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… (voir plus)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
Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy
Jos'e-Fabian Villa-V'asquez
Marco Pedersoli
Unsupervised object discovery is commonly interpreted as the task of localizing and/or categorizing objects in visual data without the need … (voir plus)for labeled examples. While current object recognition methods have proven highly effective for practical applications, the ongoing demand for annotated data in real-world scenarios drives research into unsupervised approaches. Furthermore, existing literature in object discovery is both extensive and diverse, posing a significant challenge for researchers that aim to navigate and synthesize this knowledge. Motivated by the evidenced interest in this avenue of research, and the lack of comprehensive studies that could facilitate a holistic understanding of unsupervised object discovery, this survey conducts an in-depth exploration of the existing approaches and systematically categorizes this compendium based on the tasks addressed and the families of techniques employed. Additionally, we present an overview of common datasets and metrics, highlighting the challenges of comparing methods due to varying evaluation protocols. This work intends to provide practitioners with an insightful perspective on the domain, with the hope of inspiring new ideas and fostering a deeper understanding of object discovery approaches.
2024-10-29
ArXiv (prépublication)
doi.org
arxiv.org
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
Shalaleh Rismani
Roel Dobbe
AJung Moon
2024-10-28
ArXiv (prépublication)
doi.org
arxiv.org
Injury and violence in the context of sustainable development
Ronald Lett
Tsegazeab Laeke
Respicious Boniface
Elise Presser
Berjo Dongmo Takoutsing
Emnet Tesfay Shimber
Adam Gyedu
Atalel Awedew
Halid Melkamu
Riya Sawhney
Mohammed A.S Abdullahi
Alemayehu Bedada
Shemsedin Ibro
Meseret Abeza
Matthew Boroditsky
Roy Hilzenrat
Felix Oyania
Dionysia Kravarioti
Maryse Bouchard
Riya Sawhney … (voir 80 de plus)
Gilgamesh Eamer
Chibuike Onu
Eunice Onuh
Daniel Kisitu Kyengera
Netsanet Abebe
Dagim Berhanu
Riya Sawhney
Shreenik Kundu
Mengistu Ayele
Shemsedin Amme Ibro
Gabriel Rodriguez
Samuel Girma
Hussien Endris Assen
Ayenew Gucho
Brian Kasagga
Degisew Dersso Mengistu
Davy Lau
Francesca Vituci
Tsion Seyoum
Ifeanyichukwu Onah
Dagim Berhanu
Wongel Tena Shale
Kidist Bartolomeos
Ryan Lett
Abenezer Tirsit
Azarias Kassahun
Victoria Munthali
Tarek Razek
Dan Deckelbaum
David Bracco
Ermiyas Belay
Fitsum Kifle
Thomas G. Weiser
Katie Iverson
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
Taylor Jaraczewski
Maria Sgro
Ajiel Mae Basmayor
Asegid Ergete
Katherine Iverson
Mary Schroeder
Christopher Dodgion
Emmanuel Nakua
Peter Donkor
Charles Mock
Tsegazeab Laeke
Mestet Yibeltal
Mengistu Ayele
Sisay Bekele
Berhanu Hailemariam
Enku Shiferaw
Yishak Shiferaw
Wubetie Yirdaw
Shlok Patel
Debojit Basak
Deepa Kizhakke Veetil
Nobhojit Roy
Martin Gerdin Wärnberg
Santosh Rath
Kefas Mbaya
Abubakar Kakasanda
Stephanie Danjuma
Hector Olasoji
Emmanuel Ameh
Mpapho Joseph Motsumi
Shimelis Genna Hamda
Demuma Amdisa
Getachew Tilahun
Tsegazeab Laeke
Mark Hill
Rachel Livergant
invaluable
2024-10-28
Canadian journal of surgery. Journal canadien de chirurgie (publié)
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 (prépublication)
doi.org
arxiv.org
Sum and Tensor of Quantitative Effects
Giorgio Bacci
Radu Mardare
Prakash Panangaden
Gordon Plotkin
2024-10-28
Logical Methods in Computer Science (publié)
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 … (voir plus)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 (publié)
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 … (voir 11 de plus)
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… (voir plus)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) (publié)
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… (voir plus)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 (prépublication)
doi.org
arxiv.org
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 (publié)
doi.org
arxiv.org
Parameter Efficient Fine-tuning of Transformer-Based Language Models Using Dataset Pruning
Sayed Mohammadreza Tayaranian Hosseini
Seyyed Hasan Mozafari
James Clark
Brett Meyer
Warren Gross
The widespread use of transformer-based language models is in part owed to their ease of adaptation to various tasks. Fine-tuning is a metho… (voir plus)d of adapting pre-trained language models to a downstream task. The resource requirements for fine-tuning, although still less than pre-training, has been increasing due to the significant growth in the number of parameters of language models. Parameter efficient fine-tuning methods limit the set of model parameters that are updated during fine-tuning, leading to reductions in both memory usage and fine-tuning time. Dataset pruning is another method of efficient fine-tuning which removes training data points, thus reducing training time, while maintaining the evaluation performance of the fine-tuned model. In this work, we apply dataset pruning on top of parameter efficient fine-tuning to further reduce the hardware requirements of the fine-tuning. Our approach benefits from lower memory usage of parameter efficient methods while addressing their long fine-tuning time with dataset pruning. On average, our proposed method uses 22% of the fine-tuning dataset while updating only 0.5% of model parameters. As a result, while achieving an evaluation performance similar to full fine-tuning, our method reduces the peak memory usage of the fine-tuning by 40% and its wall clock time by 83%.
2024-10-26
Asilomar Conference on Signals, Systems and Computers (publié)
doi.org
ProtSCAPE: Mapping the landscape of protein conformations in molecular dynamics
Siddharth Viswanath
Dhananjay Bhaskar
David R. Johnson
João Felipe Rocha
Egbert Castro
Jackson Grady
Alex T. Grigas
Michael Perlmutter
Corey S. O'Hern
Smita Krishnaswamy
Understanding the dynamic nature of protein structures is essential for comprehending their biological functions. While significant progress… (voir plus) has been made in predicting static folded structures, modeling protein motions on microsecond to millisecond scales remains challenging. To address these challenges, we introduce a novel deep learning architecture, Protein Transformer with Scattering, Attention, and Positional Embedding (ProtSCAPE), which leverages the geometric scattering transform alongside transformer-based attention mechanisms to capture protein dynamics from molecular dynamics (MD) simulations. ProtSCAPE utilizes the multi-scale nature of the geometric scattering transform to extract features from protein structures conceptualized as graphs and integrates these features with dual attention structures that focus on residues and amino acid signals, generating latent representations of protein trajectories. Furthermore, ProtSCAPE incorporates a regression head to enforce temporally coherent latent representations.
2024-10-26
ArXiv (prépublication)
doi.org
arxiv.org