skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 8:00 PM ET on Friday, March 21 until 8:00 AM ET on Saturday, March 22 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • Home
  • Search Results
  • Page 1 of 1

Search for: All records

Creators/Authors contains: "Desai, Pradnya"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; ( , International Conference on Neural Information Processing)
    In this paper, we focus on preserving differential privacy (DP) in continual learning (CL), in which we train ML models to learn a sequence of new tasks while memorizing previous tasks. We first introduce a notion of continual adjacent databases to bound the sensitivity of any data record participating in the training process of CL. Based upon that, we develop a new DP-preserving algorithm for CL with a data sampling strategy to quantify the privacy risk of training data in the well-known Averaged Gradient Episodic Memory (A-GEM) approach by applying a moments accountant. Our algorithm provides formal guarantees of privacy for data records across tasks in CL. Preliminary theoretical analysis and evaluations show that our mechanism tightens the privacy loss while maintaining a promising model utility. 
    more » « less
    Full Text Available 
  2. ; ; ; ; ; ( , Proceedings of the Annual Symposium on Computer-Human Interaction in Play)
    Digital patronage is the act of delivering recurring direct support to content creators online. In this paper, we define digital patronage and examine why patrons engage in this behavior on the live streaming platform Twitch. Our mixed method research illustrates patrons' motivations, how patronage motivations differ from that of donations, and the motivational factors that are associated with higher levels of patronage. We discuss how results extend understanding of patronage in the context of social support theory and provide design implications for digital patronage platforms. 
    more » « less
    Full Text Available