Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)

Multivariate imputation and matrix completion algorithms implemented in Python

Implementation of Diffusion Convolutional Recurrent Neural Network in Tensorflow

A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputatio…

LibCity: An Open Library for Urban Spatial-temporal Data Mining

Deep Active Learning

Code for KDD'20 "Generative Pre-Training of Graph Neural Networks"

[ICLR 2020; IPDPS 2019] Fast and accurate minibatch training for deep GNNs and large graphs (GraphSAINT: Graph Sampling Based Inductive Learning Method).

TenforFlow Implementation of Neural Factorization Machine

Codebase for Generative Adversarial Imputation Networks (GAIN) - ICML 2018

Inductive graph-based matrix completion (IGMC) from "M. Zhang and Y. Chen, Inductive Matrix Completion Based on Graph Neural Networks, ICLR 2020 spotlight".

The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-s…

tsl: a PyTorch library for processing spatiotemporal data.

Chainer implementation of adversarial autoencoder (AAE)

Code to reproduce results from the paper: "Compressed Sensing using Generative Models".

Implementation of the "Deep Matrix Factorization Models for Recommender Systems"

Code of NIPS18 Paper: BRITS: Bidirectional Recurrent Imputation for Time Series

Granger causality discovery for neural networks.

Official repository for the paper "Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks" (ICLR 2022)

Reimplementation of "Reasoning With Neural Tensor Networks for Knowledge Base Completion" (Socher, Chen 2013) in Google's TensorFlow framework. MIT 6.806 Final Project. NOTE: Not maintained.

[NeurIPS 2021]: Improve the GNN expressivity and scalability by decoupling the depth and receptive field of state-of-the-art GNN architectures

TensorFlow implementation for the GP-VAE model described in https://arxiv.org/abs/1907.04155

Tensorflow implementation for "Generative Adversarial User Model forReinforcement Learning Based Recommendation System"

Multiple imputation utilising denoising autoencoder for approximate Bayesian inference

Spatio-Temporal Graph Convolutional Networks

Sparse modeling and Compressive sensing in Python

高斯过程回归