1 code implementation • 15 Sep 2023 • Yasuaki Hiraoka, Yusuke Imoto, Killian Meehan, Théo Lacombe, Toshiaki Yachimura
Node2vec is a graph embedding method that learns a vector representation for each node of a weighted graph while seeking to preserve relative proximity and global structure.
1 code implementation • 22 May 2023 • Felix Hensel, Charles Arnal, Mathieu Carrière, Théo Lacombe, Hiroaki Kurihara, Yuichi Ike, Frédéric Chazal
Despite their successful application to a variety of tasks, neural networks remain limited, like other machine learning methods, by their sensitivity to shifts in the data: their performance can be severely impacted by differences in distribution between the data on which they were trained and that on which they are deployed.
1 code implementation • 3 Feb 2022 • Thibault de Surrel, Felix Hensel, Mathieu Carrière, Théo Lacombe, Yuichi Ike, Hiroaki Kurihara, Marc Glisse, Frédéric Chazal
The use of topological descriptors in modern machine learning applications, such as Persistence Diagrams (PDs) arising from Topological Data Analysis (TDA), has shown great potential in various domains.
1 code implementation • 6 Jan 2022 • Théo Lacombe
We propose to modify the entropic regularization term to retrieve an UROT model that is homogeneous while preserving most properties of the standard UROT model.
1 code implementation • 1 Sep 2021 • Jacob Leygonie, Mathieu Carrière, Théo Lacombe, Steve Oudot
We introduce a novel gradient descent algorithm extending the well-known Gradient Sampling methodology to the class of stratifiably smooth objective functions, which are defined as locally Lipschitz functions that are smooth on some regular pieces-called the strata-of the ambient Euclidean space.
no code implementations • 11 May 2021 • Vincent Divol, Théo Lacombe
To overcome this issue, we propose an algorithm to compute a quantization of the empirical EPD, a measure with small support which is shown to approximate with near-optimal rates a quantization of the theoretical EPD.
no code implementations • 7 May 2021 • Théo Lacombe, Yuichi Ike, Mathieu Carriere, Frédéric Chazal, Marc Glisse, Yuhei Umeda
We showcase experimentally the potential of Topological Uncertainty in the context of trained network selection, Out-Of-Distribution detection, and shift-detection, both on synthetic and real datasets of images and graphs.
1 code implementation • 20 Apr 2019 • Mathieu Carrière, Frédéric Chazal, Yuichi Ike, Théo Lacombe, Martin Royer, Yuhei Umeda
Persistence diagrams, the most common descriptors of Topological Data Analysis, encode topological properties of data and have already proved pivotal in many different applications of data science.
no code implementations • NeurIPS 2018 • Théo Lacombe, Marco Cuturi, Steve Oudot
Persistence diagrams (PDs) are now routinely used to summarize the underlying topology of complex data.