Bias mitigation for machine learning classifiers: A comprehensive survey

M Hort, Z Chen, JM Zhang, M Harman… - ACM Journal on …, 2024 - dl.acm.org
This article provides a comprehensive survey of bias mitigation methods for achieving
fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning …

A survey on bias and fairness in machine learning

N Mehrabi, F Morstatter, N Saxena, K Lerman… - ACM computing …, 2021 - dl.acm.org
With the widespread use of artificial intelligence (AI) systems and applications in our
everyday lives, accounting for fairness has gained significant importance in designing and …

Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset

C Meng, L Trinh, N Xu, J Enouen, Y Liu - Scientific Reports, 2022 - nature.com
The recent release of large-scale healthcare datasets has greatly propelled the research of
data-driven deep learning models for healthcare applications. However, due to the nature of …

Unsupervised speech representation learning using wavenet autoencoders

J Chorowski, RJ Weiss, S Bengio… - … /ACM transactions on …, 2019 - ieeexplore.ieee.org
We consider the task of unsupervised extraction of meaningful latent representations of
speech by applying autoencoding neural networks to speech waveforms. The goal is to …

Information leakage in embedding models

C Song, A Raghunathan - Proceedings of the 2020 ACM SIGSAC …, 2020 - dl.acm.org
Embeddings are functions that map raw input data to low-dimensional vector
representations, while preserving important semantic information about the inputs. Pre …

Learning robust representations by projecting superficial statistics out

H Wang, Z He, ZC Lipton, EP Xing - arXiv preprint arXiv:1903.06256, 2019 - arxiv.org
Despite impressive performance as evaluated on iid holdout data, deep neural networks
depend heavily on superficial statistics of the training data and are liable to break under …

Diva: Domain invariant variational autoencoders

M Ilse, JM Tomczak, C Louizos… - Medical Imaging with …, 2020 - proceedings.mlr.press
We consider the problem of domain generalization, namely, how to learn representations
given data from a set of domains that generalize to data from a previously unseen domain …

Incorporating symmetry into deep dynamics models for improved generalization

R Wang, R Walters, R Yu - arXiv preprint arXiv:2002.03061, 2020 - arxiv.org
Recent work has shown deep learning can accelerate the prediction of physical dynamics
relative to numerical solvers. However, limited physical accuracy and an inability to …

Modality-invariant asymmetric networks for cross-modal hashing

Z Zhang, H Luo, L Zhu, G Lu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Cross-modal hashing has garnered considerable attention and gained great success in
many cross-media similarity search applications due to its prominent computational …

Mitigating confounding bias in recommendation via information bottleneck

D Liu, P Cheng, H Zhu, Z Dong, X He, W Pan… - Proceedings of the 15th …, 2021 - dl.acm.org
How to effectively mitigate the bias of feedback in recommender systems is an important
research topic. In this paper, we first describe the generation process of the biased and …