Open Access10.1145/3465416.3483305
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Harini Suresh,John V. Guttag +1 more
- 05 Oct 2021
TL;DR: In this paper, the authors identify seven potential sources of downstream harm in machine learning, spanning data collection, development, and deployment, and propose a framework to facilitate more productive and precise communication around these issues.
read more
Abstract: As machine learning (ML) increasingly affects people and society, awareness of its potential unwanted consequences has also grown. To anticipate, prevent, and mitigate undesirable downstream consequences, it is critical that we understand when and how harm might be introduced throughout the ML life cycle. In this paper, we provide a framework that identifies seven distinct potential sources of downstream harm in machine learning, spanning data collection, development, and deployment. In doing so, we aim to facilitate more productive and precise communication around these issues, as well as more direct, application-grounded ways to mitigate them.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Gender Stereotyping Impact in Facial Expression Recognition
TL;DR: In this article , the authors used a popular FER dataset, FER+, to generate derivative datasets with different amounts of stereotypical bias by altering the gender proportions of certain labels. And they then measured the discrepancy between the performance of the models trained on these datasets for the apparent gender groups.
Current challenges in adopting machine learning to critical care and emergency medicine
Cyra Y. Kang,J.-H. Yoon +1 more
TL;DR: In this article , a series of current challenges of adopting ML models to clinical research is discussed, including data, feature generation, model design, performance assessment, and limited implementation of the research.
7
Social media and volunteer rescue requests prediction with random forest and algorithm bias detection: a case of Hurricane Harvey
TL;DR: In this article , the authors evaluate a Random Forest regression model trained to predict Twitter rescue request rates from social-environmental data using three fairness criteria (independence, separation, and sufficiency).
7
Rethinking Transparency as a Communicative Constellation
Florian Eyert,Paola Lopez +1 more
- 12 Jun 2023
TL;DR: In this paper , the authors make the case for an expanded understanding of transparency and propose to view transparency as a communicative constellation that is a precondition for meaningful democratic deliberation.
7
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition
TL;DR: In this article , a taxonomy for the classification of these metrics, providing a practical guide for the selection of appropriate metrics, was developed, and a case study of 20 datasets used in Facial Emotion Recognition (FER), analyzing the biases present in them.
References
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
SMOTE: synthetic minority over-sampling technique
TL;DR: In this article, a method of over-sampling the minority class involves creating synthetic minority class examples, which is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
SMOTE: Synthetic Minority Over-sampling Technique
TL;DR: In this article, a method of over-sampling the minority class involves creating synthetic minority class examples, which is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
Joy Buolamwini,Timnit Gebru +1 more
- 21 Jan 2018
TL;DR: It is shown that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men, in commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition.
Big Data's Disparate Impact
Solon Barocas,Andrew D. Selbst +1 more
TL;DR: In the absence of a demonstrable intent to discriminate, the best doctrinal hope for data mining's victims would seem to lie in disparate impact doctrine as discussed by the authors, which holds that a practice can be justified as a business necessity when its outcomes are predictive of future employment outcomes, and data mining is specifically designed to find such statistical correlations.
2.8K