Guillaume Huguet

Maximilian Nickel

Ian Adelstein

Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to comput… (voir plus)e reliably in high dimensions. Indeed, in noisy and high-dimensional data, traditional estimates in ambient dimensions approach a fixed entropy and are prohibitively hard to compute. To address these issues, we leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. Specifically, we define diffusion spectral entropy (DSE) in neural representations of a dataset as well as diffusion spectral mutual information (DSMI) between different variables representing data. First, we show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data that outperform classic Shannon entropy, nonparametric estimation, and mutual information neural estimation (MINE). We then study the evolution of representations in classification networks with supervised learning, self-supervision, or overfitting. We observe that (1) DSE of neural representations increases during training; (2) DSMI with the class label increases during generalizable learning but stays stagnant during overfitting; (3) DSMI with the input signal shows differing trends: on MNIST it increases, while on CIFAR-10 and STL-10 it decreases. Finally, we show that DSE can be used to guide better network initialization and that DSMI can be used to predict downstream classification accuracy across 962 models on ImageNet.

2024-01-01

CISS (publié)

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation.

James Vuckovic

Kilian FATRAS

Eric Laufer

Pablo Lemos

Riashat Islam

Cheng-Hao Liu

Jarrid Rector-Brooks

Tara Akhound-Sadegh

Michael M. Bronstein

Alexander Tong

Joey Bose

2024-01-01

Neural Information Processing Systems (publié)

dblp.uni-trier.de

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Alexander Tong

Nikolay Malkin

Kilian FATRAS

Lazar Atanackovic

Yanlei Zhang

Yoshua Bengio

We present simulation-free score and flow matching ([SF]…

2024-01-01

AISTATS (publié)

F66. FROM GENE TO COGNITION: MAPPING THE EFFECTS OF GENOMIC DELETIONS AND DUPLICATIONS ON COGNITIVE ABILITY

Sayeh Kazem

Kuldeep Kumar

Myriam Lizotte

Thomas Renne

Jakub Kopal

Stefan Horoi

Martineau Jean-Louis

Zohra Saci

Laura Almasy

David C. Glahn

Guillaume Dumas

Sébastien Jacquemont

2023-10-01

European Neuropsychopharmacology (publié)

W56. UNRAVELING THE IMPACT OF GENOMIC VARIATIONS ON COGNITIVE ABILITY ACROSS THE HUMAN CORTEX: INSIGHTS FROM GENE EXPRESSION AND COPY NUMBER VARIANTS

Kuldeep Kumar

Sayeh Kazem

Thomas Renne

Bank Engchuan

Omar Shanta

Bhooma Thiruvahindrapuram

J. MacDonald

Marieke Klein

Stephen W Scherer

Laura Almasy

Jonathan Sebat

David C. Glahn

Guillaume Dumas

Sébastien Jacquemont

2023-10-01

European Neuropsychopharmacology (publié)

Subcortical Brain Alterations in Carriers of Genomic Copy Number Variants.

Kuldeep Kumar

Claudia Modenato

Clara A. Moreau

C. Ching

Christopher R. K. Ching

Annabelle Harvey

Sandra Martin-Brevet

Martineau Jean-Louis

Elise Douard

Charles-Olivier Martin

C.O. Martin

Nadine Younis

Petra Tamer

Anne M. Maillard

Borja Rodriguez-Herreros

Aurélie Pain

Sonia Richetin

Leila Kushan

Dmitry Isaev … (voir 26 de plus)

Kathryn Alpert

Anjani Ragothaman

Jessica A. Turner

Wei Wang

T. Ho

Tiffany C. Ho

Lianne Schmaal

Ana I. Silva

Marianne B.M. van den Bree

V. Marianne

David E.J. Linden

M. J. Owen

Marie Owen

Jeremy Hall

Sarah Lippé

Guillaume Dumas

Bogdan Draganski

Boris A. Gutman

Ida E. Sønderby

Ole A. Andreassen

Laura Schultz

Laura Almasy

David C. Glahn

Carrie E. Bearden

Paul M. Thompson

Sébastien Jacquemont

OBJECTIVE Copy number variants (CNVs) are well-known genetic pleiotropic risk factors for multiple neurodevelopmental and psychiatric disord… (voir plus)ers (NPDs), including autism (ASD) and schizophrenia. Little is known about how different CNVs conferring risk for the same condition may affect subcortical brain structures and how these alterations relate to the level of disease risk conferred by CNVs. To fill this gap, the authors investigated gross volume, vertex-level thickness, and surface maps of subcortical structures in 11 CNVs and six NPDs. METHODS Subcortical structures were characterized using harmonized ENIGMA protocols in 675 CNV carriers (CNVs at 1q21.1, TAR, 13q12.12, 15q11.2, 16p11.2, 16p13.11, and 22q11.2; age range, 6-80 years; 340 males) and 782 control subjects (age range, 6-80 years; 387 males) as well as ENIGMA summary statistics for ASD, schizophrenia, attention deficit hyperactivity disorder, obsessive-compulsive disorder, bipolar disorder, and major depression. RESULTS All CNVs showed alterations in at least one subcortical measure. Each structure was affected by at least two CNVs, and the hippocampus and amygdala were affected by five. Shape analyses detected subregional alterations that were averaged out in volume analyses. A common latent dimension was identified, characterized by opposing effects on the hippocampus/amygdala and putamen/pallidum, across CNVs and across NPDs. Effect sizes of CNVs on subcortical volume, thickness, and local surface area were correlated with their previously reported effect sizes on cognition and risk for ASD and schizophrenia. CONCLUSIONS The findings demonstrate that subcortical alterations associated with CNVs show varying levels of similarities with those associated with neuropsychiatric conditions, as well distinct effects, with some CNVs clustering with adult-onset conditions and others with ASD. These findings provide insight into the long-standing questions of why CNVs at different genomic loci increase the risk for the same NPD and why a single CNV increases the risk for a diverse set of NPDs.

