CEILS

Counterfactual Explanations as Interventions in Latent Space (CEILS) is a methodology to generate counterfactual explanations capturing by design the underlying causal relations from the data, and at the same time to provide feasible recommendations to reach the proposed profile.

Authors & contributors:

Riccardo Crupi, Alessandro Castelnovo, Daniele Regoli, Beatriz San Miguel Gonzalez

You can cite this work as:

@article{crupi2021counterfactual,
  title={Counterfactual Explanations as Interventions in Latent Space},
  author={Crupi, Riccardo and Castelnovo, Alessandro and Regoli, Daniele and Gonzalez, Beatriz San Miguel},
  journal={arXiv preprint arXiv:2106.07754},
  year={2021}
}

Documentation

To know more about this research work, please refer to our full paper.

Currently, CEILS has been published and/or presented in:

• 8th Causal Inference Workshop at UAI (causalUAI2021) (Video) by Riccardo Crupi
• Workshop on Explainable AI in Finance @ICAIF 2021 by Beatriz San Miguel
• ICAART - 14th International Conference on Agents and Artificial Intelligence @ICAART 2022 by Beatriz San Miguel

Installation

Create a new environment based on Python 3.9 or 3.6 and install the requirements.

Python 3.9:

pip install -r requirements.txt

Python 3.6:

pip install -r requirements_py36.txt

CEILS Workflow

CEILS workflow consists of the following steps:

Inputs

Two main inputs are needed:

• Data. Prepare your dataset as a pandas.DataFrame for the features (X) and a pandas.Series for the target variable (Y)
• Causal graph. Define your causal relations in a causal graph (G) using networkx.DiGraph.

Moreover, you need to define the features constrains (immutable, higher, lower) as a python dictionary, e.g. constraints_features = {"immutable": ["native-country"], "higher": ["age"]}

Generation of structural equations and the model in the latent space

In the method create_structural_eqs(X, Y, G) from core.build_struct_eq the following steps are carried out:

• generation of structural equations (F) mapping U to X (F: U->X)
• computation of residuals (U)
• generation of original ML model to predict the target variable Y using the features dataset (C: X->Y)
• composition of the model in the latent space, integrating the previous components (C_causal(U) = C(F(U)))

Summary of the main variables and functions involved:

Generation of counterfactual explanations

In the method create_counterfactuals(X, Y, G, F, C_causal, constraints_features, numCF=20) from core.counter_causal_generator, two set of counterfactual explanations will be generated based on:

• CEILS approach: uses the model in the latent space and a general counterfactual generator (Alibi in our current implementation)
• Baseline approach: uses the original model and the library Alibi

Evaluation

In the method calculate_metrics(X, Y, G, categ_features, constraints_features) from core.metrics, a set of metrics will be computed to compare the two sets of counterfactual explanations. The metrics will be printed.

Experiments

Currenly we have included 3 experiments based on public datasets and 2 experiments with synthetic data:

• German credit dataset
• Sachs
• Adult income dataset

Experiments are under a specific folder in:

\experiments_run

We recommend to check the run_experiment.py file to know the details and understand the whole CEILS workflow.

Synthetic datasets experiments are the best way to have a first understanding of our solution