Publications

General Causal Imputation via Synthetic Interventions
Marco Jiralerspong
Thomas Jiralerspong
Vedant Shah
Dhanya Sridhar
Gauthier Gidel
Given two sets of elements (such as cell types and drug compounds), researchers typically only have access to a limited subset of their inte… (see more)ractions. The task of causal imputation involves using this subset to predict unobserved interactions. Squires et al. (2022) have proposed two estimators for this task based on the synthetic interventions (SI) estimator: SI-A (for actions) and SI-C (for contexts). We extend their work and introduce a novel causal imputation estimator, generalized synthetic interventions (GSI). We prove the identifiability of this estimator for data generated from a more complex latent factor model. On synthetic and real data we show empirically that it recovers or outperforms their estimators.
2024-10-29
NeurIPS.cc/2024/Workshop/CRL (poster)
doi.org
openreview.net
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
Shalaleh Rismani
Roel Dobbe
AJung Moon
2024-10-28
ArXiv (preprint)
doi.org
arxiv.org
Injury and violence in the context of sustainable development
Kidist Bartolomeos
Ryan Lett
Berjo Takoutsing
Respicious Boniface
Victoria Munthali
Tarek Razek
Dan Deckelbaum
David Bracco
Ermiyas Belay
Fitsum Kifle
David Ulrich Dalle
Celestin Bilong Mbangtang
Arsene Daniel Nyalundja
Jondre Macaraeg
Irene Dzirasa
Ulrick Sidney Kanmounye
Delanyo Dovlo
Kwadwo Koram
Eugene Nyarko
Desmond T. Jumbam … (see 185 more)
Emnet Tesfay Shimber
Taylor Jaraczewski
Shemsedin Ibro
Maria Sgro
Ajiel Mae Basmayor
Asegid Ergete
Mary Schroeder
Adam Gyedu
Emmanuel Nakua
Peter Donkor
Charles Mock
Atalel Awedew
Halid Melkamu
Sisay Bekele
Berhanu Hailemariam
Enku Shiferaw
Yishak Shiferaw
Wubetie Yirdaw
Debojit Basak
Deepa Kizhakke Veetil
Nobhojit Roy
Martin Gerdin Wärnberg
Santosh Rath
Mohammed A.S Abdullahi
Kefas Mbaya
Abubakar Kakasanda
Stephanie Danjuma
Hector Olasoji
Alemayehu Bedada
Mpapho Joseph Motsumi
Shimelis Genna Hamda
Demuma Amdisa
Getachew Tilahun
Katie Iverson
Matthew Boroditsky
Mark Hill
Roy Hilzenrat
Rachel Livergant
Jayd Adams
Catherine Binda
Allison Chhor
Helen Hsiao
Faizal Haji
Esther Chin
Felix Oyania
Caroline Q. Stephens
Sarah Ullrich
Meera Kotagal
Francis Bajunirwe
Doruk Ozgediz
Dionysia Kravarioti
Lye-Yeng Wong
Tsegazeab Laeke Teklemariam
Abenezer Tirsit
Tewodros Liyew
Mark Ferguson
Timothy Plackett
Jaymie Claire Henry
Meseret Abeza
Seye Mesfin Minas
Maryse Bouchard
Dimuthu Tennakoon
Rahul Burra
Fleming Mathew
Annabelle Jones
Sargun Virk
Shlok Patel
Tanaz Vaghaiwalla
James Hudspeth
Tracy Rabin
Virginia Rowthorn
Raymond R. Price
Nakul Raykar
Gilgamesh Eamer
Stephen Mutiso
Yvette Kisaka
Gladwell Gathecha
Ronald Lett
Chibuike Onu
Emmanuel Ameh
Matthias Igoche
Meseret Abeza
Paschal Anyanwu
Eunice Onuh
Oikeh Ojeamen
Edith Terna Yawe
Amina Abubakar
Yakubu Ashoms
Hadiza Suleiman
Naomi Musa
Daniel Kisitu Kyengera
Netsanet Abebe
Richard Gardener
Nebyou Seyoum Abebe
Henok T/Silasie Zeleke
Kacylia Roy Proulx
Shreenik Kundu
Boaz Laor
Riya Sawhney
Taylor Wurdeman
Fabio Botelho
Ayla Gerk
Elena Guadagno
Dan Poenaru
Mengistu Ayele
Azarias Kassahun
Tsegazeab Laeke
Mestet Yibeltal
Bereket Hailu
Ermias Fikru
Shemsedin Ibro
Abdeta Workineh
Fikadu Balcha
Fira Abamecha
Sheka Shemsi
Abdullah Saleh Alruwaili
Gabriel Rodriguez
Anna Jose
Shahd Ebied
