My research.

This work is the product of diverse research interests and a variety of research opportunities that I have been lucky enough to pursue. The overarching goal is to provide interpretable methods, useful in their application but that also provide a broader understanding of the problem at hand.

Publications

Explanations and meaningful information: at the interface between technical capabilities and legal frameworks

PLSC 2022

D. Bourgeois, S. Vergnolle

For many individuals, decisions taken by a computer are preferable to ones made by humans because they are often considered to be more objective. At the same time, individuals feel uncomfortable with autonomous vehicles roaming the roads. This clash can be explained by the fact that decisions made by computers, and more specifically by AI-enabled systems, can be virtually impossible to understand from the outside.

Learning Representations of Source Code from Structure and Context

MSc. Thesis

D. Bourgeois

Early transformer models would view source code as plain text. In this work, we show the value of heterogenous representations, in particular tree and graph-based forms such as ASTs. We also show how transformers can be considered equivalent to Graph Neural Networks (GNN) in some forms, and leverage this fact to propose novel code understanding models.

GNNExplainer: Generating explanations for Graph Neural Networks

NeurIPS 2019

R. Ying, D. Bourgeois, J. You, M. Zitnik, J. Leskovec

Graph Neural Networks (GNNs) represent information very compactly, yet when machine learning models operate on them we lose the ability to understand predictions' rationale. In this work we propose a model-agnostic framework to extract meaningful explanations of any GNN's predictions.

A Dynamic Embedding Model of the Media Landscape

WWW 2019

J. Rappaz*, D. Bourgeois*, K. Aberer

Leverage the unsupervised news coverage similarity maps from prior work, we show that market dynamics greatly affect coverage patterns. In particular, acquisitions tend to concentrate and unify the set of covered events over time.

Selection Bias in News Coverage: Learning It, Fighting It

WWW 2018

D. Bourgeois, J. Rappaz, K. Aberer

Leveraging advanced recommendation systems, we analyze large amounts of news coverage from many sources. We extract similarity maps from the embedding, in order to understand similarities and biases in coverage, and propose a method for diversifying news consumption.

Using holistic information in the Trigger

LHCb Public Note

D. Bourgeois, C. Fitzpatrick, S. Stahl

The trigger sifts through large amounts of particle collision data in near real-time. This must be done in software, at a whopping 30MHz rate. In doing so, it must remove large amounts of data while retaining the most important information (i.e. the rarest decays). For this purpose, we devise high recall, configurable machine learning methods to efficiently retain the most useful information for later processing.

New approaches for track reconstruction in LHCb's Vertex Locator

JHEP 2018

C. Hasse, J. Albrecht, B. Couturier, D. Bourgeois, V. Coco, N. Nolte, S. Ponce

The VErtex LOcator (VELO) is the closest subdetector to the collision point. We reconstruct collision tracks and the residuals of each hit with respect to the initial estimated straight line. Using recurrent networks, we estimate the position and uncertainty of a VELO track's closest to beam state. The resolution of this prediction as well as its ability to estimate the uncertainty is shown to be superior to existing methods.

Patents

Cleaning robot

US20210346543A1

R. Brooks, D. Bourgeois, C. Chao, A. Trevor, M.R. Amer, A. Jules, G.F. Marcus

An autonomous mobile robot system designed for comprehensive UV-C disinfection of indoor environments. The robot features intelligent navigation, real-time pathogen detection capabilities, and adaptive UV exposure control to effectively eliminate COVID-19 and other harmful microorganisms while ensuring safe operation around humans.

Ultraviolet cleaning trajectory modeling

US20210347048A1

A. Trevor, D. Bourgeois, M. Kollmitz, C. Chao

An intelligent path planning system that uses factor graph optimization to ensure complete UV disinfection coverage. The framework provides mathematical guarantees for pathogen elimination by modeling UV exposure thresholds and optimizing robotic trajectories for maximum disinfection efficacy.

Systems and methods for a virtual facility supporting robotics fleet control and sensor data simulation

WO2025096496A1

M. Amer, D. Bourgeois, S. Nusser, P.-E. Evreux, K. Marshall, J. Staker, N. Vander Valk

An advanced simulation framework that creates digital twins of physical facilities to enable comprehensive robotic fleet testing and validation. The system generates synthetic sensor data at scale, allowing for extensive training of autonomous systems in realistic virtual environments before real-world deployment.

Systems and Methods for a Virtual Facility Supporting Robotics Fleet Control and Sensor Data Simulation

US20250251740A1

M. Amer, D. Bourgeois, S. Nusser, P.-E. Evreux, K. Marshall, J. Staker, N. Vander Valk

A comprehensive virtual simulation platform that creates photorealistic 3D digital twins of real facilities using neural rendering and computer vision. The system enables large-scale robotic fleet simulation, synthetic sensor data generation, and advanced training environments for autonomous systems, bridging the gap between virtual testing and real-world deployment.