Timezone: »

 
Poster
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
Amir-Hossein Karimi · Julius von Kügelgen · Bernhard Schölkopf · Isabel Valera

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #793
in Poster Session 4 »

Recent work has discussed the limitations of counterfactual explanations to recommend actions for algorithmic recourse, and argued for the need of taking causal relationships between features into consideration. Unfortunately, in practice, the true underlying structural causal model is generally unknown. In this work, we first show that it is impossible to guarantee recourse without access to the true structural equations. To address this limitation, we propose two probabilistic approaches to select optimal actions that achieve recourse with high probability given limited causal knowledge (e.g., only the causal graph). The first captures uncertainty over structural equations under additive Gaussian noise, and uses Bayesian model averaging to estimate the counterfactual distribution. The second removes any assumptions on the structural equations by instead computing the average effect of recourse actions on individuals similar to the person who seeks recourse, leading to a novel subpopulation-based interventional notion of recourse. We then derive a gradient-based procedure for selecting optimal recourse actions, and empirically show that the proposed approaches lead to more reliable recommendations under imperfect causal knowledge than non-probabilistic baselines.

Author Information

Amir-Hossein Karimi (Max Planck Institute for Intelligent Systems)
Julius von Kügelgen (Max Planck Institute for Intelligent Systems Tübingen & University of Cambridge)

I am a PhD student with Bernhard Schölkopf at the Max Planck Institute for Intelligent Systems in Tübingen. As part of the Cambridge-Tübingen programme I am also co-supervised by Adrian Weller at the University of Cambridge, where I spent the first year of my PhD. My research interests lie at the intersection of causal inference and machine learning. Previously, I studied Mathematics (BSc+MSci) at Imperial College London and Artificial Intelligence (MSc) at UPC Barcelona in Spain and at TU Delft in the Netherlands. I am originally from the beautiful Hamburg in northern Germany.

Bernhard Schölkopf (MPI for Intelligent Systems, Tübingen)

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.

Isabel Valera (Saarland University & MPI for Intelligent Systems)

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

More from the Same Authors