Sheaf Neural Networks — mentioned by mjhay

Tue, 11 Jun 2024 13:33:16 GMT

There's been a decent amount of work using simplicial complexes and related ideas to generalize graph neural networks, e.g. [0], [1]. If LLMs obey a similar geometry, it could be a promising direction for multimodal models and more principled RAGs with better inductive biases. [0] https://arxiv.org/pdf/2010.03633 [1] https://arxiv.org/pdf/2012.06333

Paper and discussion history. A mention is not an endorsement.

Sheaf Neural Networks — mentioned by gspr

Thu, 05 Aug 2021 06:04:47 GMT

At least there is work on greatly generalizing convolutions. They're much more broadly applicable (in neural networks) to very differently structured data than they appear to be in their standard form. (The "in neural networks" qualifier is there because quite a bit of this has been understood about the mathematical operation convolution for a long long time). Some recent developments: * https://arxiv.org/abs/2010.03633 (disclosure: I'm one of the authors) * https://arxiv.org/abs/2012.06333

Paper and discussion history. A mention is not an endorsement.

Sheaf Neural Networks · HackerPapers discussions

Sheaf Neural Networks — mentioned by mjhay

Sheaf Neural Networks — mentioned by gspr