4 papers
Geodesics of Dynamic Graphs for Regime Change Detection
William Cappelletti, Ãtienne Voutaz, Pascal Frossard
Traditional change point detection in dynamic networks assumes abrupt transitions between stationary states, overlooking scenarios of continuous evolution which arise in most real-…
Graph-Dictionary Signal Model for Sparse Representations of Multivariate Data
William Cappelletti, Pascal Frossard
Representing and exploiting multivariate signals requires capturing relations between variables, which we can represent by graphs. Graph dictionaries allow to describe complex rela…
rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data
Yuhan Xie, William Cappelletti, Mahsa Shoaran +1
Deep neural networks for time series must capture complex temporal patterns, to effectively represent dynamic data. Self- and semi-supervised learning methods show promising result…
PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks
Yamin Sepehri, Pedram Pad, Pascal Frossard +1
The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training d…