ICML 2023: Initial commit of Simplicial Neural Networks

[Hellsegga]

This is a minimal first pull request for an implementation of Stefania Ebli, Michael Defferrard and Gard Spreemann. Simplicial Neural Networks. TDA {&} Beyond. 2020.

Comparison with the code of the authors of that paper plus extension or addition of new examples in the tutorial will be done later.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[ninamiolane]

🚀 (The doc deployment issue is on us, it is not related to this PR.)

[codecov]

Codecov Report

Merging #98 (5382ee0) into main (c471ea2) will increase coverage by 1.64%.
The diff coverage is 100.00%.

❗ Current head 5382ee0 differs from pull request most recent head edb885a. Consider uploading reports for the commit edb885a to get more accurate results

@@            Coverage Diff             @@
##             main      #98      +/-   ##
==========================================
+ Coverage   93.00%   94.64%   +1.64%     
==========================================
  Files           8        9       +1     
  Lines         200      224      +24     
==========================================
+ Hits          186      212      +26     
+ Misses         14       12       -2     

Impacted Files	Coverage Δ
topomodelx/nn/simplicial/snn_layer.py	100.00% <100.00%> (ø)

... and 1 file with indirect coverage changes

[mathildepapillon]

Hello @Hellsegga ! Thank you for your submission. As we near the end of the challenge, I am collecting participant info for the purpose of selecting and announcing winners. Please email me (or have one member of your team email me) at papillon@ucsb.edu so I can share access to the voting form. In your email, please include:

• your first and last name (as well as any other team members)
• the title of the model you implemented
• the domain of the model you implemented
• your pull request number (ICML 2023: Initial commit of Simplicial Neural Networks #98)

Before July 13, make sure that your submission respects all Submission Requirements laid out on the challenge page. Any submission that fails to meet this criteria will be automatically disqualified.

[Hellsegga]

Note that the coauthorship dataset will not be loaded currently due to problem reported in pyt-team/TopoNetX#195

A workaround is to install TopoNetX manually in editable mode
git clone https://github.com/pyt-team/TopoNetX
pip install -e '.[all]'

(instead of letting it be installed through the dependency management when installing TopoModelX).

This is also why "test_tutorial" fails.