Competition
Privacy Preserving Federated Learning Document VQA
Dimosthenis Karatzas · Rubèn Tito · Lei Kang · Mohamed Ali Souibgui · Khanh Nguyen · Raouf Kerkouche · Kangsoo Jung · Marlon Tobaben · Joonas Jälkö · Vincent Poulain d'Andecy · Aurélie JOSEPH · Ernest Valveny · Josep Llados · Antti Honkela · Mario Fritz
Room 356
In an era of increasing digitalization and data-driven decision-making, the intersection of document intelligence and privacy has become a critical concern. The Privacy-Preserving Federated Learning Document Visual Question Answering Workshop aims to bring together experts, researchers, and practitioners to explore innovative solutions and discuss the latest advancements in this crucial field.
Join us for insightful invited talks by leading figures in the field. These talks will provide valuable perspectives on the current state of privacy-preserving document intelligence and its future directions. Get an in-depth look at the Privacy-Preserving Document Visual Question Answering Competition that we are currently holding, with a detailed overview of the competition, the dataset, and the competition results. Moreover, the top winners of the competition will have the opportunity to give short talks about their winning methods and strategies. Gain firsthand insights into the innovative approaches that led to their success.
Workshop URL: https://sites.google.com/view/pfldocvqa-neurips-23/home
Associated Competition URL: https://benchmarks.elsa-ai.eu/?ch=2
Schedule
Fri 7:00 a.m. - 7:05 a.m.
|
Opening remarks
(
Opening
)
>
SlidesLive Video |
Dimosthenis Karatzas 🔗 |
Fri 7:05 a.m. - 7:20 a.m.
|
Presentation of the ELSA network
(
Overview
)
>
SlidesLive Video |
Mario Fritz 🔗 |
Fri 7:20 a.m. - 7:50 a.m.
|
Virginia Smith - On Privacy and Personalization in Federated Learning
(
Invited talk
)
>
SlidesLive Video |
Virginia Smith 🔗 |
Fri 7:50 a.m. - 8:20 a.m.
|
David Doermann - Advancing Privacy and Dataset Augmentation in Medical and Chart Data Using AI-Driven Image Editing
(
Invited talk
)
>
SlidesLive Video |
DAVID DOERMANN 🔗 |
Fri 8:20 a.m. - 8:30 a.m.
|
Coffee Break
|
🔗 |
Fri 8:30 a.m. - 9:00 a.m.
|
Florien Tramèr - Privacy side-channels in machine learning systems
(
Invited talk
)
>
SlidesLive Video |
Florian Tramer 🔗 |
Fri 9:00 a.m. - 9:25 a.m.
|
Overview of the competition: Datasets, Metrics, and Results
(
Presentation
)
>
SlidesLive Video |
Marlon Tobaben · Khanh Nguyen 🔗 |
Fri 9:25 a.m. - 9:35 a.m.
|
Presentation from Participants – Winner FL Only Track: Communication Tuned Low-Rank Adaptation of Document Encoder
(
Presentation
)
>
SlidesLive Video |
Aashiq Muhamed 🔗 |
Fri 9:35 a.m. - 9:45 a.m.
|
Presentation from Participants – Winner FL+DP Track: Differentially Private Federated Learning with LoRA
(
Presentation
)
>
|
Ragul N 🔗 |
Fri 9:45 a.m. - 9:55 a.m.
|
Presentation from Participants – Runner-up Track 1 & 2: FedShampoo & DP-CLGECL
(
Presentation
)
>
SlidesLive Video |
Takumi Fukami · Yusuke Yamasaki 🔗 |
Fri 9:55 a.m. - 10:00 a.m.
|
Closing Remarks
(
Closing
)
>
SlidesLive Video |
Antti Honkela 🔗 |