Attentive Mixtures of Experts (AMEs)

Attentive Mixtures of Experts (AMEs) are neural network models that learn to output both accurate predictions and estimates of feature importance for individual samples.

Schwab, P., Miladinovic, D., & Karlen, W. (2019). Granger-Causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 4846–4853.

AMEs on github

Dose response networks (DRNets)

Dose response networks (DRNets) are a method for learning to estimate individual dose-​response curves for multiple parametric treatments from observational data using neural networks.


Schwab, P., Linhardt, L., Bauer, S., Buhmann, J. M., & Karlen, W. (2020). Learning Counterfactual Representations for Estimating Individual Dose-Response Curves. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5612–5619.

DRNets on github

Causal Explanations (CXPlain)

Causal Explanations (CXPlain) is a method for explaining the predictions of any machine-​learning model.


Schwab, P., & Karlen, W. (2019). CXPlain: Causal Explanations for Model Interpretation under Uncertainty. Annual Conference on Neural Information Processing Systems, NeurIPS 2019, 32, 9211.

CXPlain on github