NeuralProphet is an easy to learn framework for interpretable time series forecasting. NeuralProphet is built on PyTorch and combines Neural Networks and traditional time-series algorithms, …
Keywords: time series, forecasting, human in the lopp, machine learning, Python, PyTorch
Newspaper3k is a Python 3 package for News, full-text, and article metadata extraction. It has many features including: (1) multi-threaded article download framework; (2) news …
Keywords: article scraping, multilingual, Python
The reference implementation of the node2vec algorithm for unsupervised graph representation learning.
The node2vec framework learns low-dimensional representations for nodes in a graph by optimizing …
Keywords: graph representation learning, random walks, neural network, skipgram, Python
This package implements fast/scalable node embedding algorithms. This can be used to embed the nodes in graph objects and arbitrary SciPy CSR Sparse Matrices. It …
Keywords: node embeddings, graph representation learning, Node2Vec, Python
A PyTorch implementation of normalizing flows. Many popular flow architectures are implemented including GLOW, NICE, Real NVP, Masked Autoregressive Flow, Planar Flow, Radial Flow and …
Keywords: normalising flows, GLOW, NICE, Real NVP, Neural Spline Flow, generative model, probabilistic programming, Python, PyTorch
Causal structure inference from observational data using continuous optimisation.
Keywords: causal inference, causal structure learning, DAGs, Bayesian Networks, machine learning, Python, PyTorch
The Pytorch implementation of the OpenAI paper titled "Jukebox: A Generative Model for Music" by P. Dhariwal, H. Jun, C. Payne, J. W. Kim, A. …
Keywords: OpenAI, Jukebox, generative modelling, deep generative model, music, deep learning, deep neural network, machine learning, PyTorch
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Keywords: large language model, LLM, assistant, chat bot, discord, machine learning, natural language processing, NLP, chatGPT, Python, PyTorch
Optuna is an automatic hyperparameter optimization software framework, particularly designed for machine learning. It features an imperative, define-by-run style user API. Thanks to our define-by-run …
Keywords: hyper-parameter optimization, hyper-parameter tuning, Python
The official implementation of the PairNorm normalisation layer for graph neural networks (GNNs). It is useful for tackling the oversmoothing problem in deep GNNs and …
Keywords: graph neural networks, oversmoothing, layer normalisation, GNN, PyTorch, Python, PyTorch Geometric