BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:871@lincs.fr
DTSTART;TZID=Europe/Paris:20250221T110000
DTEND;TZID=Europe/Paris:20250221T120000
DTSTAMP:20250228T150133Z
URL:https://www.lincs.fr/events/fjord-fair-and-accurate-federated-learning
 -under-heterogeneous-targets-with-ordered-dropout/
SUMMARY:FjORD: Fair and Accurate Federated Learning under heterogeneous
 targets with Ordered Dropout
DESCRIPTION:Federated Learning (FL) has been gaining significant traction
 across different ML tasks\, ranging from vision to keyboard predictions. In
 large-scale deployments\, client heterogeneity is a fact and constitutes a
 primary problem for fairness\, training performance and accuracy. Although
 significant efforts have been made into tackling statistical data
 heterogeneity\, the diversity in the processing capabilities and network
 bandwidth of clients\, termed as system heterogeneity\, has remained
 largely unexplored. Current solutions either disregard a large portion of
 available devices or set a uniform limit on the model's capacity\,
 restricted by the least capable participants. This work introduces Ordered
 Dropout\, a mechanism that achieves an ordered\, nested representation of
 knowledge in deep neural networks (DNNs) and enables the extraction of
 lower footprint submodels without the need of retraining. It further shows
 that for linear maps\, Ordered Dropout is equivalent to SVD. This
 technique\, along with a self-distillation methodology\, is applied in the
 realm of FL in a framework called FjORD. FjORD alleviates the problem of
 client system heterogeneity by tailoring the model width to the client's
 capabilities. Extensive evaluation on both CNNs and RNNs across diverse
 modalities shows that FjORD consistently leads to significant performance
 gains over state-of-the-art baselines\, while maintaining its nested
 structure. In this seminar\, we discuss this paper and we highlight some of
 its features and how it relates to my current work.
CATEGORIES:Practical Networks,Working Group,Youtube
LOCATION:Amphi 6\, 19 Place Marguerite Perey\, Palaiseau\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=19 Place Marguerite Perey\,
 Palaiseau\, France;X-APPLE-RADIUS=100;X-TITLE=Amphi 6:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR