeuralGraphPDE.jl/dev/
Size: 709 KB

Statistics

Stars: 18
Watchers: 2
Forks: 1
Open Issues: 9
Releases: 11

Topics

deep-learning equivariant-representations gnn graph-neural-networks julia partial-differential-equations

Created almost 4 years ago · Last pushed over 2 years ago

Metadata Files

Readme License Citation

README.md

NeuralGraphPDE

This package is based on GraphNeuralNetwork.jl and Lux.jl.

The goal is to extend Neural (Graph) ODE to Neural Graph PDE (experimental).

Technically, it has become a general framework for graph neural networks.

References

Iakovlev V, Heinonen M, Lähdesmäki H. Learning continuous-time PDEs from sparse data with graph neural networks[J]. arXiv preprint arXiv:2006.08956, 2020.
Poli M, Massaroli S, Rabideau C M, et al. Continuous-depth neural models for dynamic graph prediction[J]. arXiv preprint arXiv:2106.11581, 2021.
Chamberlain B, Rowbottom J, Gorinova M I, et al. Grand: Graph neural diffusion[C]. International Conference on Machine Learning. PMLR, 2021: 1407-1418.
Brandstetter J, Worrall D, Welling M. Message passing neural PDE solvers[J]. arXiv preprint arXiv:2202.03376, 2022.
Li Z, Kovachki N, Azizzadenesheli K, et al. Neural operator: Graph kernel network for partial differential equations[J]. arXiv preprint arXiv:2003.03485, 2020.
Toshev, Artur, et al. "On the Relationships between Graph Neural Networks for the Simulation of Physical Systems and Classical Numerical Methods." ICML 2022 2nd AI for Science Workshop. 2022.

Current Status

This package is no longer actively maintained.

What does this mean?

No new features will be added, and issues will not be actively triaged or resolved.
The repository will remain available as an archive, and the code can still be accessed and used.

Can I still use the package?

Yes, you can continue to use the package, but please do so with caution. As it won’t be updated, it may not work in future versions of dependent technologies.

Owner

Name: Ethan Wu
Login: YichengDWu
Kind: user
Location: Calgary, AB

Repositories: 152
Profile: https://github.com/YichengDWu

Citation (CITATION.bib)

@misc{NeuralGraphPDE.jl,
	author  = {Shambles},
	title   = {NeuralGraphPDE.jl},
	url     = {https://github.com/MilkshakeForReal/NeuralGraphPDE.jl},
	version = {v0.1.6},
	year    = {2022},
	month   = {7}
}

GitHub Events

Total

Watch event: 1

Last Year

Watch event: 1

Committers

Last synced: over 1 year ago

All Time

Total Commits: 301
Total Committers: 4
Avg Commits per committer: 75.25
Development Distribution Score (DDS): 0.083

Past Year

Commits: 0
Committers: 0
Avg Commits per committer: 0.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
NeuralGraphPDE	y**u@u**a	276
CompatHelper Julia	c**y@j**g	13
github-actions[bot]	4****]	9
Pietro Monticone	3****e	3

Committer Domains (Top 20 + Academic)

julialang.org: 1 ucalgary.ca: 1

Issues and Pull Requests

Last synced: over 1 year ago

All Time

Total issues: 22
Total pull requests: 57
Average time to close issues: 4 days
Average time to close pull requests: 5 days
Total issue authors: 2
Total pull request authors: 3
Average comments per issue: 2.18
Average comments per pull request: 0.49
Merged pull requests: 47
Bot issues: 0
Bot pull requests: 21

Past Year

Issues: 0
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

YichengDWu (21)
JuliaTagBot (1)

Pull Request Authors

YichengDWu (35)
github-actions[bot] (20)
pitmonticone (1)

Top Labels

Issue Labels

enhancement (1) breaking (1)

Pull Request Labels

breaking (1)

Packages

Total packages: 1
Total downloads: unknown

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 11

juliahub.com: NeuralGraphPDE

Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks

Homepage: https://yichengdwu.github.io/NeuralGraphPDE.jl/dev/
Documentation: https://docs.juliahub.com/General/NeuralGraphPDE/stable/
License: MIT
Latest release: 0.2.0
published almost 3 years ago

Versions: 11
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent repos count: 9.9%

Average: 24.4%

Dependent packages count: 38.9%

Last synced: 10 months ago