adversarial-9

Fairness

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in fairness-28

Trend

Dataset

Best Model

Actions

DiveFace

UTKFace

MORPH

Libraries

i

Use these libraries to find fairness-28 models and implementations

faceonlive/ai-research

4 papers 144

Datasets

RFW

Subtasks

Exposure Fairness

Most implemented papers

FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking

Xinggang Wang, Wenyu Liu, Yifu Zhang, Chunyu Wang, Wenjun Zeng•Fri Apr 03 2020

This work presents a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet, which outperforms the state-of-the-art methods by a large margin on several public datasets.

1568

Content

GVGAI

0

AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias

S. Mehta, Kush R. Varshney, Stephanie Houde, John T. Richards, Samuel C. Hoffman, P. Sattigeri, Yunfeng Zhang, R. Bellamy, K. Dey, M. Hind, Kalapriya Kannan, P. Lohia, Jacquelyn Martino, A. Mojsilovic, Seema Nagar, K. Ramamurthy, Diptikalyan Saha, Moninder Singh•Tue Oct 02 2018

A new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms.

907 0

Paper Graph

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

Mengnan Du, Fan Yang, Haofan Wang, Zifan Wang, Zijian Zhang, Sirui Ding, Piotr (Peter) Mardziel, Xia Hu•Wed Oct 02 2019

This paper develops a novel post-hoc visual explanation method called Score-CAM based on class activation mapping that outperforms previous methods on both recognition and localization tasks, it also passes the sanity check.

1316 0

Paper Graph

A critic evaluation of methods for COVID-19 automatic detection from X-ray images

L. Nanni, Gianluca Maguolo•Sun Apr 26 2020

It is deduced that several testing protocols for the recognition are not fair and that the neural networks are learning patterns in the dataset that are not correlated to the presence of COVID-19.

207 0

Paper Graph

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

Jianfeng Gao, Houdong Hu, Zicheng Liu, Jianwei Yang, Pengchuan Zhang, Haotian Liu, Liunian Harold Li, J. Aneja, Ping Jin, Yong Jae Lee•Mon Apr 18 2022

This work builds ELEVATER (Evaluation of Language-augmented Visual Task-level Transfer), the first benchmark and toolkit for evaluating (pre-trained) language-AUgmented visual models.

178 0

Paper Graph

Learning Adversarially Fair and Transferable Representations

R. Zemel, David Madras, Elliot Creager, T. Pitassi•Fri Feb 16 2018

This paper presents the first in-depth experimental demonstration of fair transfer learning and demonstrates empirically that the authors' learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.

746 0

Paper Graph

Agnostic Federated Learning

M. Mohri, A. Suresh, Gary Sivek•Thu Jan 31 2019

This work proposes a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions, and shows that this framework naturally yields a notion of fairness.

1063 0

Paper Graph

Learning to Pivot with Adversarial Networks

M. Kagan, Gilles Louppe, Kyle Cranmer•Wed Nov 02 2016

This work introduces and derive theoretical results for a training procedure based on adversarial networks for enforcing the pivotal property (or, equivalently, fairness with respect to continuous attributes) on a predictive model and includes a hyperparameter to control the trade-off between accuracy and robustness.

234 0

Paper Graph

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

Aaron Roth, Michael Kearns, Seth Neel, Zhiwei Steven Wu•Mon Nov 13 2017

It is proved that the computational problem of auditing subgroup fairness for both equality of false positive rates and statistical parity is equivalent to the problem of weak agnostic learning, which means it is computationally hard in the worst case, even for simple structured subclasses.

862 0

Paper Graph

An Empirical Study of Rich Subgroup Fairness for Machine Learning

Aaron Roth, Michael Kearns, Seth Neel, Zhiwei Steven Wu•Thu Aug 23 2018

In general, the Kearns et al. algorithm converges quickly, large gains in fairness can be obtained with mild costs to accuracy, and that optimizing accuracy subject only to marginal fairness leads to classifiers with substantial subgroup unfairness.

220 0

Paper Graph

Adding a benchmark result helps the community track progress.