Esprii Chapman – Notes on Fair-Minded Machines – 11/25/20 (Article 6 of 10)

“This is a very common issue with machine learning,” says computer scientist Moritz Hardt of the University of California, Berkeley. Even if a programmer designs an algorithm without prejudicial intent, “you’re very likely to end up in a situation that will have fairness issues,” Hardt says. “This is more the default than the exception.” (27)

  • Key words “More the default than the exception”

Several socially conscious computer and data scientists have recently started wrestling with the problem of machine bias. Some have come up with ways to add fairness requirements into machine-learning systems. Others have found ways to illuminate the sources of algorithms’ biased behavior. But the very nature of machine-learning algorithms as self-taught systems means there’s no easy fix to make them play fair. (27)

At first glance, the answer seems obvious: Remove any sensitive features, such as race or sex, from the training data. The problem is, there are many ostensibly nonsensitive aspects of a dataset that could play proxy for some sensitive feature. Zip code may be strongly related to race, college major to sex, health to socioeconomic status. (27)

  • There is no simple fix; though in talking to David Leubke at NVIDIA, a proposed algorithm that’s trained to recognize bias could have some positive effects? No one has done that for sure yet though.
    • “ In 2015, one group proposed testing data for potential bias by building a computer program that uses people’s nonsensitive features to predict their sensitive ones, like race or sex. If the program could do this with reasonable accuracy, the dataset’s sensitive and nonsensitive attributes were tightly connected, the researchers concluded. That tight connection was liable to train discriminatory machine-learning algorithms. “ (28)
      • This is a quick take on what I just said. In theory, building a racist algorithm just to be able to engineer the literal opposite algorithm might work.

Creators of machine-learning systems “used to be able to look at the source code of our programs and understand how they work, but that era is long gone,” says Simon DeDeo, a cognitive scientist at Carnegie Mellon University in Pittsburgh. In many cases, neither an algorithm’s authors nor its users care how it works, as long as it works, he adds. “It’s like, ‘I don’t care how you made the food; it tastes good.’ ” (27)

  • A deeper understanding of AI is needed to understand how this is working, a look through at its cognitive process perhaps.

Bilal Zafar of the Max Planck Institute for Software Systems in Kaiserslautern, Germany, and colleagues proposed that developers add instructions to machine-learning algorithms to ensure they dole out errors to different demographics at equal rates—the same type of requirement Hardt’s team set. This technique, presented in Perth, Australia, at the International World Wide Web Conference, requires that the training data have information about whether the examples in the dataset were actually good or bad decisions. For something like stop-and-frisk data, where it’s known whether a frisked person actually had a weapon, the approach works. Developers could add code to their program that tells it to account for past wrongful stops. 

Zafar and colleagues tested their technique by designing a crime-predicting machine-learning algorithm with specific nondiscrimination instructions. The researchers trained their algorithm on a dataset containing criminal profiles and whether those people actually reoffended. By forcing their algorithm to be a more equal opportunity error-maker, the researchers were able to reduce the difference between how often blacks and whites who didn’t recommit were wrongly classified as being likely to do so: The fraction of people that COMPAS mislabeled as future criminals was about 45 percent for blacks and 23 percent for whites. In the researchers’ new algorithm, misclassification of blacks dropped to 26 percent and held at 23 percent for whites. (28-29)

“Every research area has to go through this exploration phase,” he says, “where we may have only very preliminary and half-baked answers, but the questions are interesting.” (29)

  • It’s a matter of not implementing these systems into courts until we can fully research this subject to the point where we can definitively prove that there is little no bias.

Temming, Maria. “Fair-Minded Machines” Science News, Vol. 192, No. 4, September 2017, pp. 26-29.

1 Comment

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s