Publications

Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks
Sitao Luan
Mingde Zhao
Xiao-Wen Chang
Doina Precup
2024-02-19
Complex Networks & Their Applications XII (publié)
doi.org
arxiv.org
When Do We Need Graph Neural Networks for Node Classification?
Sitao Luan
Chenqing Hua
Qincheng Lu
Jiaqi Zhu
Xiao-Wen Chang
Doina Precup
2024-02-19
Complex Networks & Their Applications XII (publié)
doi.org
arxiv.org
Virtual Reality for Pediatric Trauma Education - A Face and Content Validation Study
Fabio Botelho
Said Ashkar
Shreenik Kundu
TJ Matthews
Elena Guadgano
Jason Harley
Dan Poenaru
Purpose: Pediatric trauma is a leading cause of death and disability among children. While trauma education can improve these outcomes, it r… (voir plus)emains expensive and available only to a few providers worldwide. Innovative educational technologies like virtual reality (VR) can be key to democratizing trauma education. This study, therefore, evaluates the face and content validity of a VR platform designed to enhance pediatric trauma skills. Specifically, we seek to determine whether the platform effectively presents an injured child and comprehensively covers the essential tasks to successfully treat them within a trauma team. Methods: Physicians were invited to test a VR platform simulating a child with blunt head and truncal trauma. After the simulation, they filled out surveys assessing the face and content validity of the scenario, including their opinions on the realism, interaction, ease of use, and the educational content of the platform. Additionally, they completed a cybersickness questionnaire. Demographic data were also collected, including age, gender, country of medical education, and previous experience with VR. A descriptive analysis was performed. Results: Eleven physicians graduated from eight different countries tested the VR platform. Most (87%) found it valuable, and 81% preferred using it over high-fidelity mannequins for training purposes. The platform received more favorable evaluations for non-technical skills training (median: 5, IQR: 5.0 to 5.0) than for technical skills (median: 4, IQR: 3.0 to 5.0). Regarding cybersickness, 73% of the participants reported experiencing any or minimal discomfort during the simulation, and none needed to stop the test due to discomfort. Conclusion: Our initial validation of a VR platform designed for pediatric trauma education was positive. Participants endorsed VR and its potential to enhance performance, particularly in non-technical skills. Encouraged by these results, we will proceed with feasibility and implementation studies, comparing VR to high-fidelity mannequins.
2024-02-17
MedRxiv (prépublication)
doi.org
Multi-ancestry polygenic risk scores using phylogenetic regularization
Elliot Layne
Shadi Zabad
Yue Li
Mathieu Blanchette
Accurately predicting phenotype using genotype across diverse ancestry groups remains a significant challenge in human genetics. Many state-… (voir plus)of-the-art polygenic risk score models are known to have difficulty generalizing to genetic ancestries that are not well represented in their training set. To address this issue, we present a novel machine learning method for fitting genetic effect sizes across multiple ancestry groups simultaneously, while leveraging prior knowledge of the evolutionary relationships among them. We introduce DendroPRS, a machine learning model where SNP effect sizes are allowed to evolve along the branches of the phylogenetic tree capturing the relationship among populations. DendroPRS outperforms existing approaches at two important genotype-to-phenotype prediction tasks: expression QTL analysis and polygenic risk scores. We also demonstrate that our method can be useful for multi-ancestry modelling, both by fitting population-specific effect sizes and by more accurately accounting for covariate effects across groups. We additionally find a subset of genes where there is strong evidence that an ancestry-specific approach improves eQTL modelling.
2024-02-16
bioRxiv (prépublication)
doi.org
Deep Equilibrium Models For Algorithmic Reasoning
Sophie Xhonneux
Yu He
Andreea Deac
Jian Tang
Gauthier Gidel
In this blogpost we discuss the idea of teaching neural networks to reach fixed points when reasoning. Specifically, on the algorithmic reas… (voir plus)oning benchmark CLRS the current neural networks are told the number of reasoning steps they need. While a quick fix is to add a termination network that predicts when to stop, a much more salient inductive bias is that the neural network shouldn't change it's answer any further once the answer is correct, i.e. it should reach a fixed point. This is supported by denotational semantics, which tells us that while loops that terminate are the minimum fixed points of a function. We implement this idea with the help of deep equilibrium models and discuss several hurdles one encounters along the way. We show on several algorithms from the CLRS benchmark the partial success of this approach and the difficulty in making it work robustly across all algorithms.
