xiangyu918 Goto Github PK

annotated_deep_learning_paper_implementations

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

arope

This is the official implementation of "Arbitrary-Order Proximity Preserved Network Embedding"(KDD 2018).

autossl

[ICLR 2022] Implementation of paper "Automated Self-Supervised Learning for Graphs"

csdi

Codes for "CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation"

dggan

embedx

embedx 是基于 c++ 开发的、完全自研的分布式 embedding 训练和推理框架。它目前支持 图模型、深度排序、召回模型和图与排序、图与召回的联合训练模型等

graphmae

GraphMAE: Self-Supervised Masked Graph Autoencoders in KDD'22

grarep

A SciPy implementation of "GraRep: Learning Graph Representations with Global Structural Information" (WWW 2015).

hope

This is a sample implementation of "Asymmetric Transitivity Preserving Graph Embedding"(KDD 2016).

imgagn

Imbalanced Network Embedding vi aGenerative Adversarial Graph Networks

lemane

Learning Based Proximity Matrix Factorization for Node Embedding

mtt-distillation

Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

nrp-code

Code for Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank

openne

An Open-Source Package for Network Embedding (NE)

paretognn

Official repository for ICLR'23 paper: Multi-task Self-supervised Graph Neural Network Enable Stronger Task Generalization

pytorch-ts

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend

same

Code for the papers: "Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach", "A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings"

source-code-notebook

关于一些经典论文源码的逐行中文笔记

task_group

tinywebserver

:fire: Linux下C++轻量级Web服务器学习

transgan

[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

transgan-1

This is a re-implementation of TransGAN: Two Pure Transformers Can Make One Strong GAN (CVPR 2021) in PyTorch.

transganformer

Implementation of TransGanFormer, an all-attention GAN that combines the finding from the recent GanFormer and TransGan paper

xiangyu918.github.io

Blog