EquiTriton is a project that seeks to implement high-performance kernels for commonly used building blocks in equivariant neural networks, enabling compute efficient training and inference.

GraphAny: A foundation model for node classification on any graph.

Neural Bellman-Ford networks implemented in MLX for Apple Silicon

Graph Neural Network library made for Apple Silicon

Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery supporting widely used materials science datasets, and built on top of PyTorch Lig…

TorchCFM: a Conditional Flow Matching library

A foundation model for knowledge graph reasoning

Graph Positional and Structural Encoder

code for Graph Neural Networks for Link Prediction with Subgraph Sketching https://arxiv.org/abs/2209.15486

Official implementation of A* Networks

A collection of resources on the topic of Complex Logical Query Answering

Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks.

Code for our paper "Attending to Graph Transformers"

Influence-Based Mini-Batching (IBMB), as proposed in "Influence-Based Mini-Batching for Graph Neural Networks" (LoG 2022)

Weisfeiler and Leman Go Relational (LOG 2022)

The OGB-LSC is the Large Scale Competition by Open Graph Benchmark to help accelerate research into machine learning on graph structured data

Official implementation of Inductive Logical Query Answering in Knowledge Graphs (NeurIPS 2022)

Long Range Graph Benchmark, NeurIPS 2022 Track on D&B

Official implementation of Graph Neural Network Query Executor (ICML 2022)

PyG re-implementation of Neural Bellman-Ford Networks (NeurIPS 2021)

Recipe for a General, Powerful, Scalable Graph Transformer

(Personalized) Page-Rank computation using PyTorch

Decorators for maximizing memory utilization with PyTorch & CUDA

🏅 KG Inductive Link Prediction Challenge (ILPC) 2022

A PyTorch and TorchDrug based deep learning library for drug pair scoring. (KDD 2022)

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs (ICLR'22)

Official implementation of Neural Bellman-Ford Networks (NeurIPS 2021)

Курс по квантовому машинному обучению