Congratulations to Erwan Le Merrer (WIDE) and Gilles Trédan (LAAS), whose paper “Remote explainability faces the bouncer problem” has recently been published by Nature!
The paper considers the concept of explainability of machine learning decisions. The concept is simple: like humans, algorithms should explain the rationale behind their decisions so that their fairness can be assessed. Although this approach is promising in a local context (for example, the model creator explains it during debugging at the time of training), Erwan and Gilles show that in a remote setting, the very notion of remote explainability is highly problematic, and can be easily undermined.
Le Merrer, E., Trédan, G. Remote explainability faces the bouncer problem. Nat Mach Intell (2020).
