646 citations
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR251 papers
- Université Paris-SaclayFR110 papers
- Centre National de la Recherche ScientifiqueFR64 papers
- CEA Paris-SaclayFR55 papers
- Institut de Recherche sur les Lois Fondamentales de l'UniversFR21 papers
- Université d'Abomey-CalaviBJ21 papers
- Laboratoire National Henri BecquerelFR19 papers
- Université Grenoble AlpesFR16 papers
- Sorbonne UniversitéFR14 papers
- CEA GrenobleFR11 papers
- CentraleSupélecFR11 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR11 papers
17 papers · 1 filter
Benchmarking Catastrophic Forgetting Mitigation Methods in Federated Time Series Forecasting
Khaled Hallak, Oudom Kem
Catastrophic forgetting (CF) poses a persistent challenge in continual learning (CL), especially within federated learning (FL) environments characterized by non-i.i.d. time series…
How Foundational are Foundation Models for Time Series Forecasting?
Nouha Karaouli, Denis Coquenet, Elisa Fromont +2
Foundation Models are designed to serve as versatile embedding machines, with strong zero shot capabilities and superior generalization performance when fine-tuned on diverse downs…
Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting
Nouha Karaouli, Denis Coquenet, Elisa Fromont +2
While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood. We present the first systematic study of cata…
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Grégoire Petit, Michael Soumm, Eva Feillet +4
Class-Incremental Learning (CIL) aims to build classification models from data streams. At each step of the CIL process, new classes must be integrated into the model. Due to catas…
Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space
Eduardo Fernandes Montesuma, Fred Ngolè Mboula, Antoine Souloumiac
This paper seeks to solve Multi-Source Domain Adaptation (MSDA), which aims to mitigate data distribution shifts when transferring knowledge from multiple labeled source domains to…
Why is the prediction wrong? Towards underfitting case explanation via meta-classification
Sheng Zhou, Pierre Blanchart, Michel Crucianu +1
In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier. Sinc…