Zobrazeno 1 - 10
of 918
pro vyhledávání: '"Frossard Pascal"'
Neural Machine Translation systems are used in diverse applications due to their impressive performance. However, recent studies have shown that these systems are vulnerable to carefully crafted small perturbations to their inputs, known as adversari
Externí odkaz:
http://arxiv.org/abs/2411.12473
Autor:
Cappelletti, William, Frossard, Pascal
Representing and exploiting multivariate signals require capturing complex relations between variables. We define a novel Graph-Dictionary signal model, where a finite set of graphs characterizes relationships in data distribution through a weighted
Externí odkaz:
http://arxiv.org/abs/2411.05729
Autor:
Wang, Ke, Dimitriadis, Nikolaos, Favero, Alessandro, Ortiz-Jimenez, Guillermo, Fleuret, Francois, Frossard, Pascal
Large pre-trained models exhibit impressive zero-shot performance across diverse tasks, but fine-tuning often leads to catastrophic forgetting, where improvements on a target domain degrade generalization on other tasks. To address this challenge, we
Externí odkaz:
http://arxiv.org/abs/2410.17146
In this study, we present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. Our approach draws inspiration from Reinforcement Learning principles, particularly the Deep Q-Network paradigm, extending Tem
Externí odkaz:
http://arxiv.org/abs/2410.06786
Graph generation is fundamental in diverse scientific applications, due to its ability to reveal the underlying distribution of complex data, and eventually generate new, realistic data points. Despite the success of diffusion models in this domain,
Externí odkaz:
http://arxiv.org/abs/2410.04263
This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between
Externí odkaz:
http://arxiv.org/abs/2408.05599
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 dataset contains sensitive content, e.g., face images. In this work, we
Externí odkaz:
http://arxiv.org/abs/2408.05092
Dealing with multi-task trade-offs during inference can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front with a single model, contrary to traditional Multi-Task Learning (MTL) approaches that optimize for a sing
Externí odkaz:
http://arxiv.org/abs/2407.08056
In this work, we propose a novel approach for subgraph matching, the problem of finding a given query graph in a large source graph, based on the fused Gromov-Wasserstein distance. We formulate the subgraph matching problem as a partial fused Gromov-
Externí odkaz:
http://arxiv.org/abs/2406.19767
Graph diffusion models have emerged as state-of-the-art techniques in graph generation, yet integrating domain knowledge into these models remains challenging. Domain knowledge is particularly important in real-world scenarios, where invalid generate
Externí odkaz:
http://arxiv.org/abs/2406.17341