Mateo Rojas-Carulla
now a Chief Scientist & Co-Founder at Lakera
Publications
Avoiding Discrimination through Causal Reasoning
Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf, December 2017. (In Advances in Neural Information Processing Systems 30). Long Beach, California.
Abstract▼ URL
Recent work on fairness in machine learning has focused on various statistical discrimination criteria and how they trade off. Most of these criteria are observational: They depend only on the joint distribution of predictor, protected attribute, features, and outcome. While convenient to work with, observational criteria have severe inherent limitations that prevent them from resolving matters of fairness conclusively. Going beyond observational criteria, we frame the problem of discrimination based on protected attributes in the language of causal reasoning. This viewpoint shifts attention from “What is the right fairness criterion?” to “What do we want to assume about our model of the causal data generating process?” Through the lens of causality, we make several contributions. First, we crisply articulate why and when observational criteria fail, thus formalizing what was before a matter of opinion. Second, our approach exposes previously ignored subtleties and why they are fundamental to the problem. Finally, we put forward natural causal non-discrimination criteria and develop algorithms that satisfy them.
Learning Independent Causal Mechanisms
Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, Bernhard Schölkopf, July 2018. (In 35th International Conference on Machine Learning). Stockholm Sweden.
Abstract▼ URL
Statistical learning relies upon data sampled from a distribution, and we usually do not care what actually generated it in the first place. From the point of view of causal modeling, the structure of each distribution is induced by physical mechanisms that give rise to dependences between observables. Mechanisms, however, can be meaningful autonomous modules of generative models that make sense beyond a particular entailed data distribution, lending themselves to transfer between problems. We develop an algorithm to recover a set of independent (inverse) mechanisms from a set of transformed data points. The approach is unsupervised and based on a set of experts that compete for data generated by the mechanisms, driving specialization. We analyze the proposed method in a series of experiments on image data. Each expert learns to map a subset of the transformed data back to a reference distribution. The learned mechanisms generalize to novel domains. We discuss implications for transfer learning and links to recent trends in generative modeling.
A causal perspective on domain adaptation
Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, Jonas Peters, 2015. (arXiv preprint arXiv:1507.05333)).
Abstract▼ URL
From training data from several related domains (or tasks), methods of domain adaptation try to combine knowledge to improve performance. This paper discusses an approach to domain adaptation which is inspired by a causal interpretation of the multi-task problem. We assume that a covariate shift assumption holds true for a subset of predictor variables: the conditional of the target variable given this subset of predictors is invariant with respect to shifts in those predictors (covariates). We propose to learn the corresponding conditional expectation in the training domains and use it for estimation in the target domain. We further introduce a method which allows for automatic inference of the above subset in regression and classification. We study the performance of this approach in an adversarial setting, in the case where no additional examples are available in the test domain. If a labeled sample is available, we provide a method for using both the transferred invariant conditional and task specific information. We present results on synthetic data sets and a sentiment analysis problem.