Samuel Girma
Abigael Abiy
Hussien Endris Assen
Kalab Tesfaye
Kassaye Demeke
Aklilu Yiheyis
Khalid Jemal
Demeke Yilkal
Ashenafi Amsalu
Lema Derseh
Yophtahe W/Gerima
Tadesse Belayneh
Mekuanint Tiruneh
Almaw Bitew
Sewbesew Yitayih
Tadesse Awoke
Chanyalew Worku
Anissa Mohammed
Mohammed Alemu
Mohammed Yesuf
Fantu Mamo
Kegnie Shitu
Biks Liyew
Ayenew Gucho
Gezahegn Tilahun
Timothy Love
Andrew Chew
Brian Kasagga
Berjo Takoutsing
Obuku Ekwaro
Emmanuel Elobu
Degisew Dersso Mengistu
Alex Zhuang
Bethlehem Shiferew
Gelila Mengistu
Ayalew Zewdie
Nahom Tadelle
Alegnta Gebreyesus
Elise Presser
Katie Iverson
Christopher Dodgion
Thomas G. Weiser
Rachel Koch
Nichole Starr
Davy Lau
Irena Zivkovic
Christopher Dodgion
Shahrzad Joharifard
Emilie Joos
Naisan Garraway
Francesca Vituci
Eric O’Flynn
Ines Péric
Léa Simon
Geoffrey Ibbotson
Tsion Seyoum
Aklilu Azazh
Lemlem Beza
Ifeanyichukwu Onah
Chijioke Chukwuma
Dagim Berhanu
Jason Shenoi
Nick Sears
Yoseph Bedore
Richard Caplan
Wongel Tena Shale
invaluable
2024-10-28
Canadian journal of surgery. Journal canadien de chirurgie (published)
doi.org
Sliced-Wasserstein-based Anomaly Detection and Open Dataset for Localized Critical Peak Rebates
Julien Pallage
Bertrand Scherrer
Salma Naccache
Christophe B'elanger
Antoine Lesage-Landry
2024-10-28
ArXiv (preprint)
doi.org
arxiv.org
The Case for Globalizing Fairness: A Mixed Methods Study on Colonialism, AI, and Health in Africa
Mercy Nyamewaa Asiedu
Awa Dieng
Iskandar Haykel
Negar Rostamzadeh
Stephen R. Pfohl
Chirag Nagpal
Maria Nagawa
Abigail Oppong
Sanmi Koyejo
Katherine Heller
With growing application of machine learning (ML) technologies in healthcare, there have been calls for developing techniques to understand … (see more)and mitigate biases these systems may exhibit. Fair-ness considerations in the development of ML-based solutions for health have particular implications for Africa, which already faces inequitable power imbalances between the Global North and South.This paper seeks to explore fairness for global health, with Africa as a case study. We conduct a scoping review to propose axes of disparities for fairness consideration in the African context and delineate where they may come into play in different ML-enabled medical modalities. We then conduct qualitative research studies with 672 general population study participants and 28 experts inML, health, and policy focused on Africa to obtain corroborative evidence on the proposed axes of disparities. Our analysis focuses on colonialism as the attribute of interest and examines the interplay between artificial intelligence (AI), health, and colonialism. Among the pre-identified attributes, we found that colonial history, country of origin, and national income level were specific axes of disparities that participants believed would cause an AI system to be biased.However, there was also divergence of opinion between experts and general population participants. Whereas experts generally expressed a shared view about the relevance of colonial history for the development and implementation of AI technologies in Africa, the majority of the general population participants surveyed did not think there was a direct link between AI and colonialism. Based on these findings, we provide practical recommendations for developing fairness-aware ML solutions for health in Africa.
