Context-sensitive ranking

machine-learning, deep-learning, tensorflow, pytorch, ranking, neural-networks, learning-to-rank, context-aware, choice-model, discrete-choice, object-ranking
pip install csrank==2.0.0rc2


Coverage Binder


This library has recently been migrated from tensorflow to PyTorch. The 2.0 version marks a breaking change. Some of the previous functionality is now unavailable and some classes behave differently. You can use the latest 1.x release if you are looking for the tensorflow based estimators.


CS-Rank is a Python package for context-sensitive ranking and choice algorithms.

We implement the following new object ranking/choice architectures:

  • FATE (First aggregate then evaluate)
  • FETA (First evaluate then aggregate)

In addition, we also implement these algorithms for choice functions:

  • RankNetChoiceFunction
  • GeneralizedLinearModel
  • PairwiseSVMChoiceFunction

These are the state-of-the-art approaches implemented for the discrete choice setting:

  • GeneralizedNestedLogitModel
  • MixedLogitModel
  • NestedLogitModel
  • PairedCombinatorialLogit
  • RankNetDiscreteChoiceFunction
  • PairwiseSVMDiscreteChoiceFunction

Getting started

As a simple "Hello World!"-example we will try to learn the Pareto problem:

import csrank as cs
from csrank import ChoiceDatasetGenerator
gen = ChoiceDatasetGenerator(dataset_type='pareto',
X_train, Y_train, X_test, Y_test = gen.get_single_train_test_split()

All our learning algorithms are implemented using the scikit-learn estimator API. Fitting our FATENet architecture is as simple as calling the fit method:

fate = cs.FATEChoiceFunction()
fate.fit(X_train, Y_train)

Predictions can then be obtained using:



The latest release version of CS-Rank can be installed from Github as follows:

pip install git+https://github.com/kiudee/cs-ranking.git

Another option is to clone the repository and install CS-Rank using:

python setup.py install


CS-Rank depends on PyTorch, skorch, NumPy, SciPy, matplotlib, scikit-learn, joblib and tqdm. For data processing and generation you will also need PyGMO, H5Py and pandas.

Citing CS-Rank

You can cite our arXiv papers:

  author    = {Karlson Pfannschmidt and
               Pritha Gupta and
               Eyke H{\"{u}}llermeier},
  title     = {Learning Choice Functions: Concepts and Architectures },
  journal   = {CoRR},
  volume    = {abs/1901.10860},
  year      = {2019}

  author    = {Karlson Pfannschmidt and
               Pritha Gupta and
               Eyke H{\"{u}}llermeier},
  title     = {Deep architectures for learning context-dependent ranking functions},
  journal   = {CoRR},
  volume    = {abs/1803.05796},
  year      = {2018}


Apache License, Version 2.0