Vous êtes ici : Accueil » Réunions » Réunion

Identification

Identifiant: 
Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?

Signal processing over graphs, with a focus on neuroscience data

Nous vous rappelons que, afin de garantir l'accès de tous les inscrits aux salles de réunion, l'inscription aux réunions est gratuite mais obligatoire.

S'inscrire à la réunion.

Inscriptions

28 personnes membres du GdR ISIS, et 26 personnes non membres du GdR, sont inscrits à cette réunion.
Capacité de la salle : 90 personnes.

Prise en charge d'un déplacement dans le cadre d'une réunion d'animation

Qui ?

Le GdR ISIS prend en charge les déplacements des organisateurs des réunions et des orateurs. Le GdR prend aussi en charge les déplacements des participants aux réunions membres d'un laboratoire adhérent du GdR dans la limite d'un doctorant et d'un permanent par laboratoire académique et par réunion, ou d'une personne par adhérent du club des partenaires et par réunion.

Quand organiser son déplacement ?

Les demandes de mission et les réservations doivent impérativement être effectuées au moins deux semaines avant la date de la mission.

Comment réserver ?

Annonce

Graphs are a central modeling tool for network-structured data. Depending on the application, the nodes of a graph may represent people in a social network, stations in a transportation network, web pages in the hyperlink network... basically any system made of interconnected sub-systems. Data on a graph, called graph signals, such as individual hobbies in a social network, or traffic at a given time in a transportation network, may typically be represented by a scalar per node. Processing these signals while taking into account the irregular structure on which they are defined is the goal of the young research field of Graph Signal Processing (GSP).

An important application of GSP is neuroscience data, where graphs are an essential modelisation tool of the brain at various scales of description. Also, the versatility of graphs made them popular for the processing (and even the joint processing) of many different types of brain signals: EEG, MEG, functional MRI, diffusion MRI...

The objective of this conference day is two-fold:

- a methodological perspective on recent advances in Graph Signal Processing. Topics of interest include: filtering, sampling, transforms, graph topology inference, higher-order graphs, learning over graphs, dynamic signals and/or dynamic graphs, etc.

- a focus on graphs for neuroscience data, with a special attention to cross-fertilize ideas from different scientific communities --neuroscience, network science and signal processing. How are graphs used today in neuroscience data processing? What are the needs in terms of methodological development? How can GSP bring new perspectives?

Invited speakers:

- Dimitri van de Ville (EPFL)
- Mahmoud Hassan (LTSI, Rennes)
- Sarah Morgan (Cambridge)

Call for abstracts (oral presentations and posters)

Everyone, and especially PhD students, are encouraged to participate and present their work at this conference day: please send an abstract (maximum 1 page) to the organizers before the 1st of September (extended to the 9th of September).

Where?

The conference room of délégation CNRS (site d'Ivry-sur-Seine): 27 rue Paul Bert, 94204 Ivry sur Seine (subway 7, Paris). http://www.dr1.cnrs.fr/spip.php?article116

When?

Wednesday 25th of September 2019. All day.

Organizers:

- Nicolas Tremblay (Gipsa-lab, CNRS) : nicolas.tremblay@gipsa-lab.fr
- Bastien Pasdeloup (EPFL) : bastien.pasdeloup@gmail.com

Programme

This is the program for the day:
- 09h15: doors open
- 09h45: welcome talk
- 10h - 10h55 : D. van de Ville (EPFL), Graph Signal Processing for Human Neuroimaging Addresses Function-Structure Relationships
- 10h55 - 11h15 : Potel et al. (Rennes), Imaging disrupted brain networks at rest in Parkinson's disease using dense EEG
- 11h15 - 11h35 : Takerkart (Marseille, institut la Timone), Learning from individual parcellations using functionaly informed brain graphs
- 11h35 - 11h55 : Cattai et al. (Sorbonne Université), EEG network mechanisms in motor imagery-based BCI tasks
- 11h55 - 12h15 : Brahim and Farrugia (IMT Atlantique), Graph Fourier Transform of temporal fluctuations of brain activity for supervised learning
- 12h15 - 13h45 : lunch
- 13h45 - 14h40 : M. Hassan (Rennes), Tracking sub-second dynamic brain networks using electroencephalography
- 14h40 - 15h35 : S. Morgan (Cambridge), Applications of network neuroscience- in development, health and disease
- 15h35 - 15h50 : break
- 15h50 - 16h10 : Frusque et al. (ENS Lyon), Time Varying Graphical Lasso on Phase Synchronizing Time Series
- 16h10 - 16h30 : Melot et al. (Marseille), Intertwinning wavelets or multiresolution analysis on graphs through random forests.
- 16h30 - 16h50 : Keriven et al. (ENS Paris), Universal Invariant and Equivariant Graph Neural Networks
- 16h50 - 17h00 : Final words

Résumés des contributions

10h-10h55. "Graph Signal Processing for Human Neuroimaging Addresses Function-Structure Relationships" (D. Van de ville)

State-of-the-art magnetic resonance imaging (MRI) provides unprecedented opportunities to study brain structure (anatomy) and function (physiology). Based on such data, graph representations can be built where nodes are associated to brain regions and edge weights to strengths of structural or functional connections. In particular, structural graphs capture major neural pathways in white matter, while functional graphs map out statistical interdependencies between pairs of regional activity traces. Network analysis of these graphs has revealed emergent system-level properties of brain structure or function, such as efficiency of communication and modular organization.

