This session is further rooting me in my beliefs that feature importance is a social construct lol #FAT2020
There’s some interesting social science research on the idea / lots of models of how it “works”, often to do with social context & interaction, so .... yes? It’s at the very least a concept that doesn’t lend itself well to precise technical definitions!
-
-
Fascinating, any pointers on where to start in the social sci literature? Is it safe to say that the social context of a decision (or intervention as a result of a model output) in the real world would be a precursor to the need for a justification or explanation?
-
This is my one and only lead
https://arxiv.org/abs/1706.07269 I’m no social scientist!!!
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
PhD student
she/her