mkofinas/neural-graphs
Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).
This project helps machine learning researchers understand and predict the behavior of neural networks. It takes existing neural networks, represented as graphs, and applies Graph Neural Networks to analyze them. The output provides insights into how different network architectures perform on tasks like image classification or style editing, benefiting researchers who design and evaluate deep learning models.
No commits in the last 6 months.
Use this if you are a machine learning researcher or deep learning engineer interested in analyzing, comparing, or predicting the performance of different neural network architectures.
Not ideal if you are looking for a tool to train or deploy standard machine learning models without a focus on their underlying graph-based representations.
Stars
82
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jul 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mkofinas/neural-graphs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SamsungSAILMontreal/nino
Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [ICLR 2025]
graphdeeplearning/graphtransformer
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to...
vijaydwivedi75/gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional...
snap-stanford/relgt
Relational Graph Transformer
omron-sinicx/crystalframer
The official code respository for "Rethinking the role of frames for SE(3)-invariant crystal...