2024-02-15
ICLR.cc/2024/BlogPosts (accepté)
openreview.net
openreview.net
Distributional GFlowNets with Quantile Flows
Dinghuai Zhang
Ling Pan
Ricky T. Q. Chen
Aaron Courville
Yoshua Bengio
Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating com… (voir plus)plex combinatorial structure through a series of decision-making steps. Despite being inspired from reinforcement learning, the current GFlowNet framework is relatively limited in its applicability and cannot handle stochasticity in the reward function. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. By parameterizing each edge flow through their quantile functions, our proposed \textit{quantile matching} GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty. Moreover, we find that the distributional approach can achieve substantial improvement on existing benchmarks compared to prior methods due to our enhanced training algorithm, even in settings with deterministic rewards.
2024-02-15
Transactions on Machine Learning Research (accepté)
doi.org
openreview.net
Systematic cross-sectional age-associations in global fMRI signal topography
Jason S. Nomi
Danilo Bzdok
Jingwei Li
Taylor Bolt
Catie Chang
Salome Kornfeld
Zachary T. Goodman
B.T. Thomas Yeo
R. Nathan Spreng
Lucina Q. Uddin
The global signal (GS) in resting-state functional MRI (fMRI), known to contain artifacts and non-neuronal physiological signals, also conta… (voir plus)ins important neural information related to individual state and trait characteristics. Here, we show distinct linear and curvilinear relationships between GS topography and age in a cross-sectional sample of individuals (6-85 years old) representing a significant portion of the lifespan. Subcortical brain regions such as the thalamus and putamen show linear associations with the GS across age. The thalamus has stronger contributions to the GS in older-age individuals compared with younger-aged individuals, while the putamen has stronger contributions in younger individuals compared with older individuals. The subcortical nucleus basalis of Meynert shows a u-shaped pattern similar to cortical regions within the lateral frontoparietal network and dorsal attention network, where contributions of the GS are stronger at early and old age, and weaker in middle age. This differentiation between subcortical and cortical brain activity across age supports a dual-layer model of GS composition, where subcortical aspects of the GS are differentiated from cortical aspects of the GS. We find that these subcortical-cortical contributions to the GS depend strongly on age across the lifespan of human development. Our findings demonstrate how neurobiological information within the GS differs across development and highlight the need to carefully consider whether or not to remove this signal when investigating age-related functional differences in the brain.
2024-02-15
Imaging Neuroscience (publié)
doi.org
Diagnosis Model for Detection of e-threats Against Soft-Targets
Sónia M. A. Morgado
Margarida Carvalho
Sérgio Felgueiras
2024-02-13
Lecture Notes in Networks and Systems (publié)
doi.org
Computing Power and the Governance of Artificial Intelligence
Girish Sastry
Lennart Heim
Haydn Belfield
Markus Anderljung
Miles Brundage
Julian Hazell
Cullen C. O'keefe
Gillian K. Hadfield
Richard Ngo
Konstantin Pilz
George Gor
Emma Bluemke
Sarah Shoker
Janet Egan
Robert Trager
Shahar Avin
Adrian Weller
Yoshua Bengio
Diane Coyle
Computing power, or"compute,"is crucial for the development and deployment of artificial intelligence (AI) capabilities. As a result, govern… (voir plus)ments and companies have started to leverage compute as a means to govern AI. For example, governments are investing in domestic compute capacity, controlling the flow of compute to competing countries, and subsidizing compute access to certain sectors. However, these efforts only scratch the surface of how compute can be used to govern AI development and deployment. Relative to other key inputs to AI (data and algorithms), AI-relevant compute is a particularly effective point of intervention: it is detectable, excludable, and quantifiable, and is produced via an extremely concentrated supply chain. These characteristics, alongside the singular importance of compute for cutting-edge AI models, suggest that governing compute can contribute to achieving common policy objectives, such as ensuring the safety and beneficial use of AI. More precisely, policymakers could use compute to facilitate regulatory visibility of AI, allocate resources to promote beneficial outcomes, and enforce restrictions against irresponsible or malicious AI development and usage. However, while compute-based policies and technologies have the potential to assist in these areas, there is significant variation in their readiness for implementation. Some ideas are currently being piloted, while others are hindered by the need for fundamental research. Furthermore, naive or poorly scoped approaches to compute governance carry significant risks in areas like privacy, economic impacts, and centralization of power. We end by suggesting guardrails to minimize these risks from compute governance.
