Stars
Microsoft Graphormer (https://arxiv.org/abs/2106.05234) rewritten in Pytorch-Geometric
The official implementation for NeurIPS2023 paper "SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations"
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.
Label-free Node Classification on Graphs with Large Language Models (LLMS)
A community-maintained Python framework for creating mathematical animations.
A course on aligning smol models.
Simple, unified interface to multiple Generative AI providers
[ICLR 2024] VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
Fastest random walks generator on networkx graphs
⚡️ A tmux plugin giving you a hackable status bar consisting of dynamic & beautiful looking powerline segments, written purely in bash.
[ICLR'25 Spotlight] Revisiting Random Walks for Learning on Graphs (RWNN), in PyTorch
Graph Positional and Structural Encoder
Source 9780 code for the paper "Simulation of Graph Algorithms with Looped Transformers"
Transformers and Reasoners Algorítmicos Neurais (NARs)
Code for our paper "Attending to Graph Transformers"
[NeurIPS 2024] Implementation of "Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification"
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Matrix Calculus via Differentials, Matrix Derivative, 矩阵求导教程
MIT IAP short course: Matrix Calculus for Machine Learning and Beyond
✱ Understanding the underlying learning dynamics of simple tasks in Transformer networks
Mechanistic Interpretability for Transformer Models