1 code implementation • 2 Apr 2024 • Martijn Oldenhof, Edward De Brouwer, Adam Arany, Yves Moreau
Identifying the chemical structure from a graphical representation, or image, of a molecule is a challenging pattern recognition task that would greatly benefit drug development.
no code implementations • 23 Feb 2024 • Ilker Demirel, Edward De Brouwer, Zeshan Hussain, Michael Oberst, Anthony Philippakis, David Sontag
Drawing causal inferences from observational studies (OS) requires unverifiable validity assumptions; however, one can falsify those assumptions by benchmarking the OS with experimental data from a randomized controlled trial (RCT).
no code implementations • 26 Oct 2023 • Charles Xu, Laney Goldman, Valentina Guo, Benjamin Hollander-Bodie, Maedee Trank-Greene, Ian Adelstein, Edward De Brouwer, Rex Ying, Smita Krishnaswamy, Michael Perlmutter
We make several crucial changes to the original geometric scattering architecture which we prove increase the ability of our network to capture information about the input signal and show that BLIS-Net achieves superior performance on both synthetic and real-world data sets based on traffic flow and fMRI data.
1 code implementation • 8 Jul 2023 • Joyce Chew, Edward De Brouwer, Smita Krishnaswamy, Deanna Needell, Michael Perlmutter
We introduce a class of manifold neural networks (MNNs) that we call Manifold Filter-Combine Networks (MFCNs), that aims to further our understanding of MNNs, analogous to how the aggregate-combine framework helps with the understanding of graph neural networks (GNNs).
no code implementations • 13 Jun 2023 • Dhananjay Bhaskar, Sumner Magruder, Edward De Brouwer, Aarthi Venkat, Frederik Wenkel, Guy Wolf, Smita Krishnaswamy
Complex systems are characterized by intricate interactions between entities that evolve dynamically over time.
1 code implementation • NeurIPS 2023 • Guillaume Huguet, Alexander Tong, Edward De Brouwer, Yanlei Zhang, Guy Wolf, Ian Adelstein, Smita Krishnaswamy
Finally, we show that parameters of our more general method can be configured to give results similar to PHATE (a state-of-the-art diffusion based manifold learning method) as well as SNE (an attraction/repulsion neighborhood based method that forms the basis of t-SNE).
1 code implementation • 9 Mar 2023 • Martijn Oldenhof, Adam Arany, Yves Moreau, Edward De Brouwer
In this work, we propose ProbKT, a framework based on probabilistic logical reasoning that allows to train object detection models with arbitrary types of weak supervision.
1 code implementation • 3 Mar 2023 • Edward De Brouwer, Rahul G. Krishnan
These models provide a continuous-time latent representation of the underlying dynamical system where new observations at arbitrary time points can be used to update the latent representation of the dynamical system.
no code implementations • 14 Nov 2022 • Yukti Makhija, Edward De Brouwer, Rahul G. Krishnan
Checklists, while being only recently introduced in the medical domain, have become highly popular in daily clinical practice due to their combined effectiveness and great interpretability.
1 code implementation • 11 Oct 2022 • Edward De Brouwer
The standard approach to estimate counterfactuals resides in using a structural equation model that accurately reflects the underlying data generating process.
1 code implementation • 24 Feb 2022 • Edward De Brouwer, Javier González Hernández, Stephanie Hyland
In this work, we propose Counterfactual ODE (CF-ODE), a novel method to predict the impact of treatments continuously over time using Neural Ordinary Differential Equations equipped with uncertainty estimates.
1 code implementation • 25 Nov 2021 • Jonghyeon Lee, Edward De Brouwer, Boumediene Hamzi, Houman Owhadi
A simple and interpretable way to learn a dynamical system from data is to interpolate its vector-field with a kernel.
1 code implementation • 28 Oct 2021 • Michael F. Adamer, Edward De Brouwer, Leslie O'Bray, Bastian Rieck
Furthermore, we demonstrate practical use cases of magnitude for machine learning applications and propose a novel magnitude model that consists of a computationally efficient magnitude computation and a learnable metric.
1 code implementation • ICLR 2022 • Max Horn, Edward De Brouwer, Michael Moor, Yves Moreau, Bastian Rieck, Karsten Borgwardt
Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks, yet have been shown to be oblivious to eminent substructures such as cycles.
no code implementations • ICLR 2021 • Edward De Brouwer, Adam Arany, Jaak Simm, Yves Moreau
Discovering causal structures of temporal processes is a major tool of scientific inquiry because it helps us better understand and explain the mechanisms driving a phenomenon of interest, thereby facilitating analysis, reasoning, and synthesis for such systems.
no code implementations • 9 Nov 2020 • Edward De Brouwer, Thijs Becker, Yves Moreau, Eva Kubala Havrdova, Maria Trojano, Sara Eichau, Serkan Ozakbas, Marco Onofrj, Pierre Grammond, Jens Kuhle, Ludwig Kappos, Patrizia Sola, Elisabetta Cartechini, Jeannette Lechner-Scott, Raed Alroughani, Oliver Gerlach, Tomas Kalincik, Franco Granella, Francois GrandMaison, Roberto Bergamaschi, Maria Jose Sa, Bart Van Wijmeersch, Aysun Soysal, Jose Luis Sanchez-Menoyo, Claudio Solaro, Cavit Boz, Gerardo Iuliano, Katherine Buzzard, Eduardo Aguera-Morales, Murat Terzi, Tamara Castillo Trivio, Daniele Spitaleri, Vincent Van Pesch, Vahid Shaygannej, Fraser Moore, Celia Oreja Guevara, Davide Maimone, Riadh Gouider, Tunde Csepany, Cristina Ramo-Tello, Liesbet Peeters
In this work, we address the task of optimally extracting information from longitudinal patient data in the real-world setting with a special focus on the sporadic sampling problem.
1 code implementation • 25 Jul 2019 • Jaak Simm, Adam Arany, Edward De Brouwer, Yves Moreau
Applying machine learning to molecules is challenging because of their natural representation as graphs rather than vectors. Several architectures have been recently proposed for deep learning from molecular graphs, but they suffer from informationbottlenecks because they only pass information from a graph node to its direct neighbors.
4 code implementations • NeurIPS 2019 • Edward De Brouwer, Jaak Simm, Adam Arany, Yves Moreau
Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i. e., sampling is irregular both in time and across dimensions)-such as in the case of clinical patient data.
Ranked #2 on Multivariate Time Series Forecasting on MIMIC-III
no code implementations • 26 Nov 2018 • Edward De Brouwer, Jaak Simm, Adam Arany, Yves Moreau
We present a generative approach to classify scarcely observed longitudinal patient trajectories.