fairness-ai

There are 11 repositories under fairness-ai topic.

giskard
Giskard-AI / giskard
🐢 Open-Source Evaluation & Testing for ML models & LLMs
ai-red-team ai-safety ai-security ai-testing ethical-artificial-intelligence evaluation-framework fairness-ai llm llm-eval llm-evaluation llm-security llmops ml-safety ml-testing ml-validation mlops rag-evaluation red-team-tools responsible-ai trustworthy-ai
Language:Python 3919
Trusted-AI / AIF360
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
ai artificial-intelligence bias bias-correction bias-detection bias-finder bias-reduction codait deep-learning discrimination fairness fairness-ai fairness-awareness-model fairness-testing ibm-research ibm-research-ai machine-learning python r trusted-ai
Language:Python 2409
fairlearn / fairlearn
A Python package to assess and improve fairness of machine learning models.
ai ai-systems artificial-intelligence fairness fairness-ai fairness-assessment fairness-ml group-fairness harms machine-learning responsible-ai unfairness-mitigation
Language:Python 1908
microsoft / responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
data-analysis data-science data-visualization error-analysis explainability explainable-ai explainable-ml fairness fairness-ai fairness-ml interpretability jupyter machine-learning machinelearning ml responsible-ai ui visualization widget widgets
Language:TypeScript 1327
dccuchile / wefe
WEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
bias-detection bias-reduction fairness-ai fairness-ml library nlp nlp-library python3 word-embedding-evaluation word-embedding-fairness word-embeddings
Language:Python 173
linkedin / LiFT
The LinkedIn Fairness Toolkit (LiFT) is a Scala/Spark library that enables the measurement of fairness in large scale machine learning workflows.
fairness fairness-ml fairness-ai linkedin spark machine-learning scala
Language:Scala 168
microsoft / SafeNLP
Safety Score for Pre-Trained Language Models
ai-safety fairness-ai nlp
Language:Python 93
ResponsiblyAI / responsibly
Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰
artificial-intelligence audit bias bias-correction bias-finder bias-reduction data-science ethics fairness fairness-ai fairness-awareness-model fairness-ml fairness-testing machine-bias machine-learning natural-language-processing python
Language:Python 92
firmai / ml-fairness-framework
FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)
fairness-ml fairness-ai fairness-indicators explainable-ai xai explainable-ml interpretable-machine-learning contrastive prototypical aif360 alibi aix360 counterfactual
Language:Jupyter Notebook 70
aws / amazon-sagemaker-clarify
Fairness Aware Machine Learning. Bias detection and mitigation for datasets and models.
machine-learning fairness fairness-ml fairness-ai
Language:Python 66
brandeis-machine-learning / awesome-ml-fairness
Papers and online resources related to machine learning fairness
machine-learning awesome papers fairness trustworthy-machine-learning human-ai-interaction fairness-ml fairness-ai research-paper
65
inFairness
IBM / inFairness
PyTorch package to train and audit ML models for Individual Fairness
individual-fairness machine-learning pytorch fairness-ai trustworthy-machine-learning fairness responsible-ai
Language:Python 63
pliang279 / sent_debias
[ACL 2020] Towards Debiasing Sentence Representations
fairness-ai machine-learning natural-language-processing representation-learning
Language:Python 59
pliang279 / LM_bias
[ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models
natural-language-processing machine-learning fairness-ai language-model
Language:Python 58
influenciae
deel-ai / influenciae
👋 Influenciae is a Tensorflow Toolbox for Influence Functions
influence-functions explainable-ai explainability outlier-detection misclassification fairness-ai
Language:Python 55
CODAIT / presentations
Talks & Workshops by the CODAIT team
presentations deep-learning open-source data-science machine-learning fairness-ai fairness-ml
Language:Jupyter Notebook 52
AthenaCore / AwesomeResponsibleAI
A curated list of awesome academic research, books, code of ethics, data sets, institutes, newsletters, principles, podcasts, reports, tools, regulations and standards related to Responsible AI, Trustworthy AI, and Human-Centered AI.
responsible-ai xai fairness-ai awesome-list ethical-ai explainable-ai interpretable-ai trustworthy-ai
50
credo-ai / credoai_lens
Credo AI Lens is a comprehensive assessment framework for AI systems. Lens standardizes model and data assessment, and acts as a central gateway to assessments created in the open source community.
