Fairer Software Made Easier (using "Keys")
This work addresses the challenge of making software analytics more interpretable and fair, particularly for ethical AI applications, though it appears incremental as it builds on known concepts like the keys effect.
The paper tackles the problem of simplifying explanations for software analytics by exploiting the 'keys effect' where a few key features control system behavior, proposing that this approach can dramatically simplify complex explanations needed for ethical AI systems.
Can we simplify explanations for software analytics? Maybe. Recent results show that systems often exhibit a "keys effect"; i.e. a few key features control the rest. Just to say the obvious, for systems controlled by a few keys, explanation and control is just a matter of running a handful of "what-if" queries across the keys. By exploiting the keys effect, it should be possible to dramatically simplify even complex explanations, such as those required for ethical AI systems.