Welcome!
Networks, or graphs, are a valuable tool for comprehending complex systems -- they can represent a wide range of real-world phenomena such as social networks, biological networks, financial systems, communication networks, and more. Graphs enable modeling various aspects of these systems and help us understand the intricate relationships and interactions between their entities. Apart from being useful in studying complex systems, applications of machine learning to graphs have led to important new applications -- from information systems and social media to drug discovery -- and have become one of the fastest growing areas in artificial intelligence. However, standard graph representations of complex relational data are limited in their representation capabilities as they only capture dyadic relationships but do not take higher-order properties of the analyzed systems into account.
In recent years, deep learning techniques combined with higher-order network models have gained significant attention as they can effectively capture the multi-relational and multi-dimensional characteristics of complex systems. These models, such as simplicial complexes, manifolds and hypergraph representations, provide a more faithful representation of the system, enabling a deeper understanding of the intricate relationships within the data. The utilization of deep learning algorithms in conjunction with such higher-order network models has demonstrated the ability to enhance the identification of previously unobserved characteristics and patterns in complex systems.
Previous editions of HONS have been a valuable platform for scientific discussions between researchers who study the challenges and opportunities of higher-order network models. Focusing on bridging the network science and deep learning community, this year's edition of HONS will explore how we can leverage higher-order networks for the analysis of (spatio-)temporal network data and how we can apply deep graph learning techniques for spatio-temporal data. The purpose of this event is to create an environment for the exchange of ideas and collaborations between participants to discuss challenges and opportunities. Some of the topics that will be discussed are:
- - How can (temporal) networks be inferred from spatial data, e.g. in large-scale infrastructure systems, single-cell biology data, intrinsic brain networks, etc.?
- - Which modelling approaches can we use to analyze spatio-temporal graphs?
- - How can higher-order models like simplicial complexes and hypergraphs be used to model spatio-temporal data?
- - How can spatio-temporal graph data best be incorporated into deep learning models?
- - Which challenges in terms of, for example, computational complexity, data efficiency, and overfitting does the modelling of spatio-temporal graphs and utilizing deep-learning approaches entail?
- - Which benchmark data are available to reliably test and validate higher-order network approaches for spatio-temporal networks?
- - How can spatio-temporal graphs be visualized efficiently and intuitively?
- - Which analytical statements can we make about the expressivity of temporal graph neural networks?
- - Which additional ethical challenges are introduced by the use of spatio-temporal graph models in deep learning?
We look forward to seeing you at the HONS satellite!
Date and Venue
The satellite will be held in June 2024 in Quebec City, Canada. More details coming soon...