Publications

Deep Generative Sampling in the Dual Divergence Space: A Data-efficient&Interpretative Approach for Generative AI
Sahil Garg
Anderson Schneider
Anant Raj
Kashif Rasul
Yuriy Nevmyvaka
S. Gopal
Amit Dhurandhar
Guillermo A. Cecchi
Irina Rish
Building on the remarkable achievements in generative sampling of natural images, we propose an innovative challenge, potentially overly amb… (see more)itious, which involves generating samples of entire multivariate time series that resemble images. However, the statistical challenge lies in the small sample size, sometimes consisting of a few hundred subjects. This issue is especially problematic for deep generative models that follow the conventional approach of generating samples from a canonical distribution and then decoding or denoising them to match the true data distribution. In contrast, our method is grounded in information theory and aims to implicitly characterize the distribution of images, particularly the (global and local) dependency structure between pixels. We achieve this by empirically estimating its KL-divergence in the dual form with respect to the respective marginal distribution. This enables us to perform generative sampling directly in the optimized 1-D dual divergence space. Specifically, in the dual space, training samples representing the data distribution are embedded in the form of various clusters between two end points. In theory, any sample embedded between those two end points is in-distribution w.r.t. the data distribution. Our key idea for generating novel samples of images is to interpolate between the clusters via a walk as per gradients of the dual function w.r.t. the data dimensions. In addition to the data efficiency gained from direct sampling, we propose an algorithm that offers a significant reduction in sample complexity for estimating the divergence of the data distribution with respect to the marginal distribution. We provide strong theoretical guarantees along with an extensive empirical evaluation using many real-world datasets from diverse domains, establishing the superiority of our approach w.r.t. state-of-the-art deep learning methods.
2024-04-09
ArXiv (preprint)
doi.org
arxiv.org
AI healthcare research: Pioneering iSMART Lab
Narges Armanfard
Dr Narges Armanfard, Professor, talks us through the AI healthcare research at McGill University which is spearheading a groundbreaking init… (see more)iative – the iSMART Lab. Access to high-quality healthcare is not just a fundamental human right; it is the bedrock of our societal wellbeing, with the crucial roles played by doctors, nurses, and hospitals. Yet, healthcare systems globally face mounting challenges, particularly from aging populations. Dr Narges Armanfard, affiliated with McGill University and Mila Quebec AI Institute in Montreal, Canada, has spearheaded a groundbreaking initiative – the iSMART Lab. This laboratory represents a revolutionary leap into the future of healthcare, with its pioneering research in AI for health applications garnering significant attention. Renowned for its innovative integration of AI across diverse domains, iSMART Lab stands at the forefront of harnessing Artificial Intelligence to elevate and streamline health services.
2024-04-08
Open Access Government (published)
doi.org
Interpretable machine learning for finding intermediate-mass black holes
Mario Pasquato
PIERO TREVISAN
ABBAS ASKAR
Pablo Lemos
GAIA CARENINI
MICHELA MAPELLI
Yashar Hezaveh
Definitive evidence that globular clusters (GCs) host intermediate-mass black holes (IMBHs) is elusive. Machine learning (ML) models trained… (see more) on GC simulations can in principle predict IMBH host candidates based on observable features. This approach has two limitations: first, an accurate ML model is expected to be a black box due to complexity; second, despite our efforts to realistically simulate GCs, the simulation physics or initial conditions may fail to fully reflect reality. Therefore our training data may be biased, leading to a failure in generalization on observational data. Both the first issue -- explainability/interpretability -- and the second -- out of distribution generalization and fairness -- are active areas of research in ML. Here we employ techniques from these fields to address them: we use the anchors method to explain an XGBoost classifier; we also independently train a natively interpretable model using Certifiably Optimal RulE ListS (CORELS). The resulting model has a clear physical meaning, but loses some performance with respect to XGBoost. We evaluate potential candidates in real data based not only on classifier predictions but also on their similarity to the training data, measured by the likelihood of a kernel density estimation model. This measures the realism of our simulated data and mitigates the risk that our models may produce biased predictions by working in extrapolation. We apply our classifiers to real GCs, obtaining a predicted classification, a measure of the confidence of the prediction, an out-of-distribution flag, a local rule explaining the prediction of XGBoost and a global rule from CORELS.
