Publications

Aperiodic brain activity and response to anesthesia vary in disorders of consciousness
Charlotte Maschke
Catherine Duclos
Adrian M. Owen
Karim Jerbi
Stefanie Blain‐Moraes
The analysis of human EEG has traditionally focused on oscillatory power, which is characterized by peaks above an aperiodic component in th… (voir plus)e power spectral density. This study investigates the aperiodic EEG component of individuals in a disorder of consciousness (DOC); how it changes in response to exposure to anesthesia; and how it relates to the brain’s information richness and criticality. High-density EEG was recorded from 43 individuals in a DOC, with 16 of these individuals undergoing a protocol of propofol anesthesia. The aperiodic component was defined by the spectral slope of the power spectral density. Our results demonstrate that the EEG aperiodic component is more informative about the participants’ level of consciousness than the oscillatory component. Importantly, the pharmacologically induced change in the spectral slope from 30-45 Hz positively correlated with individual’s pre-anesthetic level of consciousness. The pharmacologically induced loss of information-richness and criticality was associated with individual’s pre-anesthetic aperiodic component. During exposure to anesthesia, the aperiodic component was correlated with 3-month recovery status for individuals with DOC. The aperiodic EEG component has been historically neglected; this research highlights the necessity of considering this measure for the assessment of individuals in DOC and future research that seeks to understand the neurophysiological underpinnings of consciousness.
2022-12-31
NeuroImage (publié)
doi.org
ArK: Augmented Reality with Knowledge Emergent Infrastructure
Qiuyuan Huang
J. Park
Abhinav Gupta
Pan Lu
Paul N. Bennett
Ran Gong
Subhojit Som
Baolin Peng
Owais Khan Mohammed
Christopher Pal
Yejin Choi
Jianfeng Gao
Despite the growing adoption of mixed reality and interactive AI, it remains challenging to generate high-quality 2D/3D scenes in unseen env… (voir plus)ironments. Typically, an AI agent requires collecting extensive training data for every new task, which can be costly or impossible for many domains. In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e.g., GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in physical or virtual worlds. Central to our approach is the interactive emerging mechanism, dubbed Augmented Reality with Knowledge Emergent Infrastructure (ArK) , which leverages knowledge-memory to generate scenes in unseen physical worlds and virtual reality environments. The knowledge interactive emergent ability (Figure 1) is demonstrated through i) micro-action of cross-modality : in multi-modality models to collect a large amount of relevant knowledge-memory data for each interaction task (e.g., unseen scene understanding) from the physical reality; and ii) macro-behavior of reality-agnostic : in mix-reality environments to improve interactions that tailor to different characterized roles, target variables, collaborative information, and so on. We validate ArK’s effectiveness in scene generation and editing tasks and show that our ArK approach, combined with large foundation models, significantly improves the quality of generated 2D/3D scenes, highlighting its potential in applications such as metaverse and gaming simulation.
2022-12-31
(publié)
www.semanticscholar.org
Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images
Yufei Cui
Ziquan Liu
Xiangyu Liu
Xue Liu
Cong Wang
Tei-Wei Kuo
Chun Jason Xue
Antoni B. Chan
Multiple instance learning (MIL) is a popular weakly-supervised learning model on the whole slide image (WSI) for AI-assisted pathology diag… (voir plus)nosis. The recent advance in attention-based MIL allows the model to find its region-of-interest (ROI) for interpretation by learning the attention weights for image patches of WSI slides. However, we empirically find that the interpretability of some related methods is either untrustworthy as the principle of MIL is violated or unsatisfactory as the high-attention regions are not consistent with experts’ annotations. In this paper, we propose Bayes-MIL to address the problem from a probabilistic perspective. The induced patch-level uncertainty is proposed as a new measure of MIL interpretability, which outperforms previous methods in matching doctors annotations. We design a slide-dependent patch regularizer (SDPR) for the attention, imposing constraints derived from the MIL assumption, on the attention distribution. SDPR explicitly constrains the model to generate correct attention values. The spatial information is further encoded by an approximate convolutional conditional random field (CRF), for better interpretability. Experimental results show Bayes-MIL outperforms the related methods in patch-level and slide-level metrics and provides much better interpretable ROI on several large-scale WSI datasets.
2022-12-31
ICLR (publié)
dblp.uni-trier.de
Benchmarking Graph Neural Networks
Vijay Prakash Dwivedi
Chaitanya K. Joshi
Thomas Laurent
Anh Tuan Luu
Yoshua Bengio
Xavier Bresson
2022-12-31
J. Mach. Learn. Res. (publié)
arxiv.org
arxiv.org
Benchmarking State-Merging Algorithms for Learning Regular Languages.
Adil Soubki
Jeffrey Heinz
François Coste
Faissal Ouardi
Guillaume Rabusseau
2022-12-31
International Conference on Graphics and Interaction (publié)
dblp.uni-trier.de
Best-Case Retrieval Evaluation: Improving the Sensitivity of Reciprocal Rank with Lexicographic Precision
Fernando Diaz
Across a variety of ranking tasks, researchers use reciprocal rank to measure the effectiveness for users interested in exactly one relevant… (voir plus) item. Despite its widespread use, evidence suggests that reciprocal rank is brittle when discriminating between systems. This brittleness, in turn, is compounded in modern evaluation settings where current, high-precision systems may be difficult to distinguish. We address the lack of sensitivity of reciprocal rank by introducing and connecting it to the concept of best-case retrieval, an evaluation method focusing on assessing the quality of a ranking for the most satisfied possible user across possible recall requirements. This perspective allows us to generalize reciprocal rank and define a new preference-based evaluation we call lexicographic precision or lexiprecision. By mathematical construction, we ensure that lexiprecision preserves differences detected by reciprocal rank, while empirically improving sensitivity and robustness across a broad set of retrieval and recommendation tasks.
