Publications

Determinants of pleiotropy and monotonic gene dosage responses across human traits
Sayeh Kazem
Kuldeep Kumar
Guillaume Huguet
Josephine Mollon
Thomas Renne
Laura M. Schultz
Emma E.M. Knowles
Worrawat Engchuan
Omar Shanta
Bhooma Thiruvahindrapuram
Jeffrey R. MacDonald
Celia M. T. Greenwood
Stephen W. Scherer
Laura Almasy
Jonathan Sebat
David C. Glahn
Guillaume Dumas
Sébastien Jacquemont
While pleiotropic effects of gene dosage are of particular relevance for comorbidities observed in the developmental pediatric and psychiatr… (see more)ic clinic, the biological processes underlying such pleiotropy remain unknown. We developed a new functional burden analysis (FunBurd) to investigate all CNVs, genome-wide, beyond well-studied recurrent CNVs. In ~500,000 UK-Biobank participants, we tested the association between 43 traits and CNVs disrupting 172 tissue or cell-type gene-sets. CNVs affected all traits. Pleiotropy was correlated with genetic constraint and was higher in the brain compared to non-brain functions, even after normalizing for genetic constraint. The levels of pleiotropy, measured by burden correlation, were similar in deletions and loss-of-function SNVs and higher compared to common variants and duplications. Gene sets under high genetic constraint showed less monotonic gene dosage responses across traits. Even in the absence of a monotonic response, we observed a negative correlation between deletion and duplication effect sizes across most traits. Overall, functional gene sets are preferentially associated with a given trait when either deleted or duplicated, but rarely both.
2025-11-18
Research Square (preprint)
doi.org
Risk factors for catastrophic healthcare expenditure and high economic burden for children with anorectal malformations in Southwestern Uganda
Felix Oyania
Caroline Q. Stephens
Sarah Ullrich
Amy M. Shui
Meera Kotagal
Godfrey Zari Rukundo
Joseph Ngonzi
Ava Yap
Francis Bajunirwe
Dan Poenaru
Doruk Ozgediz
2025-11-18
International Journal for Equity in Health (published)
doi.org
Towards an informational account of interpersonal coordination
Edoardo Chidichimo
Andrea Luppi
Pedro A. Mediano
Victoria Leong
Guillaume Dumas
Andres Canales-Johnson
Richard A.I. Bethlehem

Human sociality is grounded in the dynamic coordination of individuals as they interact with one another. Indeed, interpersonal coordinat… (see more)ion on various levels—neural, behavioural, physiological, affective, linguistic—are hallmarks of successful social communication and cooperation. However, describing these complex, interdependent dynamics has been limited by current methodological approaches, owing to a restrictive repertoire of tools and the absence of a unified, standardised methodological framework. Here, we identify information theory, the mathematical theory of communication, as a particularly well-suited conceptual framework to address this shortfall, given its appropriate sensitivity to complex dynamics, including potential nonlinearity and higher-order interactions, and its data-driven, model-agnostic foundations. With deep roots in computational, cognitive, and systems neuroscience, the formal introduction of information-theoretic quantities and methods into the study of interpersonal coordination is perhaps overdue. This Perspective advances the case for a unified information-theoretic framework for the field while paving the path for a new generation of empirically testable, theoretically grounded research questions.

