Fwd: Thesis Defense - July 12, 2023 - Sebastian Caldas - Collaborative learning by leveraging siloed data

[Artur Dubrawski]

This will be fun!

Please mark your calendars and join to cheer for Sebastian while enjoying a
presentation of exceptional quality.

Cheers
Artur

---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Tue, Jun 27, 2023 at 4:24 PM
Subject: Thesis Defense - July 12, 2023 - Sebastian Caldas - Collaborative
learning by leveraging siloed data
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <cler at pitt.edu>, <
martin.jaggi at epfl.ch>


*Thesis Defense*

Date: July 12, 2023
Time: 4:00pm (EDT)
Place: GHC 8102 & Remote
PhD Candidate: Sebastian Caldas

*Title: **Collaborative learning by leveraging siloed data*
Abstract:
Regulations can often limit stakeholders’ modeling capabilities by
preventing data sharing. For example, in order to protect patient privacy,
clinical centers may be unable to share their data and thus lack
representative records to learn about a rare condition. To address this
challenge, previous work in machine learning has shown that these
stakeholders benefit from training models in a collaborative fashion,
improving their predictive performance. However, as we start training these
collaborative models in real-world settings, and in order to be truly
useful, they need to provide utility along dimensions beyond predictive
performance. In this thesis, we propose methods and algorithms to improve
collaborative models that leverage siloed data along three dimensions. In
the first part, we propose methods to reduce the communication footprint of
models learned by mobile devices cooperating over edge networks, allowing
for higher capacity models to be trained. Then, in the second part, we
introduce an algorithm that provides explanations about predictions of
models trained across clinical centers, thus improving their clinical
utility. Finally, in the third part, we address the need to encode expert
supervision into collaborative models trained using on-device data,
increasing the class of problems we can tackle in these scenarios.

*Thesis Committee:*
Artur Dubrawski (Chair)
Virginia Smith
Gilles Clermont (University of Pittsburgh) cler at pitt.edu
Martin Jaggi (EPFL) martin.jaggi at epfl.ch

*Link to the draft document: *
https://drive.google.com/file/d/1xTPUERARdnQnMSNCnu2VXrWk1YFKQOqp/view?usp=sharing


*Zoom meeting link:*
https://cmu.zoom.us/j/92902855666?pwd=a3l4V3ppQlp1K252K2doSjNTRlhPdz09
<https://www.google.com/url?q=https://cmu.zoom.us/j/92902855666?pwd%3Da3l4V3ppQlp1K252K2doSjNTRlhPdz09&sa=D&source=calendar&ust=1688311717182551&usg=AOvVaw0fNQndryXEeSLoOO-ZhNfp>

-- 
Diane Stidle
PhD Program Manager
Machine Learning Department
Carnegie Mellon Universitystidle at andrew.cmu.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20230627/d256ebc7/attachment.html>