2022-12-31
EVIA (publié)
doi.org
arxiv.org
Bringing language to dynamic brain states: the default network dominates neural responses to evolving movie stories
Enning Yang
Filip Milisav
Jakub Kopal
Avram J. Holmes
Georgios D. Mitsis
Bratislav Misic
Emily S. Finn
Danilo Bzdok
Naturalistic neuroscience opened the door to new insights into neural circuits that serve real-world dynamic perception. Such studies have o… (voir plus)ften neglected the rich texture of the movie narrative itself, but semantic content can be used to contextualize the induced neural responses. Here, we translated natural language processing tools from machine learning to characterize brain states estimated from hidden Markov models. Our analytical strategy allowed pitting shallow unimodal against the deep associative brain network layers in explaining how semantic content of the movie links to observed neural activity. Pooling information across >53,000 brain image time points watching Forrest Gump, we could show that distinct dynamic brain states capture unique semantic facets along the unfolding movie narrative. The spatiotemporal dynamics of brain states explicitly captured subject-level responses throughout the brain network hierarchy. Across all analyses, the default network was most intimately linked to semantic information integration, and this neural system switched online for longest durations during movie watching. Further, we identified and described two mechanisms of how the default network liaises dynamically with microanatomically defined subregion partners: the amygdala and the hippocampus. Our study thus unlocks the potential of natural language processing to explore neural processes in everyday life situations that engage key aspects of conscious awareness.
2022-12-31
McGill University (publié)
doi.org
Bringing language to dynamic brain states: the default network dominates neural responses to evolving movie stories
Enning Yang
Filip Milisav
Jakub Kopal
Avram J. Holmes
Georgios D. Mitsis
Bratislav Misic
Emily S. Finn
Danilo Bzdok
Naturalistic neuroscience opened the door to new insights into neural circuits that serve real-world dynamic perception. Such studies have o… (voir plus)ften neglected the rich texture of the movie narrative itself, but semantic content can be used to contextualize the induced neural responses. Here, we translated natural language processing tools from machine learning to characterize brain states estimated from hidden Markov models. Our analytical strategy allowed pitting shallow unimodal against the deep associative brain network layers in explaining how semantic content of the movie links to observed neural activity. Pooling information across >53,000 brain image time points watching Forrest Gump, we could show that distinct dynamic brain states capture unique semantic facets along the unfolding movie narrative. The spatiotemporal dynamics of brain states explicitly captured subject-level responses throughout the brain network hierarchy. Across all analyses, the default network was most intimately linked to semantic information integration, and this neural system switched online for longest durations during movie watching. Further, we identified and described two mechanisms of how the default network liaises dynamically with microanatomically defined subregion partners: the amygdala and the hippocampus. Our study thus unlocks the potential of natural language processing to explore neural processes in everyday life situations that engage key aspects of conscious awareness.
2022-12-31
McGill University (publié)
doi.org
Can Ensembling Pre-processing Algorithms Lead to Better Machine Learning Fairness?
Khaled Badran
Pierre-Olivier Côté
Amanda Kolopanis
Rached Bouchoucha
Antonio Collante
Diego Elias Costa
Emad Shihab
Foutse Khomh
As machine learning (ML) systems get adopted in more critical areas, it has become increasingly crucial to address the bias that could occur… (voir plus) in these systems. Several fairness pre-processing algorithms are available to alleviate implicit biases during model training. These algorithms employ different concepts of fairness, often leading to conflicting strategies with consequential trade-offs between fairness and accuracy. In this work, we evaluate three popular fairness pre-processing algorithms and investigate the potential for combining all algorithms into a more robust pre-processing ensemble. We report on lessons learned that can help practitioners better select fairness algorithms for their models.
2022-12-31
Computer (publié)
doi.org
arxiv.org
Can AI Read the Minds of Corporate Executives?
Nicolas Chapados
Zhenzhen Fan
Ruslan Goyenko
Issam Hadj Laradji
Fred Liu
Chengyu Zhang
2022-12-31
SSRN Electronic Journal (publié)
doi.org
A circulating proteome-informed prognostic model of COVID-19 disease activity that relies on 1 routinely available clinical laboratories 2
William Ma
Antoine Soulé
Karine Tremblay
Simon Rousseau
Amin Emad
Abstract
2022-12-31
(publié)
www.semanticscholar.org
Combinatorial Optimization and Reasoning with Graph Neural Networks
Quentin Cappart
Didier Chételat
Elias B. Khalil
Andrea Lodi
Christopher Morris
Petar Veličković
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused … (voir plus)on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning, especially graph neural networks (GNNs), as a key building block for combinatorial tasks, either directly as solvers or by enhancing exact solvers. The inductive bias of GNNs effectively encodes combinatorial and relational input due to their invariance to permutations and awareness of input sparsity. This paper presents a conceptual review of recent key advancements in this emerging field, aiming at optimization and machine learning researchers.
2022-12-31
Journal of Machine Learning Research (publié)
doi.org
arxiv.org