Skip to main content

NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.

Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.

U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

MGD: A Utility Metric for Private Data Publication

Project Summary

We propose MarGinal Difference (MGD), a utility metric for private data publication. MGDassigns a difference score between  the  synthesized dataset and the  ground truth dataset.  The high level idea behind MGD is to measure the differences between many pairs marginal tables, each pair having one computed from the two datasets.  For measuring the difference between a pair of marginal  tables, we  introduce  Approximate Earth  Mover  Cost, which  considers  both semantic meanings of attribute values and the noisy nature of the synthesized dataset.

Place: 1st

Prize amount: $5,000

Team members: Ninghui Li, Trung Đặng Đoàn Đức, Zitao Li, Tianhao Wang


Created February 16, 2021
Was this page helpful?