2023-07-12

American Journal of Psychiatry (publié)

Neural FIM for learning Fisher information metrics from point cloud data

Oluwadamilola Fasina

Alexander Tong

Yanlei Zhang

Maximilian Nickel

Ian Adelstein

Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the under… (voir plus)lying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature. To this end, we propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data - allowing for a continuous manifold model for the data. Neural FIM creates an extensible metric space from discrete point cloud data such that information from the metric can inform us of manifold characteristics such as volume and geodesics. We demonstrate Neural FIM’s utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells).

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Alexander Tong

Nikolay Malkin

Kilian FATRAS

Lazar Atanackovic

Yanlei Zhang

Yoshua Bengio

We present simulation-free score and flow matching ([SF]…

2023-06-19

ICML.cc/2023/Workshop/Frontiers4LCD (publié)

Graph Fourier MMD for Signals on Graphs

Samuel Leone

Aarthi Venkat

Alexander Tong

While numerous methods have been proposed for computing distances between probability distributions in Euclidean space, relatively little at… (voir plus)tention has been given to computing such distances for distributions on graphs. However, there has been a marked increase in data that either lies on graph (such as protein interaction networks) or can be modeled as a graph (single cell data), particularly in the biomedical sciences. Thus, it becomes important to find ways to compare signals defined on such graphs. Here, we propose Graph Fourier MMD (GFMMD), a novel distance between distributions and signals on graphs. GFMMD is defined via an optimal witness function that is both smooth on the graph and maximizes the difference in expectation between the pair of distributions on the graph. We find an analytical solution to this optimization problem as well as an embedding of distributions that results from this method. We also prove several properties of this method including scale invariance and applicability to disconnected graphs. We showcase it on graph benchmark datasets as well on single cell RNA-sequencing data analysis. In the latter, we use the GFMMD-based gene embeddings to find meaningful gene clusters. We also propose a novel type of score for gene selection called gene localization score which helps select genes for cellular state space characterization.

2023-05-21

SampTA/2023/Conference (publié)

Single-cell analysis reveals inflammatory interactions driving macular degeneration

Manik Kuchroo

Marcello DiStasio

Eric Song

Eda Calapkulu

Le Zhang

Maryam Ige

Amar H. Sheth

Abdelilah Majdoubi

Madhvi Menon

Alexander Tong

Abhinav Godavarthi

Yu Xing

Scott Gigante

Holly Steach

Jessie Huang

Je-chun Huang

Janhavi Narain

Kisung You

George Mourgkos … (voir 6 de plus)

Rahul M. Dhodapkar

Matthew Hirn

Bastian Rieck

Brian P. Hafler

2023-05-05

Nature Communications (publié)

Neural FIM for learning Fisher Information Metrics from point cloud data

Oluwadamilola Fasina

Alexander Tong

Yanlei Zhang

Maximilian Nickel

Ian Adelstein

Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the under… (voir plus)lying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature. To this end, we propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data - allowing for a continuous manifold model for the data. Neural FIM creates an extensible metric space from discrete point cloud data such that information from the metric can inform us of manifold characteristics such as volume and geodesics. We demonstrate Neural FIM's utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells).

2023-04-24

ICML.cc/2023/Conference (poster)

Using rare genetic mutations to revisit structural brain asymmetry

Jakub Kopal

Kuldeep Kumar

Kimia Shafighi

Karin Saltoun

Claudia Modenato

Clara A. Moreau

Martineau Jean-Louis

Charles-Olivier Martin

C.O. Martin

Zohra Saci

Nadine Younis

Elise Douard

Khadije Jizi

Alexis Beauchamp-Chatel

Leila Kushan

Ana I. Silva

Marianne B.M. van den Bree

David E.J. Linden

M. J. Owen … (voir 11 de plus)

Jeremy Hall

Sarah Lippé

Bogdan Draganski

Ida E. Sønderby

Ole A. Andreassen

David C. Glahn

Paul M. Thompson

Carrie E. Bearden

Robert Zatorre

Sébastien Jacquemont

Danilo Bzdok

2023-04-18

bioRxiv (prépublication)