Publications

Dissociable influences of maternal vs paternal Alzheimer’s risk on neurocognitive and cardiovascular health in men and women
Chloé Savignac
Frederic St‐Onge
Sylvia Villeneuve
AmanPreet Badhwar
Sarah A Gagliano Taliun
Sali Farhan
Maiya R. Geddes
Yasser Iturria Medina
Judes Poirier
R. Nathan Spreng
Danilo Bzdok
We uncovered IPs of AD susceptibility differently expressed in male and female probands and affected by the diagnosed parent’s sex. Matern… (voir plus)al inheritance highlighted memory performance in both sexes, whereas paternal inheritance was particularly linked to cardiovascular health in males. The inheritance of the IPs was reflected in the brain structure at both superficial and deeper layers of the cortex. As the first study of its kind, our cross‐generational analysis of matri‐ vs. patrilinear AD risk bridges the epidemiological and clinical literature by leveraging the power of ∼1,000 patient visits. Our completely data‐driven framework ultimately dissociated phenotypes of maternal and paternal AD risk single‐handedly expressed in male and female probands.
2023-11-30
Alzheimer's & Dementia (publié)
doi.org
EpiK-Eval: Evaluation for Language Models as Epistemic Models
Gabriele Prato
Jerry Huang
Prasanna Parthasarathi
Shagun Sodhani
A. Chandar
In the age of artificial intelligence, the role of large language models (LLMs) is becoming increasingly central. Despite their growing prev… (voir plus)alence, their capacity to consolidate knowledge from different training documents—a crucial ability in numerous applications—remains unexplored. This paper presents the first study examining the capability of LLMs to effectively combine such information within their parameter space. We introduce EpiK-Eval, a novel question-answering benchmark tailored to evaluate LLMs' proficiency in formulating a coherent and consistent knowledge representation from segmented narratives. Evaluations across various LLMs reveal significant weaknesses in this domain. We contend that these shortcomings stem from the intrinsic nature of prevailing training objectives. Consequently, we advocate for refining the approach towards knowledge consolidation, as it harbors the potential to dramatically improve their overall effectiveness and performance. The findings from this study offer insights for developing more robust and reliable LLMs. Our code and benchmark are available at https://github.com/chandar-lab/EpiK-Eval
2023-11-30
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (publié)
doi.org
openreview.net
Fast-Converging Simulated Annealing for Ising Models Based on Integral Stochastic Computing
Naoya Onizawa
Kota Katsuki
Duckgyu Shin
Warren J. Gross
Takahiro Hanyu
Probabilistic bits (p-bits) have recently been presented as a spin (basic computing element) for the simulated annealing (SA) of Ising model… (voir plus)s. In this brief, we introduce fast-converging SA based on p-bits designed using integral stochastic computing. The stochastic implementation approximates a p-bit function, which can search for a solution to a combinatorial optimization problem at lower energy than conventional p-bits. Searching around the global minimum energy can increase the probability of finding a solution. The proposed stochastic computing-based SA method is compared with conventional SA and quantum annealing (QA) with a D-Wave Two quantum annealer on the traveling salesman, maximum cut (MAX-CUT), and graph isomorphism (GI) problems. The proposed method achieves a convergence speed a few orders of magnitude faster while dealing with an order of magnitude larger number of spins than the other methods.
2023-11-30
IEEE Transactions on Neural Networks and Learning Systems (publié)
doi.org
From physics to sentience: Deciphering the semantics of the free-energy principle and evaluating its claims: Comment on "Path integrals, particular kinds, and strange things" by Karl Friston et al.
Zahra Sheikhbahaee
Adam Safron
Casper Hesp
Guillaume Dumas
2023-11-30
Physics of Life Reviews (publié)
doi.org
arxiv.org
Gene-metabolite annotation with shortest reactional distance enhances metabolite genome-wide association studies results
Cantin Baron
Sarah Cherkaoui
Sandra Therrien-Laperriere
Yann Ilboudo
Raphaël Poujol
Pamela Mehanna
Melanie E. Garrett
Marilyn J. Telen
Allison E. Ashley-Koch
Pablo Bartolucci
John D. Rioux
Guillaume Lettre
Christine Des Rosiers
Matthieu Ruiz
Julie G. Hussin
Studies combining metabolomics and genetics, known as metabolite genome-wide association studies (mGWAS), have provided valuable insights in… (voir plus)to our understanding of the genetic control of metabolite levels. However, the biological interpretation of these associations remains challenging due to a lack of existing tools to annotate mGWAS gene-metabolite pairs beyond the use of conservative statistical significance threshold. Here, we computed the shortest reactional distance (SRD) based on the curated knowledge of the KEGG database to explore its utility in enhancing the biological interpretation of results from three independent mGWAS, including a case study on sickle cell disease patients. Results show that, in reported mGWAS pairs, there is an excess of small SRD values and that SRD values and p-values significantly correlate, even beyond the standard conservative thresholds. The added-value of SRD annotation is shown for identification of potential false negative hits, exemplified by the finding of gene-metabolite associations with SRD ≤1 that did not reach standard genome-wide significance cut-off. The wider use of this statistic as an mGWAS annotation would prevent the exclusion of biologically relevant associations and can also identify errors or gaps in current metabolic pathway databases. Our findings highlight the SRD metric as an objective, quantitative and easy-to-compute annotation for gene-metabolite pairs that can be used to integrate statistical evidence to biological networks.