2024-04-08
The Astrophysical Journal (published)
doi.org
arxiv.org
Learning Minimal NAP Specifications for Neural Network Verification
Chuqin Geng
Zhaoyue Wang
Haolin Ye
Saifei Liao
Xujie Si
Specifications play a crucial role in neural network verification. They define the precise input regions we aim to verify, typically represe… (see more)nted as L-infinity norm balls. While recent research suggests using neural activation patterns (NAPs) as specifications for verifying unseen test set data, it focuses on computing the most refined NAPs, often limited to very small regions in the input space. In this paper, we study the following problem: Given a neural network, find a minimal (coarsest) NAP that is sufficient for formal verification of the network's robustness. Finding the minimal NAP specification not only expands verifiable bounds but also provides insights into which neurons contribute to the model's robustness. To address this problem, we propose several exact and approximate approaches. Our exact approaches leverage the verification tool to find minimal NAP specifications in either a deterministic or statistical manner. Whereas the approximate methods efficiently estimate minimal NAPs using adversarial examples and local gradients, without making calls to the verification tool. This allows us to inspect potential causal links between neurons and the robustness of state-of-the-art neural networks, a task for which existing verification frameworks fail to scale. Our experimental results suggest that minimal NAP specifications require much smaller fractions of neurons compared to the most refined NAP specifications, yet they can significantly expand the verifiable boundaries to several orders of magnitude larger.
2024-04-05
ArXiv (preprint)
doi.org
arxiv.org
SAT-DIFF: A Tree Diffing Framework Using SAT Solving
Chuqin Geng
Haolin Ye
Yihan Zhang
Brigitte Pientka
Xujie Si
Computing differences between tree-structured data is a critical but challenging problem in software analysis. In this paper, we propose a n… (see more)ovel tree diffing approach called SatDiff, which reformulates the structural diffing problem into a MaxSAT problem. By encoding the necessary transformations from the source tree to the target tree, SatDiff generates correct, minimal, and type safe low-level edit scripts with formal guarantees. We then synthesize concise high-level edit scripts by effectively merging low-level edits in the appropriate topological order. Our empirical results demonstrate that SatDiff outperforms existing heuristic-based approaches by a significant margin in terms of conciseness while maintaining a reasonable runtime.
2024-04-05
ArXiv (preprint)
doi.org
arxiv.org
PopulAtion Parameter Averaging (PAPA)
Alexia Jolicoeur-Martineau
Emy Gervais
Kilian Fatras
Yang Zhang
Simon Lacoste-Julien
2024-04-04
TMLR (accepted)
doi.org
openreview.net
Applying Recurrent Neural Networks and Blocked Cross-Validation to Model Conventional Drinking Water Treatment Processes
Aleksandar Jakovljevic
Laurent Charlin
Benoit Barbeau
The jar test is the current standard method for predicting the performance of a conventional drinking water treatment (DWT) process and opti… (see more)mizing the coagulant dose. This test is time-consuming and requires human intervention, meaning it is infeasible for making continuous process predictions. As a potential alternative, we developed a machine learning (ML) model from historical DWT plant data that can operate continuously using real-time sensor data without human intervention for predicting clarified water turbidity 15 min in advance. We evaluated three types of models: multilayer perceptron (MLP), the long short-term memory (LSTM) recurrent neural network (RNN), and the gated recurrent unit (GRU) RNN. We also employed two training methodologies: the commonly used holdout method and the theoretically correct blocked cross-validation (BCV) method. We found that the RNN with GRU was the best model type overall and achieved a mean absolute error on an independent production set of as low as 0.044 NTU. We further found that models trained using BCV typically achieve errors equal to or lower than their counterparts trained using holdout. These results suggest that RNNs trained using BCV are superior for the development of ML models for DWT processes compared to those reported in earlier literature.
