Highlights
- Pro
Stars
A python package for benchmarking interpretability techniques on Transformers.
Python package designed to facilitate the creation and management of PyTorch DataLoaders with custom batch sizes and ratios.
Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).
Uncertainty quantification with PyTorch
Python implementation of the multistate Bennett acceptance ratio (MBAR)
TorchCFM: a Conditional Flow Matching library
A primer on Bayesian Neural Networks. The aim of this reading list is to facilitate the entry of new researchers into the field of Bayesian Deep Learning, by providing an overview of key papers. Mo…
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.
List of papers studying machine learning through the lens of category theory
Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks.
Removes large or troublesome blobs like git-filter-branch does, but faster. And written in Scala
Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/
OpenXAI : Towards a Transparent Evaluation of Model Explanations
The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
Paper list for equivariant neural network
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)
Statistical Rethinking Course for Jan-Mar 2023
Graph Neural Network Library for PyTorch
A curated collection of adversarial attack and defense on graph data.
A game theoretic approach to explain the output of any machine learning model.
A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).