responsible-ai machine-learning ml ethical-artificial-intelligence assessment data-science artificial-intelligence ai jupyter python fairness-ml fairness-ai visualization reporting
Language:Python 46
fidelity / jurity
[ICMLA 2021] Jurity: Fairness & Evaluation Library
evaluation fairness-ai machine-learning metrics recommenders
Language:Python 45
txsun1997 / Metric-Fairness
EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
bertscore deep-learning fairness-ai fairness-ml natural-language-processing pretrained-language-model text-generation metric-bias
Language:Jupyter Notebook 38
microsoft / responsible-ai-toolbox-genbit
A tool for gender bias identification in text. Part of Microsoft's Responsible AI toolbox.
data-science fairness-ai fairness-ml gender gender-bias jupyter machine-learning natural-language natural-language-processing fairnness
Language:Python 36
kozodoi / fairness
R package for computing and visualizing fair ML metrics
fairness machine-learning fairness-ml fairness-ai discrimination algorithmic-fairness disparate-impact algorithmic-discrimination r
Language:R 33
microsoft / responsible-ai-workshop
Responsible AI Workshop: a series of tutorials & walkthroughs to illustrate how put responsible AI into practice
responsible-ai principles fairness fairness-ai fairness-ml error-analysis explainability explainable-ai explainable-ml ml machine-learning jupyter-notebook widgets mlops-workshop
Language:Jupyter Notebook 31
mlr-org / mcboost
Multi-Calibration & Multi-Accuracy Boosting for R
machine-learning classification fairness fairness-ml fairness-ai responsible-ai bias-correction bias-detection post-processing ethics
Language:R 30
ClearExplanationsAI / CLEAR
Counterfactual Local Explanations of AI systems
explainable-ai counterfactual-local-explanations fidelity fairness-ai
Language:Python 28
dbountouridis / siren
SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments
diversity fairness-ai explainable-ai explainable-artificial-intelligence recommendation-system recommendation-engine simulations simulation-toolkit news
Language:Python 28
aida-ugent / fairret
A fairness library in PyTorch.
ai artificial-intelligence bias deep-learning fairness fairness-ai fairness-ml machine-learning python pytorch
Language:Python 26
ajsanjoaquin / Shapley_Valuation
PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuation of Data" by Amirata Ghorbani and James Zou [ICML 2019]
data-valuation deeplearning explainable-ai fairness fairness-ai fairness-ml game-theory interpretable-deep-learning interpretable-machine-learning machine-learning pytorch pytorch-implementation shapley-value training-data training-data-curation
Language:Python 23
cylynx / verifyml
Open-source toolkit to help companies implement responsible AI workflows.
responsible-ai fairness fairness-ai machine-learning machine-bias veritas model-card
Language:Python 23
monk1337 / Awesome-Robust-Machine-Learning
A curated list of Robust Machine Learning papers/articles and recent advancements.
awesome-list bias-detection concept-shift covariate-shift data-shift deep-learning distribution-shift fairness fairness-ai fairness-ml fairness-testing federated-learning healthcare healthcare-federated-learning label-shift machine-learning machine-learning-bias ood robust-learning robust-machine-learning
23
wearepal / EthicML
Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency
ethical-artificial-intelligence fairness toolkit pytorch machine-learning fairness-comparison data-science ethical-data-science computer-vision algorithmic-fairness fairness-ml fairness-ai responsible-ai machine-bias fairness-awareness-model fairness-assessment
Language:Python 23
jphall663 / hc_ml
Slides, videos and other potentially useful artifacts from various presentations on responsible machine learning.
fairness xai interpretability iml fatml accountability transparency machine-learning data-science data-mining machine-learning-interpretability interpretable-machine-learning interpretable-ml interpretable-ai explainable-ai explainable-ml fairness-ai fairness-ml
Language:TeX 22
oracle-samples / automlx
This repository contains demo notebooks (sample code) for the AutoMLx (automated machine learning and explainability) package from Oracle Labs.
python ai automl data-science explainability machine-learning oracle automlx automated-machine-learning fairness fairness-ai interpretability machine-learning-explainability mlx classification hyperparameter-optimization regression tuning timeseries-forecasting unsupervised-anomaly-detection
22
heyaudace / ml-bias-fairness
Data and Model-based approaches for Mitigating Bias in Machine Learning Applications
machine-learning bias fairness-ai fairness d-lab
Language:Jupyter Notebook 19
valeria-io / bias-in-credit-models
Examples of unfairness detection for a classification-based credit model
fairness fairness-ai fairness-testing ethical-data-science bias-detection bias-correction
Language:Jupyter Notebook 19
yuji-roh / fairbatch
FairBatch: Batch Selection for Model Fairness (ICLR 2021)
machine-learning pytorch deep-learning fairness fairness-ml fairness-ai trustworthy-ai responsible-ai tensorflow2
Language:Python 19