Jump to content

Talk:Topological deep learning

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia
[edit]

Prior content in this article duplicated one or more previously published sources. The material was copied from: https://www.researchgate.net/publication/370134352_Topological_Deep_Learning_Going_Beyond_Graph_Data. Copied or closely paraphrased material has been rewritten or removed and must not be restored, unless it is duly released under a compatible license. (For more information, please see "using copyrighted works from others" if you are not the copyright holder of this material, or "donating copyrighted materials" if you are.)

For legal reasons, we cannot accept copyrighted text or images borrowed from other web sites or published material; such additions will be deleted. Contributors may use copyrighted publications as a source of information, and, if allowed under fair use, may copy sentences and phrases, provided they are included in quotation marks and referenced properly. The material may also be rewritten, provided it does not infringe on the copyright of the original or plagiarize from that source. Therefore, such paraphrased portions must provide their source. Please see our guideline on non-free text for how to properly implement limited quotations of copyrighted text. Wikipedia takes copyright violations very seriously, and persistent violators will be blocked from editing. While we appreciate contributions, we must require all contributors to understand and comply with these policies. Thank you. Significa liberdade (she/her) (talk) 21:54, 21 March 2024 (UTC)[reply]

Feedback from New Page Review process

[edit]

I left the following feedback for the creator/future reviewers while reviewing this article: Thanks for this interesting article on a modern, if somewhat technical, field. The article does seem to be rather heavily based on Hajij et al (2022), but this does seem like an appropriate starting point. I note that you have acted on the copyright notices in an appropriate way. Impressive for a first article!

Klbrain (talk) 09:07, 26 March 2024 (UTC)[reply]

removing who first coined the term TDL as this the refererence is not accurate

[edit]

see for instance :

(825) Topological Deep Learning - YouTube

which is older than the reference mentioned in the article Topology.tda (talk) 23:05, 17 August 2024 (UTC)[reply]

Great reference! Why not integrate both of them to show the history better? Fraa Elor (talk) 05:24, 18 August 2024 (UTC)[reply]

TML / TDL & changes in introduction

[edit]

The changes in the introduction by @Topology.tda make the article somewhat confusing in my opinion. The current phrasing could equally apply to the term of geometric deep learning, which also specifically tackles other domains.

Would @Topology.tda kindly provide additional citations for the claim that topological machine learning is concerned with what I construe to be two specific algorithms arising from topological data analysis? My literature review did not uncover any such definition and I would like to understand it better where this is coming from.

My proposal is the following: Can we find a way to merge the existing perspectives such that it is more clear what aspects TDL handles and which remain handled by GDL? There is a recent paper (https://arxiv.org/abs/2402.08871) that provides a somewhat general definition. It would strike me as a useful way to follow this somewhat more general definition:

[...] However, this paper uses the term ‘TDL’ to refer to the collection of ideas and methods related to the use of topological concepts in deep learning [...]

Fraa Elor (talk) 17:41, 18 August 2024 (UTC)[reply]

hi Fraa,
Sounds great, I think we should make tdl more inclusive indeed. There is a recent paper by Papamarkou that we should consider in this direction. I'll add more details into the discussion here and let's edit till we arrive at a common ground.
I'll add more details also on topological machine learning. Please give me 48 hours to finish this. Topology.tda (talk) 17:45, 18 August 2024 (UTC)[reply]
That would be so great! In all honesty, it seems that TDL is much more dynamic at the moment, so maybe the other page is not necessarily needed? I understand that TDL is to TML as deep learning is to machine learning... Does this match your intuition (since you know a lot about the emerging TDL aspects)? Fraa Elor (talk) 18:19, 18 August 2024 (UTC)[reply]