Highlights
- Pro
📚 Research Paper
[VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.
Graphormer is a general-purpose deep learning backbone for molecular modeling.
37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 20 datasets.
This repo hosts notebooks, cleaned data files to create an intrusion detection system using Deep learining.
Benchmark datasets, data loaders, and evaluators for graph machine learning
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Graph Neural Network Library for PyTorch
FedGraphNN: A Federated Learning Platform for Graph Neural Networks with MLOps Support. The previous research version is accepted to ICLR'2021 - DPML and MLSys'21 - GNNSys workshops.
A library for federated learning (a distributed machine learning process) in an enterprise environment.
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o…
Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.
An Industrial Grade Federated Learning Framework
Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
The GitHub repository for the paper "Informer" accepted by AAAI 2021.
Making large AI models cheaper, faster and more accessible
An easy-to-use federated learning platform
Time series forecasting by transformer
Wind Power Forecasting using Machine Learning techniques.
Wind Power forecasting for the day-ahead energy market - Data Challenge
PaddleSpatial is an open-source spatial-temporal computing tool based on PaddlePaddle.
Source code of ICML'22 paper: FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
A python library for user-friendly forecasting and anomaly detection on time series.
The GitHub repository for the paper: “Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction“. (NeurIPS 2022)
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM