Mike Ananny | Searcharxiv

arXiv2025

A Critical Field Guide for Working with Machine Learning Datasets

Machine learning datasets are powerful but unwieldy. Despite the fact that large datasets commonly contain problematic material--whether from a technical, legal, or ethical perspective--datasets are valuable resources when handled carefully and critically. A Critical Field Guide for Working with Machine Learning Datasets suggests practical guidance for conscientious dataset stewardship. It offers questions, suggestions, strategies, and resources for working with existing machine learning datasets at every phase of their lifecycle. It combines critical AI theories and applied data science concepts, explained in accessible language. Equipped with this understanding, students, journalists, artists, researchers, and developers can be more capable of avoiding the problems unique to datasets. They can also construct more reliable, robust solutions, or even explore new ways of thinking with machine learning datasets that are more critical and conscientious.

cs.CY↗

arXiv2021

A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication

Datasets are central to training machine learning (ML) models. The ML community has recently made significant improvements to data stewardship and documentation practices across the model development life cycle. However, the act of deprecating, or deleting, datasets has been largely overlooked, and there are currently no standardized approaches for structuring this stage of the dataset life cycle. In this paper, we study the practice of dataset deprecation in ML, identify several cases of datasets that continued to circulate despite having been deprecated, and describe the different technical, legal, ethical, and organizational issues raised by such continuations. We then propose a Dataset Deprecation Framework that includes considerations of risk, mitigation of impact, appeal mechanisms, timeline, post-deprecation protocols, and publication checks that can be adapted and implemented by the ML community. Finally, we propose creating a centralized, sustainable repository system for archiving datasets, tracking dataset modifications or deprecations, and facilitating practices of care and stewardship that can be integrated into research and publication processes.

cs.CY↗