Proud to share our 150-page "proto-book" with @mmbronstein @joanbruna @TacoCohen on geometric DL! Through the lens of symmetries and invariances, we attempt to distill "all you need to build the architectures that are all you need".
geometricdeeplearning.com
More info below! 🧵
geometricdeeplearning.com
More info below! 🧵
We have investigated the essence of popular deep learning architectures (CNNs, GNNs, Transformers, LSTMs) and realised that, assuming a proper set of symmetries we would like to stay resistant to, they can all be expressed using a common geometric blueprint.
But there's more!
But there's more!
Going further, we use our blueprint on less standard domains (such as homogeneous groups and manifolds), showing that the blueprint allows for nicely expressing recent advances in those areas, such as Spherical CNNs, SO(3)-Transformers, and Gauge-Equivariant Mesh CNNs.
Hence we believe that our work can be a useful way to navigate the increasingly challenging landscape of deep learning architectures. We'd also like to acknowledge Arthur Szlam, @trekkinglemon & @ylecun, who co-authored the first GDL survey in 2017 with two of our team.
arXiv (and other goodies, blogs and talks) coming soon! Our work is very much a work-in-progress, and we welcome any and all feedback!
• • •
Missing some Tweet in this thread? You can try to
force a refresh