2024-10-28
Proceedings of the 4th ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (published)
doi.org
arxiv.org
Doctoral Symposium Committee
Anthony Cleve
Christian Lange
Silvia Breu
Manar H. Alalfi
Mario Luca Bernardi
Cornelia Boldyreff
Marco D'Ambros
Simon Denier
Natalia Dragan
Ekwa Duala-Ekoko
Fausto Fasano
Adnane Ghannem
Carmine Gravino
Maen Hammad
Imed Hammouda
Salima Hassaine
Yue Jia
Zhen Ming (Jack) Jiang
Foutse Khomh
Adam Kiezun … (see 11 more)
Jay Kothari
Jonathan Memaitre
Naouel Moha
Rocco Oliveto
Denys Poshyvanyk
Michele Risi
Giuseppe Scanniello
Bonita Sharif
Andrew Sutton
Anis Yousefi
Eugenio Zimeo
Manar H. Alalfi Mario Luca Bernardi Cornelia Boldyreff Anthony Cleve Marco D'Ambros Simon Denier Natalia Dragan Ekwa Duala-Ekoko Fausto Fasa… (see more)no Adnane Ghannem Carmine Gravino Maen Hammad Imed Hammouda Salima Hassaine Yue Jia Zhen Ming Jiang Foutse Khomh Adam Kiezun Jay Kothari Jonathan Memaitre Naouel Moha Rocco Oliveto Denys Poshyvanyk Michele Risi Giuseppe Scanniello Bonita Sharif Andrew Sutton Anis Yousefi Eugenio Zimeo
2024-10-27
2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW) (published)
doi.org
Investigating the Benefits of Nonlinear Action Maps in Data-Driven Teleoperation
Michael Przystupa
Gauthier Gidel
Matthew E. Taylor
Martin Jagersand
Justus Piater
Samuele Tosatto
As robots become more common for both able-bodied individuals and those living with a disability, it is increasingly important that lay peop… (see more)le be able to drive multi-degree-of-freedom platforms with low-dimensional controllers. One approach is to use state-conditioned action mapping methods to learn mappings between low-dimensional controllers and high DOF manipulators -- prior research suggests these mappings can simplify the teleoperation experience for users. Recent works suggest that neural networks predicting a local linear function are superior to the typical end-to-end multi-layer perceptrons because they allow users to more easily undo actions, providing more control over the system. However, local linear models assume actions exist on a linear subspace and may not capture nuanced actions in training data. We observe that the benefit of these mappings is being an odd function concerning user actions, and propose end-to-end nonlinear action maps which achieve this property. Unfortunately, our experiments show that such modifications offer minimal advantages over previous solutions. We find that nonlinear odd functions behave linearly for most of the control space, suggesting architecture structure improvements are not the primary factor in data-driven teleoperation. Our results suggest other avenues, such as data augmentation techniques and analysis of human behavior, are necessary for action maps to become practical in real-world applications, such as in assistive robotics to improve the quality of life of people living with w disability.
2024-10-27
ArXiv (preprint)
doi.org
arxiv.org
Trajectory Flow Matching with Applications to Clinical Time Series Modeling
Xi Zhang
Yuan Pu
Yuki Kawamura
Andrew Loza
Yoshua Bengio
Dennis L. Shung
Alexander Tong
2024-10-27
ArXiv (preprint)
doi.org
openreview.net
In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators
Dmytro Humeniuk
Houssem Ben Braiek
Thomas Reid
Foutse Khomh
2024-10-26
Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (published)
doi.org
arxiv.org
Brain-like learning with exponentiated gradients
Jonathan Cornford
Roman Pogodin
Arna Ghosh
Kaiwen Sheng
Brendan A. Bicknell
Olivier Codol
Beverley A. Clark
Guillaume Lajoie
Blake A. Richards
Computational neuroscience relies on gradient descent (GD) for training artificial neural network (ANN) models of the brain. The advantage o… (see more)f GD is that it is effective at learning difficult tasks. However, it produces ANNs that are a poor phenomenological fit to biology, making them less relevant as models of the brain. Specifically, it violates Dale’s law, by allowing synapses to change from excitatory to inhibitory, and leads to synaptic weights that are not log-normally distributed, contradicting experimental data. Here, starting from first principles of optimisation theory, we present an alternative learning algorithm, exponentiated gradient (EG), that respects Dale’s Law and produces log-normal weights, without losing the power of learning with gradients. We also show that in biologically relevant settings EG outperforms GD, including learning from sparsely relevant signals and dealing with synaptic pruning. Altogether, our results show that EG is a superior learning algorithm for modelling the brain with ANNs.
2024-10-25
bioRxiv (preprint)
doi.org
Efficient Biological Data Acquisition through Inference Set Design
Ihor Neporozhnii
Julien Roy
Emmanuel Bengio
Jason Hartford
In drug discovery, highly automated high-throughput laboratories are used to screen a large number of compounds in search of effective drugs… (see more). These experiments are expensive, so one might hope to reduce their cost by only experimenting on a subset of the compounds, and predicting the outcomes of the remaining experiments. In this work, we model this scenario as a sequential subset selection problem: we aim to select the smallest set of candidates in order to achieve some desired level of accuracy for the system as a whole. Our key observation is that, if there is heterogeneity in the difficulty of the prediction problem across the input space, selectively obtaining the labels for the hardest examples in the acquisition pool will leave only the relatively easy examples to remain in the inference set, leading to better overall system performance. We call this mechanism inference set design, and propose the use of a confidence-based active learning solution to prune out these challenging examples. Our algorithm includes an explicit stopping criterion that interrupts the acquisition loop when it is sufficiently confident that the system has reached the target performance. Our empirical studies on image and molecular datasets, as well as a real-world large-scale biological assay, show that active learning for inference set design leads to significant reduction in experimental cost while retaining high system performance.
2024-10-24
ArXiv (preprint)
doi.org
arxiv.org
Investigating Alpha-DaRT Source Daughter Diffusion in Intra-Rectal Animal Models
Mélodie Cyr
Behnaz Behmand
Naim Chabaytah
Joud Babik
Mirta Dumancic
Joanna Li
Guillaume St-Jean
Shirin A. Enger
2024-10-24
Brachytherapy (published)
doi.org