Analysing fairness of graph anomaly detection methods
-
Updated
Aug 18, 2024 - Python
Analysing fairness of graph anomaly detection methods
A Python package to assess and improve fairness of machine learning models.
Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency
Code for the definition and testing of three new fairness-aware algorithms: Fair Decision Tree, Fair Genetic Pruning, and Fair LightGBM (FDT, FGP, FLGBM), completed for my Master's thesis.
USENIX Security'23: Inductive Graph Unlearning
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.
Service to examine data processing pipelines (e.g., machine learning or deep learning pipelines) for uncertainty consistency (calibration), fairness, and other safety-relevant aspects.
A library for generating and evaluating synthetic tabular data for privacy, fairness and data augmentation.
Fairness-Aware Team Formation
A fairness library in PyTorch.
Robust Bayesian Recourse: a robust model-agnostic algorithmic recourse method (UAI'22)
Mitigating bias for our model used to identify Glioblastoma Multiforme (tumors) using Xgboost.
SSA is a post-hoc explanation method by stereotypes and counter-stereotypes to assess social bias in hate speech classifiers
ML Testing for Everyone. Find issues before they become problems.
A Python package for mitigating bias in tabular data.
A Brazilian Portuguese Text Offensiveness Analysis System
Responsible AI Workshop: a series of tutorials & walkthroughs to illustrate how put responsible AI into practice
Compare various methods to debias a ML task (project for the AI course)
Designed a novel online platform to eliminate AI bias, integrating software engineering, cybersecurity, and machine learning techniques with ethical principles.
Add a description, image, and links to the fairness-ml topic page so that developers can more easily learn about it.
To associate your repository with the fairness-ml topic, visit your repo's landing page and select "manage topics."