Timezone: »

 
Poster
On the Adversarial Robustness of Causal Algorithmic Recourse
Ricardo Dominguez-Olmedo · Amir-Hossein Karimi · Bernhard Schölkopf

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #903
in Poster Session 1 »

Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems. Recourse recommendations should ideally be robust to reasonably small uncertainty in the features of the individual seeking recourse. In this work, we formulate the adversarially robust recourse problem and show that recourse methods that offer minimally costly recourse fail to be robust. We then present methods for generating adversarially robust recourse for linear and for differentiable classifiers. Finally, we show that regularizing the decision-making classifier to behave locally linearly and to rely more strongly on actionable features facilitates the existence of adversarially robust recourse.

Keywords: MISC: Causality · SA: Trustworthy Machine Learning · SA: Accountability, Transparency and Interpretability
[ Slides]  [ Poster]  [ Paper PDF] 

Author Information

Ricardo Dominguez-Olmedo (University of Tübingen)
Amir-Hossein Karimi (MPI for Intelligent Systems, Tübingen, Germany)
Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Bernhard Scholkopf received degrees in mathematics (London) and physics (Tubingen), and a doctorate in computer science from the Technical University Berlin. He has researched at AT&T Bell Labs, at GMD FIRST, Berlin, at the Australian National University, Canberra, and at Microsoft Research Cambridge (UK). In 2001, he was appointed scientific member of the Max Planck Society and director at the MPI for Biological Cybernetics; in 2010 he founded the Max Planck Institute for Intelligent Systems. For further information, see www.kyb.tuebingen.mpg.de/~bs.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors