The Competence Center Machine Learning Rhine-Ruhr (ML2R) connects pioneering research institutions to establish cutting-edge research, to support young scientists and to strengthen the technology transfer in companies. Our software repositories support these goals and foster reproducibility.

  • anon-github

    Simple tool that helps you to work with anonymous github accounts for paper submissions

    type:library area:other github paper submission tool
  • Graph Filtration Kernels

    Till Schulz, Pascal Welke, Stefan Wrobel, published at AAAI 2022 conference

    type:experiment area:hybrid Weisfeiler-Lehman Optimal Transport
  • A Generalized Weisfeiler-Lehman Graph Kernel

    Till Schulz, Pascal Welke, Stefan Wrobel, published in Machine Learning Journal, Springer 2022

    type:experiment area:hybrid Weisfeiler-Lehman Optimal Transport
  • Graph-Based Tensile Strength Approximation of Random Nonwoven Materials by Interpretable Regression

    Dario Antweiler, Marc Harmening, Nicole Marheineke, Andre Schmeißer, Raimund Wegener, Pascal Welke, published in Machine Learning with Applications(8), Elsevier 2022

    type:experiment area:hybrid area:resource-aware surrogate models linear regression feature extraction from graphs
  • IREE Bare-Metal Arm Sample

    Example for running IREE in a bare-metal Arm environment

    type:library area:resource-aware machine learning compiler
  • multibarplot

    Simple helper function to plot multible bar plots in the same Matplotlib figure

    type:library area:other visualization matplotlib
  • seedpy

    Easily seed frameworks used for machine learning like Numpy and PyTorch using context managers

    type:library area:other seeding numpy pytorch
  • PyPruning

    Ensemble pruning algorithms implemented in Python.

    type:library area:resource-aware ensembles pruning
  • Pysembles

    PyTorch + Ensembles = Pysembles. This is a collection of ensembling algorithms implemented in PyTorch.

    type:library area:other deep learning negative correlation learning bagging boosting
  • Submodular Streaming Maximization

    A C++ package for streaming submodular function maximization with Python bindings.

    type:library area:resource-aware area:other submodular function maximization data summaries summarization
  • CriticalDifferenceDiagrams.jl

    Plot critical difference diagrams with Julia and Tikz.

    type:library area:other hypothesis testing validation
  • MetaConfigurations.jl

    Derive a set of configurations (e.g, to specify experiments) from a single, more abstract and comprehensive meta-configuration.

    type:library area:other julia
  • Certification of Model Robustness in Active Class Selection

    M. Bunse and K. Morik at ECML-PKDD 2021.

    type:experiment area:resource-aware area:trustworthy learning theory label shift julia
  • Active Class Selection with Uncertain Deployment Class Proportions

    M. Bunse and K. Morik at the Interactive Adaptive Learning Workshop 2021.

    type:experiment area:resource-aware area:trustworthy learning theory label shift julia certification
  • Optimal Probabilistic Classification in Active Class Selection

    M. Bunse, D. Weichert, A. Kister, and K. Morik at ICDM 2020.

    type:experiment area:resource-aware area:trustworthy information theory python
  • HOPS: Probabilistic Subtree Mining for Small and Large Graphs

    P. Welke, F. Seiffarth, M. Kamp, and S. Wrobel at KDD 2020.

    type:experiment area:resource-aware area:hybrid
  • Probabilistic Gap Filling with Machine Learning - probgf

    R. Fischer, N. Piatkowski, C. Pelletier, G. Webb, F. Petitjean, and K. Morik at DSAA 2020.

    type:experiment area:hybrid
  • EAO: Evolutionary Algorithm Optimization

    Python toolkit for performing evolutionary optimization on custom domains.

    type:library area:resource-aware area:other evolutionary optimization genetic programming optimization
  • Decision Snippet Features

    P. Welke, F. Alkhoury, C. Bauckhage, and S. Wrobel at ICPR 2021.

    type:experiment area:hybrid area:resource-aware random forest model compression frequent subgraph mining
  • Generalized Isolation Forest

    S. Buschjäger, PJ. Honysz, and K. Morik:
    Randomized outlier detection with trees.
    International Journal of Data Science and Analytics (2020).

    type:library area:resource-aware outlier detection isolation forests
  • Exemplar-based clustering for GPUs

    PJ. Honysz, S. Buschjäger, & K. Morik. (2021).
    GPU-Accelerated Optimizer-Aware Evaluation of Submodular Exemplar Clustering.

    type:library area:resource-aware submodular functions exemplar clustering cuda
  • Neural Network Code Generator

    Compiler to generate C code from a trained neural network (Keras).

    type:library area:resource-aware Internet of Things Compiler Neural Network
  • Resource-Constrained On-Device Learning by Dynamic Averaging

    L. Heppe, M. Kamp, L. Adilova, D. Heinrich, N. Piatkowski, K. Morik
    Resource-Constrained On-Device Learning by Dynamic Averaging
    PDFL Workshop @ ECML-PKDD 2020

    type:experiment area:resource-aware federated distributed mrf resource-aware
  • Ariel Space Mission Challenge - Winning Submission

    M. Bunse and L. Heppe at ECML-PKDD 2021

    type:experiment area:other machine learning physics deep learning
  • bitvec

    Python toolbox for working with binary vectors

    type:library area:other numpy binary