toolings
LIBRARY
The LinkedIn Fairness Toolkit (LiFT) is a Scala/Spark library that enables the measurement of fairness in large scale machine learning workflows. The library can be deployed in training and scoring workflows to measure biases in training data, evaluate fairness metrics for ML models, and detect statistically significant differences in their performance across different subgroups. It can also be used for ad-hoc fairness analysis.
The LinkedIn Fairness Toolkit (LiFT)
LinkedinLIBRARY
The LinkedIn Fairness Toolkit (LiFT) is a Scala/Spark library that enables the measurement of fairness in large scale machine learning workflows. The library can be deployed in training and scoring workflows to measure biases in training data, evaluate fairness metrics for ML models, and detect statistically significant differences in their performance across different subgroups. It can also be used for ad-hoc fairness analysis.
toolings
TOOLKIT
Fairness Indicators is designed to support teams in evaluating, improving, and comparing models for fairness concerns in partnership with the broader Tensorflow toolkit. The tool is currently actively used internally by many of our products.
Tensorflow’s Fairness Evaluation and Visualization Toolkit
GoogleTOOLKIT
Fairness Indicators is designed to support teams in evaluating, improving, and comparing models for fairness concerns in partnership with the broader Tensorflow toolkit. The tool is currently actively used internally by many of our products.
toolings
DATABASE
WILDS builds on top of recent data collection efforts by domain experts in applications such as tumour identification, wildlife monitoring and poverty mapping, presenting a unified collection of datasets with evaluation metrics and train/test splits that the researchers believe are representative of real-world distribution shifts.
WILDS
MicrosoftDATABASE
WILDS builds on top of recent data collection efforts by domain experts in applications such as tumour identification, wildlife monitoring and poverty mapping, presenting a unified collection of datasets with evaluation metrics and train/test splits that the researchers believe are representative of real-world distribution shifts.
toolings
This paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in discriminatory behavior...
Themis Fairness Testing: Testing Software for Discrimination
RESEARCHThis paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in discriminatory behavior...
toolings
themis-ml is a Python library built on top of pandas and sklearnthat implements fairness-aware machine learning algorithms...
Themis-ml: A Fairness-aware Machine Learning Interface for End-to-end Discrimination Discovery and Mitigation
LIBRARYthemis-ml is a Python library built on top of pandas and sklearnthat implements fairness-aware machine learning algorithms...
toolings
MODEL
PowerTransformer is a tool that aims to rewrite text to correct implicit and potentially undesirable bias in character portrayals.
PowerTransformer
Allen Institute for AI (AI2), University of WashingtonMODEL
PowerTransformer is a tool that aims to rewrite text to correct implicit and potentially undesirable bias in character portrayals.
toolings
FRAMEWORK
Google today released MinDiff, a new framework for mitigating (but not eliminating) unfair biases when training AI and machine learning models. The company says MinDiff is the culmination of years of work and has already been incorporated into various Google products, including models that moderate content quality.
MinDiff
GoogleFRAMEWORK
Google today released MinDiff, a new framework for mitigating (but not eliminating) unfair biases when training AI and machine learning models. The company says MinDiff is the culmination of years of work and has already been incorporated into various Google products, including models that moderate content quality.
toolings
The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases...
Remove problematic gender bias from word embeddings
RESEARCHThe blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases...
toolings
TOOLKIT
AI Fairness 360, an LF AI incubation project, is an extensible open source toolkit that can help users examine, report, and mitigate discrimination and bias in machine learning models throughout the AI application lifecycle. It is designed to translate algorithmic research from the lab into the actual practice of domains as wide-ranging as finance, human capital management, healthcare, and education. The toolkit is available in both Python and R.
AI Fairness 360
Linux FoundationTOOLKIT
AI Fairness 360, an LF AI incubation project, is an extensible open source toolkit that can help users examine, report, and mitigate discrimination and bias in machine learning models throughout the AI application lifecycle. It is designed to translate algorithmic research from the lab into the actual practice of domains as wide-ranging as finance, human capital management, healthcare, and education. The toolkit is available in both Python and R.