In this talk, graph signal processing (GSP) will be presented as a novel framework to integrate brain structure, contained in the structural graph, with brain function, characterized by activity traces that can be considered as time-dependent graph signals. Such a perspective allows to define novel meaningful graph-filtering operations of brain activity that take into account smoothness of signals on the anatomical backbone. For instance, we will show how activity can be analyzed in terms of being aligned versus liberal with respect to brain structure, or how additional prior information about cognitive systems can be incorporated. The well-known Fourier phase randomization method to generate surrogate data can also be adapted to this new setting. Finally, recent work will highlight how the spatial resolution of this type of analyses can be increased to the voxel level, representing a few ten thousands of nodes.

References:
W. Huang, T. A. W. Bolton, J. D. Medaglia, D. S. Bassett, A. Ribeiro & D. Van De Ville, « A Graph Signal Processing Perspective on Functional Brain Imaging », Proceedings of the IEEE, 2018, 106, 868-885
M. G. Preti, D. Van De Ville, « Decoupling of Brain Function from Structure Reveals Regional Behavioral Specialization in Humans », arXiv:1905.07813

10h55-11h15. "Imaging disrupted brain networks at rest in Parkinson's disease using dense EEG" (S. Potel)
Parkinson's disease (PD) is the second most frequent neurodegenerative pathology, concerning about 200000 patients in France. Cognitive impairment is a critical combination of symptoms that often affects parkinsonian patients. Fine assessment of these symptoms is highly needed to treat patients with the right therapeutics. Functional connectivity has recently been assessed in Parkinson's disease using dense EEG, within parkinsonian patients according to their cognitive status (Hassan et al., 2017). Thus, functional connectivity may be used as a biomarker in PD-related cognitive impairment. Here, I will present results concerning edge-wise and node-wise network disruptions between healthy controls and parkinsonian patients. We used the source connectivity method to compute cortical activity from dense EEG recordings and assessed graph theory measures. This early work is a first step in building a biomarker of cognitive impairment in PD using dense EEG.
11h15-11h35. "Learning from individual parcellations using functionaly informed brain graphs" (S. Takerkart)

Abstract soon available

11h35-11h55. "EEG network mechanisms in motor imagery-based BCI tasks" (T. Cattai)

Abstract soon available

11h55-12h15. "Graph Fourier Transform of temporal fluctuations of brain activity for supervised learning" (N. Farrugia)

Abstract soon available

13h45-14h40. "Tracking sub-second dynamic brain networks using electroencephalography" (M. Hassan)

The human brain is a large-scale network (graph) the function of which depends on dynamic communications (edges) between spatially distributed regions (nodes). Magneto/electro-encephalography (M/EEG) provides a unique direct and noninvasive access to the electrophysiological activity of the whole brain, at the millisecond scale. In this talk, I will introduce emergent methods used to track the cortical network dynamics, through M/EEG sensors, at rest and task. I will discuss the potential use of these methods to address some present and future cognitive and clinical neuroscience questions.

14h40-15h35. "Applications of network neuroscience- in development, health and disease" (S. Morgan)

The brain can be thought of as a highly complex network, whose intricate structure and dynamics span multiple temporal and spatial scales. Whilst we are unable to map this network at the neuronal level, MRI brain imaging gives us an invaluable window into macroscopic brain connectivity. For example, MRI brain networks have been used to study the developmental changes that happen during childhood and adolescence (Whitaker and Vertes, PNAS 2016), as well as the biological underpinnings of schizophrenia (Morgan et al, PNAS 2019). In this talk I will showcase a few examples of how MRI brain networks can shed light on the human brain in development, health and disease. I will describe how the networks can be derived (including work using a new technique known as morphometric similarity mapping- Seidlitz et al, Neuron 2018), analysed and ultimately what insights they give us. I will finish by briefly describing how we can link these macroscopic brain networks to openly available gene expression data from the Allen Human Brain Atlas. This approach takes us back to the microscale and can provide important clues as to the biological mechanisms underlying our results.

15h50-16h10. "Time Varying Graphical Lasso on Phase Synchronizing Time Series" (G. Frusque)

We consider the problem of inferring the conditional independence graph from the partial phase locking value index (pPLV) of multivariate time series. A typical application is: the inference of temporal functional connectivity from brain data. We propose to extend the recently proposed time-varying graphical lasso to the measure of partial locking value, resulting in a sparse and a temporally coherent dynamical graph, characterizing the evolution of the phase synchrony between each pair of signals. Two methods are proposed: using a non parametric estimate of the phase locking value, or assuming recorded signals locally follow a multivariate Gaussian distribution. We solve this optimization problem using the alternating direction method of multiplier. We validate our approach and compare both methods in simulation using Roessler oscillators and with a real iEEG dataset from an epileptic patient.

16h10-16h30. "Intertwinning wavelets or multiresolution analysis on graphs through random forests" (C. Melot)

Abstract soon available

16h30-16h50. "Universal Invariant and Equivariant Graph Neural Networks" (N. Keriven)

Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we prove new universality theorems. Recently, Maron et al. (2019) showed that by allowing higher-order tensorization inside the network, universal invariant GNNs can be obtained. As a first contribution, we propose an alternative proof of this result, which relies on the Stone-Weierstrass theorem for algebra of real-valued functions. Our main contribution is then an extension of this result to the equivariant case. The proof relies on a new generalized Stone-Weierstrass theorem for algebra of equivariant functions, which is of independent interest. This is joint work with Gabriel Peyré (ENS).

Date : 2019-09-25

Lieu : Salle de conférence de la délégation CNRS Paris-Villejuif - Site d?Ivry-sur-Seine


Thèmes scientifiques :
A - Méthodes et modèles en traitement de signal

(c) GdR 720 ISIS - CNRS - 2011-2019.