viralamo

Menu
  • Technology
  • Science
  • Money
  • Culturs
  • Trending
  • Video

Subscribe To Our Website To Receive The Last Stories

Join Us Now For Free
Home
Technology
LinkedIn open-sources toolkit to measure AI model fairness
Technology

LinkedIn open-sources toolkit to measure AI model fairness

26/08/2020

LinkedIn today released the LinkedIn Fairness Toolkit (LiFT), an open source software library designed to enable the measurement of fairness in AI and machine learning workflows. The company says LiFT can be deployed during training and scoring to measure biases in training data sets, and to evaluate notions of fairness for models while detecting differences in their performance across subgroups.

There are countless definitions of fairness in AI, each capturing different aspects of fairness to users. Monitoring models along these definitions is a step toward ensuring fair experiences, but although several toolkits tackle fairness-related challenges, most don’t address large-scale problems and are tied to specific cloud environments.

By contrast, LiFT can be leveraged for ad hoc fairness analysis or as a part of any large-scale A/B testing system. It’s usable for exploratory analysis and in production, with bias measurement components that can be integrated into stages of a machine learning training and serving system. Moreover, it introduces a novel metric-agnostic testing framework that can detect statistically significant differences in performance as measured across different subgroups.

LinkedIn LiFT

LiFT is reusable, LinkedIn says, with wrappers and a configuration language intended for deployment. At the highest level, the library provides a basic driver program powered by a simple configuration, enabling fairness measurement for data sets and models without the need to write code and related unit tests. But LiFT also provides access to higher-level and lower-level APIs that can be used to compute fairness metrics at all levels of granularity, with the ability to extend key classes to enable custom computation.

To achieve scalability, LiFT taps Apache Spark, loading data sets into an organized database with only the primary key, labels, predictions, and protected attributes. Data distributions are computed and stored on a single system in-memory to speed up the computation of subsequent fairness metric computations; users can operate on these distributions or deal with cached data sets for more involved metrics.

To date, LinkedIn says it has applied LiFT internally to measure the fairness metrics of training data sets for models prior to their training. In the future, the company plans to increase the number of pipelines where it’s measuring and mitigating bias on an ongoing basis through deeper integration of LiFT.

“News headlines and academic research have emphasized that widespread societal injustice based on human biases can be reflected both in the data that is used to train AI models and the models themselves. Research has also shown that models affected by these societal biases can ultimately serve to reinforce those biases and perpetuate discrimination against certain groups,” LinkedIn senior software engineer Sriram Vasudevan, machine learning engineer Cyrus DiCiccio, and staff applied researcher Kinjal Basu wrote in a blog post. “We are working toward creating a more equitable platform by avoiding harmful biases in our models and ensuring that people with equal talent have equal access to job opportunities.”

Source link

Share
Tweet
Pinterest
Linkedin
Stumble
Google+
Email
Prev Article
Next Article

Related Articles

ProBeat: Black journalists in tech you should follow
I am a white, heterosexual, male. I’m as privileged as …

ProBeat: Black journalists in tech you should follow

9 Amazon workers describe the daily risks they face in the pandemic
Enlarge / An Amazon Prime-branded delivery van and driver. As …

9 Amazon workers describe the daily risks they face in the pandemic

Leave a Reply Cancel reply

Find us on Facebook

Related Posts

  • Unpatched US government website gets pwned by pro-Iran script kiddie
    Unpatched US government website gets pwned by …
    06/01/2020
  • 2020 will be a big year for online childcare — here are 7 startups to watch
    Decrypted: Post-coronavirus, Auth0’s close call, North Korea …
    19/04/2020
  • Amazon’s third-party merchants are now barred from using FedEx Ground for Prime shipments – TechCrunch
    Amazon’s third-party merchants are now barred from …
    17/12/2019
  • Researchers’ AI aligns sheet music with MIDI audio
    Researchers’ AI aligns sheet music with MIDI …
    23/07/2020
  • Yann LeCun: AR glasses will be the killer app of energy-efficient machine learning
    Yann LeCun: AR glasses will be the …
    17/12/2019

Popular Posts

  • Home alarm tech backdoored security cameras to spy on customers having sex
    Home alarm tech backdoored security cameras to …
    22/01/2021 0
  • Top 10 Stunning Churches and Cathedrals – …
    24/12/2020 0
  • SolarWinds hackers are ‘impacting’ U.S. federal, state, and local governments
    SolarWinds hackers are ‘impacting’ U.S. federal, state, …
    24/12/2020 0
  • Goldman Sachs leads acquisition of bot mitigation company White Ops
    Goldman Sachs leads acquisition of bot mitigation …
    24/12/2020 0
  • Bloomberg acquires Second Measure to unlock transaction data insights
    Bloomberg acquires Second Measure to unlock transaction …
    24/12/2020 0

viralamo

Pages

  • Contact Us
  • Privacy Policy
Copyright © 2021 viralamo
Theme by MyThemeShop.com

Ad Blocker Detected

Our website is made possible by displaying online advertisements to our visitors. Please consider supporting us by disabling your ad blocker.

Refresh
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.I AgreePrivacy policy