2024-04-03
Water (published)
doi.org
Assessing the emergence time of SARS-CoV-2 zoonotic spillover
Stéphane Samson
Étienne Lord
Vladimir Makarenkov
2024-04-03
PLoS ONE (published)
doi.org
Regulating advanced artificial agents
Michael K. Cohen
Noam Kolt
Yoshua Bengio
Gillian K. Hadfield
Stuart Russell
Governance frameworks should address the prospect of AI systems that cannot be safely tested
2024-04-03
Science (unknown)
doi.org
Enjeux juridiques propres au modèle émergent des patients accompagnateurs dans les milieux de soins au Québec
Léa Boutrouille
Catherine Régis
Marie-Pascale Pomey
2024-04-02
Journal du Droit de la Santé et de l’Assurance - Maladie (JDSAM) (published)
doi.org
Explainable artificial intelligence models for predicting risk of suicide using health administrative data in Quebec
Fatemeh Gholi Zadeh Kharrat
Christian Gagné
Alain Lesage
Geneviève Gariépy
Jean-François Pelletier
Camille Brousseau-Paradis
Louis Rochette
Eric Pelletier
Pascale Lévesque
Mada Mohammed
JianLi Wang
Suicide is a complex, multidimensional event, and a significant challenge for prevention globally. Artificial intelligence (AI) and machine … (see more)learning (ML) have emerged to harness large-scale datasets to enhance risk detection. In order to trust and act upon the predictions made with ML, more intuitive user interfaces must be validated. Thus, Interpretable AI is one of the crucial directions which could allow policy and decision makers to make reasonable and data-driven decisions that can ultimately lead to better mental health services planning and suicide prevention. This research aimed to develop sex-specific ML models for predicting the population risk of suicide and to interpret the models. Data were from the Quebec Integrated Chronic Disease Surveillance System (QICDSS), covering up to 98% of the population in the province of Quebec and containing data for over 20,000 suicides between 2002 and 2019. We employed a case-control study design. Individuals were considered cases if they were aged 15+ and had died from suicide between January 1st, 2002, and December 31st, 2019 (n = 18339). Controls were a random sample of 1% of the Quebec population aged 15+ of each year, who were alive on December 31st of each year, from 2002 to 2019 (n = 1,307,370). We included 103 features, including individual, programmatic, systemic, and community factors, measured up to five years prior to the suicide events. We trained and then validated the sex-specific predictive risk model using supervised ML algorithms, including Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Multilayer perceptron (MLP). We computed operating characteristics, including sensitivity, specificity, and Positive Predictive Value (PPV). We then generated receiver operating characteristic (ROC) curves to predict suicides and calibration measures. For interpretability, Shapley Additive Explanations (SHAP) was used with the global explanation to determine how much the input features contribute to the models’ output and the largest absolute coefficients. The best sensitivity was 0.38 with logistic regression for males and 0.47 with MLP for females; the XGBoost Classifier with 0.25 for males and 0.19 for females had the best precision (PPV). This study demonstrated the useful potential of explainable AI models as tools for decision-making and population-level suicide prevention actions. The ML models included individual, programmatic, systemic, and community levels variables available routinely to decision makers and planners in a public managed care system. Caution shall be exercised in the interpretation of variables associated in a predictive model since they are not causal, and other designs are required to establish the value of individual treatments. The next steps are to produce an intuitive user interface for decision makers, planners and other stakeholders like clinicians or representatives of families and people with live experience of suicidal behaviors or death by suicide. For example, how variations in the quality of local area primary care programs for depression or substance use disorders or increased in regional mental health and addiction budgets would lower suicide rates.
2024-04-02
PLOS ONE (published)
doi.org
Constrained Robotic Navigation on Preferred Terrains Using LLMs and Speech Instruction: Exploiting the Power of Adverbs
Faraz Lotfi
Farnoosh Faraji
Nikhil Kakodkar
Travis Manderson
David Meger
Gregory Dudek
2024-04-01
ArXiv (preprint)
doi.org
arxiv.org