Wentao-Xu

Time-Series-Library

A Library for Advanced Deep Time Series Models.

torchscale

Foundation Architecture for (M)LLMs

PyTorch-Distributed-Training

Example of PyTorch DistributedDataParallel

KGE-CL

Source code for the COLING 2022 paper "KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings".

DGI

Deep Graph Infomax (https://arxiv.org/abs/1809.10341)

HIST

The source code and data of the paper "HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information".

SHGNN

The source code of the paper "SHGNN: Structure-Aware Heterogeneous Graph Neural Network"

SCINet

The GitHub repository for the paper: “Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction“. (NeurIPS 2022)

IGMTF

The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting".

HGNN-AC

Source code of "WWW21 - Heterogeneous Graph Neural Network via Attribute Completion"

MTGNN

multivariate-time-series-data

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

pytorch_geometric

Graph Neural Network Library for PyTorch

CorrectAndSmooth

[ICLR 2021] Combining Label Propagation and Simple Models Out-performs Graph Neural Networks (https://arxiv.org/abs/2010.13993)

KGE-DURA

The code of paper Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion. Zhanqiu Zhang, Jianyu Cai, Jie Wang. NeurIPS 2020.

SEEK

Source code for the ACL 2020 paper "SEEK: Segmented Embedding of Knowledge Graphs".

SuperGAT

[ICLR 2021] How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision

kbc

Tools for state of the art Knowledge Base Completion.

KGE

Some papers on Knowledge Graph Embedding(KGE)

pyGAT

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

qlib

Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.

benchmarking-gnns

Repository for benchmarking graph neural networks

ogb

Benchmark datasets, data loaders, and evaluators for graph machine learning

HGCN

MAGNN

Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

pyHGT

Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric

Graph_Transformer_Networks

Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

HAN

Heterogeneous Graph Neural Network

Conference-Acceptance-Rate

Acceptance rates for the major AI conferences