🌊 Online machine learning in Python

A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convol…

Frouros: an open-source Python library for drift detection in machine learning systems.

Code for our USENIX Security 2021 paper -- CADE: Detecting and Explaining Concept Drift Samples for Security Applications

The Tornado 🌪️ framework, designed and implemented for adaptive online learning and data stream mining in Python.

This is an official PyTorch implementation of the NeurIPS 2023 paper 《OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling》

Algorithms for detecting changes from a data stream.

AutoGBT is used for AutoML in a lifelong machine learning setting to classify large volume high cardinality data streams under concept-drift. AutoGBT was developed by a joint team ('autodidact.ai') from Flytxt, Indian Institute of Technology Delhi and CSIR-CEERI as a part of NIPS 2018 AutoML for Lifelong Machine Learning Challenge.

The official API of DoubleAdapt (KDD'23), an incremental learning framework for online stock trend forecasting, WITHOUT dependencies on the qlib package.

MemStream: Memory-Based Streaming Anomaly Detection

CinnaMon is a Python library which offers a number of tools to detect, explain, and correct data drift in a machine learning system

Online and batch-based concept and data drift detection algorithms to monitor and maintain ML performance.

📖These are the concept drift datasets we made, and we open-source the data and corresponding interfaces. Welcome to use them for free if there is a need.

unsupervised concept drift detection

A General Toolkit for Advanced Online Learning, Online Active Learning, Online Semi-supervised Learning Approaches

unsupervised concept drift detection with one-class classifiers

Broad Ensemble Learning System (BELS)

Algorithms proposed in the following paper: OLIVEIRA, Gustavo HFMO et al. Time series forecasting in the presence of concept drift: A pso-based approach. In: 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2017. p. 239-246.

a small example showing interactions between MLFlow and scikit-multiflow

This is an official PyTorch implementation of "Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting"