Random sampling for trustworthy pooling layers in graph neural networks

Información del proyecto

Rand4TrustPool

Identificador del acuerdo de subvención: 101148828

DOI

10.3030/101148828

Fecha de la firma de la CE 25 Abril 2024

Fecha de inicio 10 Marzo 2025

Fecha de finalización 9 Marzo 2027

Financiado con arreglo a

• Marie Skłodowska-Curie Actions (MSCA)

Coste total

Sin datos

Aportación de la UE

€ 226 751,04

Coordinado por

UNIVERSITETET I TROMSOE - NORGES ARKTISKE UNIVERSITET
Norway

Objetivo

Graph neural networks (GNNs) are deep learning architectures that hold the promise of durably changing our way of, e.g. predicting inter-molecular chemical affinity to accelerate drug discovery or smartly balancing power loads on the electricity grid. My project focuses on pooling layers, a major building block of neural networks, including GNNs. In a nutshell, pooling layers generate local summaries of the data to enable faster computations and generate discriminative multiscale representations. The traditional periodic-sampling-based pooling that has proven so successful for data defined on regular grids such as time series or images becomes ill-defined when the underlying space of the data loses its regularity such as data defined over graphs. Todays existing solutions stem from a trial-and-error approach often driven by two practical and somewhat short-sighted objectives: computation efficiency and empirical predictive performance. The aim of my project is to add trustworthiness as a main objective in the design of novel pooling layers for GNNs. To achieve this, I will bridge the fields of signal processing, point processes, and random numerical linear algebra with graph machine learning to incorporate random methods (mainly random sampling and random projections) into the design of pooling layers for GNNs. Indeed, randomized approaches are provably well adapted to three pillars of trustworthiness: technical robustness, transparency, and privacy. The outcome of my project will be an extensively tested, theoretically-grounded, trustworthy, ready-to-be-deployed, open-source, GNN-based toolbox, along with its user guide for practitioners. It will be the first GNN architecture benefiting from the theoretical guarantees random pooling layers come with. Such trustworthy GNNs will have an impact in the increasingly many fields in which GNNs are pushing the state-of-the-art: including circuit chip design, physics, drug discovery and network neuroscience.

Ámbito científico (EuroSciVoc)

• ciencias naturales › ciencias biológicas › neurobiología
• ciencias naturales › matemáticas › matemáticas puras › álgebra

Palabras clave

• graph machine learning
• graph neural networks
• trustworthy AI
• pooling
• sampling
• graph signal processing
• point processes
• random numerical linear algebra

Programa(s)

• HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) PROGRAMA PRINCIPAL
  

Tema(s)

• HORIZON-MSCA-2023-PF-01-01 - MSCA Postdoctoral Fellowships 2023
  

Régimen de financiación

HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships

Convocatoria de propuestas

HORIZON-MSCA-2023-PF-01

Coordinador

UNIVERSITETET I TROMSOE - NORGES ARKTISKE UNIVERSITET

• Aportación neta de la UEn: € 226 751,04
• Dirección: HANSINE HANSENS VEG 14 ; 9019 Tromso ; Noruega
• Tipo de actividad: Higher or Secondary Education Establishments
• Coste total: Sin datos