1 code implementation • 15 Feb 2024 • Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov, Aladin Virmaux, Giuseppe Paolo, Themis Palpanas, Ievgen Redko
Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting.
1 code implementation • 17 Dec 2023 • Adrien Petralia, Philippe Charpentier, Themis Palpanas
The experimental results with two large real datasets show that the proposed approach outperforms current solutions, including state-of-the-art time series classifiers applied to appliance detection.
no code implementations • 16 Nov 2023 • Romain Ilbert, Thai V. Hoang, Zonghua Zhang, Themis Palpanas
Our optimal model can retain up to $92. 02\%$ the performance of the original forecasting model in terms of Mean Squared Error (MSE) on clean data, while being more robust than the standard adversarially trained models on perturbed data.
no code implementations • 11 Jul 2023 • Zhuxian Guo, Qitong Wang, Henning Müller, Themis Palpanas, Nicolas Loménie, Camille Kurtz
In digital histopathology, entire neoplasm segmentation on Whole Slide Image (WSI) of Hepatocellular Carcinoma (HCC) plays an important role, especially as a preprocessing filter to automatically exclude healthy tissue, in histological molecular correlations mining and other downstream histopathological tasks.
1 code implementation • 3 Jul 2023 • George Papadakis, Nishadi Kirielle, Peter Christen, Themis Palpanas
Entity resolution (ER) is the process of identifying records that refer to the same entities within one or across multiple databases.
1 code implementation • 10 May 2023 • Adrien Petralia, Philippe Charpentier, Paul Boniol, Themis Palpanas
This paper presents an in-depth evaluation and comparison of state-of-the-art time series classifiers applied to detecting the presence/absence of diverse appliances in very low-frequency smart meter data.
no code implementations • 25 Jul 2022 • Paul Boniol, Themis Palpanas
Subsequence anomaly detection in long sequences is an important problem with applications in a wide range of domains.
1 code implementation • 25 Jul 2022 • Paul Boniol, Mohammed Meftah, Emmanuel Remy, Themis Palpanas
Convolutional neural networks perform well for the data series classification task; though, the explanations provided by this type of algorithm are poor for the specific case of multivariate data series.
no code implementations • 19 Aug 2020 • Wissam Maamar Kouadri, Salima Benbernou, Mourad Ouziri, Themis Palpanas, Iheb Ben Amor
The opinion expressed in various Web sites and social-media is an essential contributor to the decision making process of several organizations.
no code implementations • 19 Dec 2018 • Cagatay Turkay, Nicola Pezzotti, Carsten Binnig, Hendrik Strobelt, Barbara Hammer, Daniel A. Keim, Jean-Daniel Fekete, Themis Palpanas, Yunhai Wang, Florin Rusu
We discuss these challenges and outline first steps towards progressiveness, which, we argue, will ultimately help to significantly speed-up the overall data science process.
no code implementations • 22 May 2014 • Michele Dallachiesa, Charu Aggarwal, Themis Palpanas
We study the novel problem of node classification in uncertain graphs, by treating uncertainty as a first-class citizen.