Elias Chaibub Neto

Elias Chaibub Neto

Linear residualization is a common practice for confounding adjustment in machine learning (ML) applications. Recently, causality-aware predictive modeling has been proposed as an alternative causality-inspired approach for adjusting for confounders. The basic idea is to simulate counterfactual data that is free from the spurious associations generated by the observed confounders. In this paper, we compare the linear residualization approach against the causality-aware confounding adjustment in anticausal prediction tasks, and show that the causality-aware approach tends to (asymptotically) outperform the residualization adjustment in terms of predictive performance in linear learners. Importantly, our results still holds even when the true model is not linear. We illustrate our results in both regression and classification tasks, where we compared the causality-aware and residualization approaches using mean squared errors and classification accuracy in synthetic data experiments where the linear regression model is mispecified, as well as, when the linear model is correctly specified. Furthermore, we illustrate how the causality-aware approach is more stable than residualization with respect to dataset shifts in the joint distribution of the confounders and outcome variables.

Elias Chaibub Neto, Phil Snyder, Solveig K Sieberts et al.

In health related machine learning applications, the training data often corresponds to a non-representative sample from the target populations where the learners will be deployed. In anticausal prediction tasks, selection biases often make the associations between confounders and the outcome variable unstable across different target environments. As a consequence, the predictions from confounded learners are often unstable, and might fail to generalize in shifted test environments. Stable prediction approaches aim to solve this problem by producing predictions that are stable across unknown test environments. These approaches, however, are sometimes applied to the training data alone with the hope that training an unconfounded model will be enough to generate stable predictions in shifted test sets. Here, we show that this is insufficient, and that improved stability can be achieved by deconfounding the test set features as well. We illustrate these observations using both synthetic data and real world data from a mobile health study.

Elias Chaibub Neto

Causal modeling has been recognized as a potential solution to many challenging problems in machine learning (ML). Here, we describe how a recently proposed counterfactual approach developed to deconfound linear structural causal models can still be used to deconfound the feature representations learned by deep neural network (DNN) models. The key insight is that by training an accurate DNN using softmax activation at the classification layer, and then adopting the representation learned by the last layer prior to the output layer as our features, we have that, by construction, the learned features will fit well a (multi-class) logistic regression model, and will be linearly associated with the labels. As a consequence, deconfounding approaches based on simple linear models can be used to deconfound the feature representations learned by DNNs. We validate the proposed methodology using colored versions of the MNIST dataset. Our results illustrate how the approach can effectively combat confounding and improve model stability in the context of dataset shifts generated by selection biases.

Elias Chaibub Neto

The roles played by learning and memorization represent an important topic in deep learning research. Recent work on this subject has shown that the optimization behavior of DNNs trained on shuffled labels is qualitatively different from DNNs trained with real labels. Here, we propose a novel permutation approach that can differentiate memorization from learning in deep neural networks (DNNs) trained as usual (i.e., using the real labels to guide the learning, rather than shuffled labels). The evaluation of weather the DNN has learned and/or memorized, happens in a separate step where we compare the predictive performance of a shallow classifier trained with the features learned by the DNN, against multiple instances of the same classifier, trained on the same input, but using shuffled labels as outputs. By evaluating these shallow classifiers in validation sets that share structure with the training set, we are able to tell apart learning from memorization. Application of our permutation approach to multi-layer perceptrons and convolutional neural networks trained on image data corroborated many findings from other groups. Most importantly, our illustrations also uncovered interesting dynamic patterns about how DNNs memorize over increasing numbers of training epochs, and support the surprising result that DNNs are still able to learn, rather than only memorize, when trained with pure Gaussian noise as input.