2024-02-12
ArXiv (prépublication)
doi.org
arxiv.org
Regional Adaptive Metropolis Light Transport
Hisanari Otsu
Killian Herveau
Johannes Hanika
D. Nowrouzezahrai
Carsten Dachsbacher
The design of the proposal distributions, and most notably the kernel parameters, are crucial for the performance of Markov chain Monte Carl… (voir plus)o (MCMC) rendering. A poor selection of parameters can increase the correlation of the Markov chain and result in bad rendering performance. We approach this problem by a novel path perturbation strategy for online-learning of state-dependent kernel parameters. We base our approach on the theoretical framework of regional adaptive MCMC which enables the adaptation of parameters depending on the region of the state space which contains the current sample, and on information collected from previous samples. For this, we define a partitioning of the path space on a low-dimensional canonical space to capture the characteristics of paths, with a focus on path segments closer to the sensor. Fast convergence is achieved by adaptive refinement of the partitions. Exemplarily, we present two novel regional adaptive path perturbation techniques akin to lens and multi-chain perturbations. Our approach can easily be used on top of existing path space MLT methods to improve rendering efficiency, while being agnostic to the initial choice of kernel parameters.
2024-02-12
ArXiv (prépublication)
doi.org
arxiv.org
Antagonistic AI
Alice Cai
Ian Arawjo
Elena L. Glassman
The vast majority of discourse around AI development assumes that subservient,"moral"models aligned with"human values"are universally benefi… (voir plus)cial -- in short, that good AI is sycophantic AI. We explore the shadow of the sycophantic paradigm, a design space we term antagonistic AI: AI systems that are disagreeable, rude, interrupting, confrontational, challenging, etc. -- embedding opposite behaviors or values. Far from being"bad"or"immoral,"we consider whether antagonistic AI systems may sometimes have benefits to users, such as forcing users to confront their assumptions, build resilience, or develop healthier relational boundaries. Drawing from formative explorations and a speculative design workshop where participants designed fictional AI technologies that employ antagonism, we lay out a design space for antagonistic AI, articulating potential benefits, design techniques, and methods of embedding antagonistic elements into user experience. Finally, we discuss the many ethical challenges of this space and identify three dimensions for the responsible design of antagonistic AI -- consent, context, and framing.
2024-02-11
ArXiv (prépublication)
doi.org
arxiv.org
Antagonistic AI
Alice Cai
Ian Arawjo
Elena L. Glassman
The vast majority of discourse around AI development assumes that subservient,"moral"models aligned with"human values"are universally benefi… (voir plus)cial -- in short, that good AI is sycophantic AI. We explore the shadow of the sycophantic paradigm, a design space we term antagonistic AI: AI systems that are disagreeable, rude, interrupting, confrontational, challenging, etc. -- embedding opposite behaviors or values. Far from being"bad"or"immoral,"we consider whether antagonistic AI systems may sometimes have benefits to users, such as forcing users to confront their assumptions, build resilience, or develop healthier relational boundaries. Drawing from formative explorations and a speculative design workshop where participants designed fictional AI technologies that employ antagonism, we lay out a design space for antagonistic AI, articulating potential benefits, design techniques, and methods of embedding antagonistic elements into user experience. Finally, we discuss the many ethical challenges of this space and identify three dimensions for the responsible design of antagonistic AI -- consent, context, and framing.
2024-02-11
ArXiv (prépublication)
doi.org
arxiv.org