Toward A Causal Framework for Modeling Perception
This work addresses the challenge of accounting for differing expert interpretations in ML-enabled decision flows, with implications for fairness, but it is incremental as it introduces a first approach without broad validation.
The authors tackled the understudied problem of modeling perception in machine learning by proposing a causal framework using structural causal models, which formalizes individual experience as additional causal knowledge for expert decision-makers.
Perception occurs when individuals interpret the same information differently. It is a known cognitive phenomenon with implications for bias in human decision-making. Perception, however, remains understudied in machine learning (ML). This is problematic as modern decision flows, whether partially or fully automated by ML applications, always involve human experts. For instance, how might we account for cases in which two experts interpret differently the same deferred instance or explanation from a ML model? Addressing this and similar questions requires first a formulation of perception, particularly, in a manner that integrates with ML-enabled decision flows. In this work, we present a first approach to modeling perception causally. We define perception under causal reasoning using structural causal models (SCMs). Our approach formalizes individual experience as additional causal knowledge that comes with and is used by the expert decision-maker in the form of a SCM. We define two kinds of probabilistic causal perception: structural and parametrical. We showcase our framework through a series of examples of modern decision flows. We also emphasize the importance of addressing perception in fair ML, discussing relevant fairness implications and possible applications.