Impacts of Differential Privacy on Fostering more Racially and Ethnically Diverse Elementary Schools

• URL: http://arxiv.org/abs/2305.07762v1
• Date: Fri, 12 May 2023 21:06:15 GMT
• Title: Impacts of Differential Privacy on Fostering more Racially and Ethnically Diverse Elementary Schools
• Authors: Keyu Zhu, Nabeel Gillani, Pascal Van Hentenryck
• Abstract summary: The U.S. Census Bureau has adopted differential privacy, the de facto standard of privacy protection for the 2020 Census release. This change has the potential to impact policy decisions like political redistricting and other high-stakes practices. One under-explored yet important application of such data is the redrawing of school attendance boundaries to foster less demographically segregated schools.
• Score: 18.35063779220618
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the face of increasingly severe privacy threats in the era of data and AI, the US Census Bureau has recently adopted differential privacy, the de facto standard of privacy protection for the 2020 Census release. Enforcing differential privacy involves adding carefully calibrated random noise to sensitive demographic information prior to its release. This change has the potential to impact policy decisions like political redistricting and other high-stakes practices, partly because tremendous federal funds and resources are allocated according to datasets (like Census data) released by the US government. One under-explored yet important application of such data is the redrawing of school attendance boundaries to foster less demographically segregated schools. In this study, we ask: how differential privacy might impact diversity-promoting boundaries in terms of resulting levels of segregation, student travel times, and school switching requirements? Simulating alternative boundaries using differentially-private student counts across 67 Georgia districts, we find that increasing data privacy requirements decreases the extent to which alternative boundaries might reduce segregation and foster more diverse and integrated schools, largely by reducing the number of students who would switch schools under boundary changes. Impacts on travel times are minimal. These findings point to a privacy-diversity tradeoff local educational policymakers may face in forthcoming years, particularly as computational methods are increasingly poised to facilitate attendance boundary redrawings in the pursuit of less segregated schools.

Related papers

• Merging public elementary schools to reduce racial/ethnic segregation [0.6437284704257459]
  "School mergers" involve merging the school attendance boundaries, or catchment areas, of schools. We find that pairing or tripling schools in this way could reduce racial/ethnic segregation by a median relative 20%. We make our results available through a public dashboard for policymakers and community members to explore further.
  arXiv  Detail & Related papers  (2025-02-14T14:36:28Z)
• Masked Differential Privacy [64.32494202656801]
  We propose an effective approach called masked differential privacy (DP), which allows for controlling sensitive regions where differential privacy is applied. Our method operates selectively on data and allows for defining non-sensitive-temporal regions without DP application or combining differential privacy with other privacy techniques within data samples.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• The 2020 United States Decennial Census Is More Private Than You (Might) Think [25.32778927275117]
  We show that the 2020 U.S. Census provides significantly stronger privacy protections than its nominal guarantees suggest. We show that noise variances could be reduced by $15.08%$ to $24.82%$ while maintaining nearly the same level of privacy protection for each geographical level.
  arXiv  Detail & Related papers  (2024-10-11T23:06:15Z)
• Understanding and Mitigating the Impacts of Differentially Private Census Data on State Level Redistricting [4.589972411795548]
  Data users were shaken by the adoption of differential privacy in the 2020 DAS. We consider two redistricting settings in which a data user might be concerned about the impacts of privacy preserving noise. We observe that an analyst may come to incorrect conclusions if they do not account for noise.
  arXiv  Detail & Related papers  (2024-09-10T18:11:54Z)
• Contextual Stochastic Optimization for School Desegregation Policymaking [13.670408636443831]
  This paper develops a joint redistricting and choice modeling framework, called redistricting with choices (RWC) The main methodological contribution of the RWC is a contextual optimization model that minimizes district-wide dissimilarity. The results also reveal that predicting school choice is a challenging machine learning problem.
  arXiv  Detail & Related papers  (2024-08-22T17:40:06Z)
• The Impact of De-Identification on Single-Year-of-Age Counts in the U.S. Census [1.6114012813668932]
  In 2020, the U.S. Census Bureau transitioned from data swapping to differential privacy (DP) in its approach to de-identifying decennial census data. We compare the relative impacts of swapping and DP on census data, focusing on the use case of school planning. Our findings support the use of DP over swapping for single-year-of-age counts. For the school planning use cases we investigate, DP provides comparable, if not improved, accuracy over swapping, while offering other benefits such as improved transparency.
  arXiv  Detail & Related papers  (2023-08-24T15:56:05Z)
• All a-board: sharing educational data science research with school districts [20.799163734027466]
  We conduct randomized email outreach experiments and surveys to explore how local school districts respond to boundary changes. Approximately 4,320 elected school board members across over 800 school districts informed of potential boundary changes. Media coverage of the research drives more dashboard engagement, especially in more segregated districts.
  arXiv  Detail & Related papers  (2023-04-18T13:03:05Z)
• Redrawing attendance boundaries to promote racial and ethnic diversity in elementary schools [31.737460075609103]
  Most U.S. school districts draw "attendance boundaries" to assign students to schools near their homes. We simulate alternative boundaries for 98 US school districts serving over 3 million elementary-aged students. Our results show the possibility of greater integration without significant disruptions for families.
  arXiv  Detail & Related papers  (2023-03-14T02:50:40Z)
• On Differentially Private Online Predictions [74.01773626153098]
  We introduce an interactive variant of joint differential privacy towards handling online processes. We demonstrate that it satisfies (suitable variants) of group privacy, composition, and post processing. We then study the cost of interactive joint privacy in the basic setting of online classification.
  arXiv  Detail & Related papers  (2023-02-27T19:18:01Z)
• Mixed Differential Privacy in Computer Vision [133.68363478737058]
  AdaMix is an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset.
  arXiv  Detail & Related papers  (2022-03-22T06:15:43Z)
• Decision Making with Differential Privacy under a Fairness Lens [65.16089054531395]
  The U.S. Census Bureau releases data sets and statistics about groups of individuals that are used as input to a number of critical decision processes. To conform to privacy and confidentiality requirements, these agencies are often required to release privacy-preserving versions of the data. This paper studies the release of differentially private data sets and analyzes their impact on some critical resource allocation tasks under a fairness perspective.
  arXiv  Detail & Related papers  (2021-05-16T21:04:19Z)
• Voting-based Approaches For Differentially Private Federated Learning [87.2255217230752]
  This work is inspired by knowledge transfer non-federated privacy learning from Papernot et al. We design two new DPFL schemes, by voting among the data labels returned from each local model, instead of averaging the gradients. Our approaches significantly improve the privacy-utility trade-off over the state-of-the-arts in DPFL.
  arXiv  Detail & Related papers  (2020-10-09T23:55:19Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.