2025-11-16
Nature Reviews Neuroscience (published)
doi.org
Excitatory-Inhibitory Dynamics in Adaptive Decision-Making
Veronica Chelu
Doina Precup
2025-11-15
Lecture Notes in Computer Science (published)
doi.org
From Technical Excellence to Practical Adoption: Lessons Learned Building an ML-Enhanced Trace Analysis Tool
Kaveh Shahedi
Matthew Khouzam
Heng Li
Maxime Lamothe
Foutse Khomh
2025-11-15
2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE) (published)
doi.org
arxiv.org
Higher Order Transformers: Efficient Attention Mechanism for Tensor Structured Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
Transformers are now ubiquitous for sequence modeling tasks, but their extension to multi-dimensional data remains a challenge due to the qu… (see more)adratic cost of the attention mechanism. In this paper, we propose Higher-Order Transformers (HOT), a novel architecture designed to efficiently process data with more than two axes, i.e. higher-order tensors. To address the computational challenges associated with high-order tensor attention, we introduce a novel Kronecker factorized attention mechanism that reduces the attention cost to quadratic in each axis' dimension, rather than quadratic in the total size of the input tensor. To further enhance efficiency, HOT leverages kernelized attention, reducing the complexity to linear. This strategy maintains the model's expressiveness while enabling scalable attention computation. We validate the effectiveness of HOT on two high-dimensional tasks, including multivariate time series forecasting, and 3D medical image classification. Experimental results demonstrate that HOT achieves competitive performance while significantly improving computational efficiency, showcasing its potential for tackling a wide range of complex, multi-dimensional data.
2025-11-15
TMLR (accepted)
doi.org
openreview.net
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
Xi Xiao
Zhuxuanzi Wang
Mingqiao Mo
Chen Liu
Chenrui Ma
Yanshu Li
Smita Krishnaswamy
Xiao Wang
Tianyang Wang
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve st… (see more)rong in-domain accuracy but require costly re-annotation for new environments, while standard self-supervised methods capture generic features and remain vulnerable to domain shift. We propose \ours, a self-supervised framework that \emph{visually probes} target domains without labels. \ours introduces a Self-supervised Prompt Enhancement Module (SPEM), which derives defect-aware prompts from unlabeled target data to guide a frozen ViT backbone, and a Domain-Aware Prompt Alignment (DAPA) objective, which aligns prompt-conditioned source and target representations. Experiments on four challenging benchmarks show that \ours consistently outperforms strong supervised, self-supervised, and adaptation baselines, achieving robust zero-shot transfer, improved resilience to domain variations, and high data efficiency in few-shot adaptation. These results highlight self-supervised prompting as a practical direction for building scalable and adaptive visual inspection systems. Source code is publicly available: https://github.com/xixiaouab/PROBE/tree/main
2025-11-15
ArXiv (preprint)
doi.org
arxiv.org
Graph topological property recovery with heat and wave dynamics-based features on graphs
Dhananjay Bhaskar
Yanlei Zhang
Charles Xu
Xingzhi Sun
Oluwadamilola Fasina
Arman Afrasiyabi
Siddharth Viswanath
Guy Wolf
Maximilian Nickel
Michael Perlmutter
Smita Krishnaswamy
2025-11-12
TAG-DS/2025/Conference (spotlight)
doi.org
openreview.net
MultiTab: A Scalable Foundation for Multitask Learning on Tabular Data
Dimitrios Sinodinos
Jack Yi Wei
Narges Armanfard
Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datase… (see more)ts grow and span multiple related targets, there is an increasing need to exploit shared task information for improved multitask generalization. Multitask learning (MTL) has emerged as a powerful way to improve generalization and efficiency, yet most existing work focuses narrowly on large-scale recommendation systems, leaving its potential in broader tabular domains largely underexplored. Also, existing MTL approaches for tabular data predominantly rely on multi-layer perceptron-based backbones, which struggle to capture complex feature interactions and often fail to scale when data is abundant, a limitation that transformer architectures have overcome in other domains. Motivated by this, we introduce MultiTab-Net, the first multitask transformer architecture specifically designed for large tabular data. MultiTab-Net employs a novel multitask masked-attention mechanism that dynamically models feature-feature dependencies while mitigating task competition. Through extensive experiments, we show that MultiTab-Net consistently achieves higher multitask gain than existing MTL architectures and single-task transformers across diverse domains including large-scale recommendation data, census-like socioeconomic data, and physics datasets, spanning a wide range of task counts, task types, and feature modalities. In addition, we contribute MultiTab-Bench, a generalized multitask synthetic dataset generator that enables systematic evaluation of multitask dynamics by tuning task count, task correlations, and relative task complexity. Our code is publicly available at https://github.com/Armanfard-Lab/MultiTab.
2025-11-12
ArXiv (preprint)
doi.org
arxiv.org
The Geometry and Topology of Modular Addition Representations
Gabriela Moisescu-Pareja
Gavin McCracken
Harley Wiltzer
Colin Daniels
Vincent Létourneau
Doina Precup
Jonathan Love
The Clock and Pizza interpretations, associated with neural architectures differing in either uniform or learnable attention, were introduce… (see more)d to argue that different architectural designs can yield distinct circuits for modular addition. Applying geometric and topological analyses to learned representations, we show that this is not the case: Clock and Pizza circuits are topologically and geometrically equivalent and are thus equivalent representations.
2025-11-12
TAG-DS/2025/Conference (poster)
openreview.net
openreview.net
A HOT Dataset: 150,000 Buildings for HVAC Operations Transfer Research
Anaïs Berkes
Yoshua Bengio
David Rolnick
Donna Vakalis
2025-11-10
Proceedings of the 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (published)
doi.org
A HOT Dataset: 150,000 Buildings for HVAC Operations Transfer Research
Anaïs Berkes
Yoshua Bengio
David Rolnick
Donna Vakalis
About 12% of global energy consumption is attributable to heating, ventilation, and air conditioning (HVAC) systems in buildings [11]. Machi… (see more)ne learning-based intelligent HVAC control offers significant energy efficiency potential, but progress is constrained by limited data for training and evaluating performance across different kinds of buildings. Existing datasets primarily target energy prediction rather than control applications, forcing studies to rely on limited building sets or single-variable perturbations that fail to capture real-world complexity. We present HOT (HVAC Operations Transfer), the first large-scale open-source dataset purpose-built for research into transfer learning in building control. HOT contains 159,744 unique building-weather combinations with systematic variations across envelope properties, occupancy patterns, and climate conditions spanning all 19 ASHRAE climate zones across 76 global locations. We formalise a comprehensive similarity-based framework with quantitative metrics for assessing transfer feasibility between source and target buildings across multiple context dimensions. Our key contributions: (1) a large-scale, open dataset and tooling enabling systematic, multi-variable transfer studies across 19 climate zones; (2) a quantitative similarity framework spanning geometry, thermal, climate, and function; and (3) zero-shot climate transfer experiments showing why realistic context variation matters for HVAC control.
2025-11-10
ACM Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (published)
doi.org