2023-11-30
iScience (publié)
doi.org
Growth of TiO2 single crystals by the Verneuil method at different gas flow ratio
Xudong Liu
Hanshu Ma
Wei Wang
Yongqi Hu
Xudong Sun
2023-11-30
Journal of Crystal Growth (publié)
doi.org
Large language models: What could they do for neurology?
Guillaume Lajoie
2023-11-30
Journal of the Neurological Sciences (publié)
doi.org
A large-scale exploratory study of android sports apps in the google play store
Bhagya Chembakottu
Heng Li
Foutse Khomh
2023-11-30
Information and Software Technology (publié)
doi.org
arxiv.org
McGill BabyLM Shared Task Submission: The Effects of Data Formatting and Structural Biases
Ziling Cheng
Rahul Aralikatte
Ian Porada
Cesare Spinoso-Di Piano
Jackie CK Cheung
In this study, we describe our submission to the 2023 BabyLM shared-task's strict-small track.Our findings demonstrate the feasibility of tr… (voir plus)aining high-performing models within the constraints of limited data, computational resources, and time.We provide evidence that the formatting of input can significantly impact downstream performance.Furthermore, the induction of structural biases into the models through the use of part-of-speech trees yields modest benefits.Our most successful model achieves 79% on the BLiMP evaluations and 72% on the SuperGLUE evaluations.
2023-11-30
BabyLM Challenge @ Conference on Computational Natural Language Learning (publié)
doi.org
McGill BabyLM Shared Task Submission: The Effects of Data Formatting and Structural Biases
Ziling Cheng
Rahul Aralikatte
Ian Porada
Cesare Spinoso-Di Piano
Jackie Chi Kit Cheung
In this study, we describe our submission to the 2023 BabyLM shared-task’s strict-small track. Our findings demonstrate the feasibility of… (voir plus) training high-performing models within the constraints of limited data, computational resources, and time. We provide evidence that the formatting of input can significantly impact downstream performance. Furthermore, the induction of structural biases into the models through the use of part-of-speech trees yields modest benefits. Our most successful model achieves 79% on the BLiMP evaluations and 72% on the SuperGLUE evaluations. All models trained during this study can be found at https://huggingface . co/mcgill-babylm . 12
2023-11-30
Conference on Computational Natural Language Learning (publié)
doi.org
Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models
Amirhossein Kazemnejad
Mehdi Rezagholizadeh
Prasanna Parthasarathi
Sarath Chandar
While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge, it remains unclear how much of this par… (voir plus)ametric knowledge is actually usable in performing downstream tasks. We propose a systematic framework to measure parametric knowledge utilization in PLMs. Our framework first extracts knowledge from a PLM's parameters and subsequently constructs a downstream task around this extracted knowledge. Performance on this task thus depends exclusively on utilizing the model's possessed knowledge, avoiding confounding factors like insufficient signal. As an instantiation, we study factual knowledge of PLMs and measure utilization across 125M to 13B parameter PLMs. We observe that: (1) PLMs exhibit two gaps - in acquired vs. utilized knowledge, (2) they show limited robustness in utilizing knowledge under distribution shifts, and (3) larger models close the acquired knowledge gap but the utilized knowledge gap remains. Overall, our study provides insights into PLMs' capabilities beyond their acquired knowledge.
2023-11-30
Findings of the Association for Computational Linguistics: EMNLP 2023 (publié)
doi.org
openreview.net
Predictive inference for travel time on transportation networks
Mohamad Elmasri
Aurélie Labbe
Denis Larocque
Laurent Charlin
2023-11-30
The Annals of Applied Statistics (publié)
doi.org
arxiv.org