🧐How can we design neural networks that process other neural networks?
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.

We take an alternative approach: we introduce neural graphs, representations of neural networks as computational graphs of parameters.
This allows us to harness powerful graph neural networks and transformers that preserve permutation symmetry.
[5/9

🔍How can we design neural networks that take neural network parameters as input?
🧪Our #ICLR2024 oral on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" answers this question!

📜:💻:🧵 [1/9

github.com/mkofinas/neura… arxiv.org/abs/2403.12143

Join our poster on "Data Augmentations in Deep Weight Spaces" @neur_reps workshop, #NeurIPS2023, Ballroom A+B at 4pm!

Today at #NeurIPS2023 I will be presenting our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields".

Join us at poster session 3 on Wednesday morning, poster #619.

Paper:Source code:1/8] 🧵

github.com/mkofinas/aether arxiv.org/abs/2310.20679

How can we effectively use neural networks to process the parameters of other neural nets?

We propose representing neural networks as computation graphs, enabling the use of standard graph neural networks to preserve permutation symmetries.
Join our poster @TAGinDS in #ICML2023!

Excited to be in Hawaii for #ICML2023! Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.

Meet the giants at #icvss2023! 🤩

Kicking off #icvss2023 with generative models by @phillip_isola

"Neural Fields across Fields" workshop @iclr_conf happening now! Visit our poster on "Neural Fields for Latent Force Field Discovery in Interacting Systems".

x.com/hyunjik11/stat…

Excited to be in Kigali @iclr_conf! Ping me if you are also here and you want to have a chat. 🙂 I work on graph networks, equivariance, interacting systems, and neural fields.