Publications

MixupE: Understanding and improving Mixup from directional derivative perspective
Vikas Verma
Yingtian Zou
Sarthak Mittal
Wai Hoh Tang
Hieu Pham
Juho Kannala
Yoshua Bengio
Arno Solin
Kenji Kawaguchi
2023-07-01
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (published)
doi.org
proceedings.mlr.press
Omega: Optimistic EMA Gradients
Juan Ramirez
Rohan Sukumaran
Quentin Bertrand
Gauthier Gidel
Stochastic min-max optimization has gained interest in the machine learning community with the advancements in GANs and adversarial training… (see more). Although game optimization is fairly well understood in the deterministic setting, some issues persist in the stochastic regime. Recent work has shown that stochastic gradient descent-ascent methods such as the optimistic gradient are highly sensitive to noise or can fail to converge. Although alternative strategies exist, they can be prohibitively expensive. We introduce Omega, a method with optimistic-like updates that mitigates the impact of noise by incorporating an EMA of historic gradients in its update rule. We also explore a variation of this algorithm that incorporates momentum. Although we do not provide convergence guarantees, our experiments on stochastic games show that Omega outperforms the optimistic gradient method when applied to linear players.
2023-07-01
ICML.cc/2023/Workshop/LXAI_Regular_Deadline (oral)
doi.org
openreview.net
Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data
Baptiste Bauvin
Cécile Capponi
Florence Clerc
Pascal Germain
Sokol Koço
J. Corbeil
2023-07-01
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (published)
proceedings.mlr.press
proceedings.mlr.press
Continuous cutting plane algorithms in integer programming
Didier Chételat
Andrea Lodi
2023-06-30
Operations Research Letters (published)
doi.org
arxiv.org
Curriculum frameworks and educational programs in artificial intelligence for medical students, residents, and practicing physicians: a scoping review protocol.
Raymond Tolentino
Ashkan Baradaran
Genevieve Gore
Pierre Pluye
S. A. Rahimi
OBJECTIVE The aim of this scoping review is to synthesize knowledge from the literature on curriculum frameworks and current educational pro… (see more)grams that focus on the teaching and learning of artificial intelligence (AI) for medical students, residents, and practicing physicians. INTRODUCTION To advance the implementation of AI in clinical practice, physicians need to have a better understanding of AI and how to use it within clinical practice. Consequently, medical education must introduce AI topics and concepts into the curriculum. Curriculum frameworks are educational road maps to teaching and learning. Therefore, any existing AI curriculum frameworks must be reviewed and, if none exist, such a framework must be developed. INCLUSION CRITERIA This review will include articles that describe curriculum frameworks for teaching and learning AI in medicine, irrespective of country. All types of articles and study designs will be included, except conference abstracts and protocols. METHODS This review will follow the JBI methodology for scoping reviews. Keywords will first be identified from relevant articles. Another search will then be conducted using the identified keywords and index terms. The following databases will be searched: MEDLINE (Ovid), Embase (Ovid), Cochrane Central Register of Controlled Trials (CENTRAL), CINAHL (EBSCOhost), and Scopus. Gray literature will also be searched. Articles will be limited to the English and French languages, commencing from the year 2000. The reference lists of all included articles will be screened for additional articles. Data will then be extracted from included articles and the results will be presented in a table.
2023-06-30
JBI Evidence Synthesis (published)
doi.org
Dev2vec: Representing Domain Expertise of Developers in an Embedding Space
Arghavan Moradi Dakhel
Michel C. Desmarais
Foutse Khomh
2023-06-30
Information and Software Technology (published)
doi.org
arxiv.org
A double-oracle, logic-based Benders decomposition approach to solve the K-adaptability problem
A. Ghahtarani
A. Saif
A. Ghasemi
Erick Delage
2023-06-30
Computers & Operations Research (published)
doi.org
arxiv.org
FairPrism: Evaluating Fairness-Related Harms in Text Generation
Eve Fleisig
Aubrie Amstutz
Chad Atalla
Su Lin Blodgett
Hal Daumé III
A.R. Olteanu
Emily Sheng
Dan Vann
Hanna Wallach
It is critical to measure and mitigate fairness-related harms caused by AI text generation systems, including stereotyping and demeaning har… (see more)ms. To that end, we introduce FairPrism, a dataset of 5,000 examples of AI-generated English text with detailed human annotations covering a diverse set of harms relating to gender and sexuality. FairPrism aims to address several limitations of existing datasets for measuring and mitigating fairness-related harms, including improved transparency, clearer specification of dataset coverage, and accounting for annotator disagreement and harms that are context-dependent. FairPrism’s annotations include the extent of stereotyping and demeaning harms, the demographic groups targeted, and appropriateness for different applications. The annotations also include specific harms that occur in interactive contexts and harms that raise normative concerns when the “speaker” is an AI system. Due to its precision and granularity, FairPrism can be used to diagnose (1) the types of fairness-related harms that AI text generation systems cause, and (2) the potential limitations of mitigation methods, both of which we illustrate through case studies. Finally, the process we followed to develop FairPrism offers a recipe for building improved datasets for measuring and mitigating harms caused by AI systems.
2023-06-30
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (published)
doi.org
Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
Zhong Zhang
Bang Liu
Junming Shao
2023-06-30
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (published)
doi.org
arxiv.org
Genesis, modelling and methodological remedies to autism heterogeneity
Juliette Rabot
Eya‐mist Rødgaard
Ridha Joober
Guillaume Dumas
Danilo Bzdok
Boris C Bernhardt
Sébastien Jacquemont
Laurent Mottron
2023-06-30
Neuroscience & Biobehavioral Reviews (published)
doi.org
Imaging of Neck Nodes in Head and Neck Cancers – a Comprehensive Update
K. Bhattacharya
A. Mahajan
R. Vaish
S. Rane
S. Shukla
A.K. D'Cruz
2023-06-30
Clinical Oncology (published)
doi.org
MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages
Cheikh M. Bamba Dione
David Ifeoluwa Adelani
Peter Nabende
Jesujoba O. Alabi
Thapelo Sindane
Happy Buzaaba
Shamsuddeen Hassan Muhammad
Chris Chinenye Emezue
Perez Ogayo
Anuoluwapo Aremu
Catherine Gitau
Derguene Mbaye
Jonathan Mukiibi
Blessing Sibanda
Bonaventure F. P. Dossou
Andiswa Bukula
Rooweither Mabuya
Allahsera Auguste Tapo
Edwin Munkoh-Buabeng
Victoire Memdjokam Koagne … (see 24 more)
Fatoumata Ouoba Kabore
Amelia Taylor
Godson Kalipe
Tebogo Macucwa
Vukosi Marivate
Tajuddeen Gwadabe
Elvis Tchiaze Mboning
Ikechukwu Onyenwe
Gratien Atindogbe
Tolulope Anu Adelani
Idris Akinade
Olanrewaju Samuel
Marien Nahimana
Théogène Musabeyezu
Emile Niyomutabazi
Ester Chimhenga
Kudzai Gotosa
Patrick Mizha
Apelete Agbolo
Seydou Traore
Chinedu Uchechukwu
Aliyu Yusuf
Muhammad Abdullahi
Dietrich Klakow
In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss th… (see more)e challenges in annotating POS for these languages using the UD (universal dependencies) guidelines. We conducted extensive POS baseline experiments using conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in UD. Evaluating on the MasakhaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with cross-lingual parameter-efficient fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems more effective for POS tagging in unseen languages.
2023-06-30
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (published)
doi.org
arxiv.org