aiqbench analysis
This research advances the theoretical understanding of how information flows through Deep Graph Networks, specifically addressing the preservation of long-term dependencies in both static and evolving graph structures. By framing these networks as dynamical systems, the work offers new architectural insights for handling complex spatio-temporal patterns in sparse data regimes. These findings are critical for improving the robustness of graph-based AI models used in domains ranging from molecular modeling to social network analysis.
Information propagation dynamics in Deep Graph Networks
arXiv:2410.10464v3 Announce Type: replace Abstract: Graphs are a highly expressive abstraction for modeling entities and their relations, such as molecular structures, social networks, and traffic networks. Deep Graph Networks (DGNs) have emerged as a family of deep learning models that can effectively process and learn such structured information. However, learning effective information propagation patterns within DGNs remains a critical challenge that heavily influences the model capabilities, both in the static domain and in the temporal domain (where features and/or topology evolve). Given this challenge, this thesis investigates the dynamics of information propagation within DGNs for static and dynamic graphs, focusing on their design as dynamical systems. Throughout this work, we provide theoretical and empirical evidence to demonstrate the effectiveness of our proposed architectures in propagating and preserving long-term dependencies between nodes, and in learning complex spatio-temporal patterns from irregular and sparsely sampled dynamic graphs. In summary, this thesis provides a comprehensive exploration of the intersection between graphs, deep learning, and dynamical systems, offering insights and advancements for the field of graph representation learning and paving the way for more effective and versatile graph-based learning models.
Abstract:Graphs are a highly expressive abstraction for modeling entities and their relations, such as molecular structures, social networks, and traffic networks. Deep Graph Networks (DGNs) have emerged as a family of deep learning models that can effectively process and learn such structured information. However, learning effective information propagation patterns within DGNs remains a critical challenge that heavily influences the model capabilities, both in the static domain and in the temporal domain (where features and/or topology evolve). Given this challenge, this thesis investigates the dynamics of information propagation within DGNs for static and dynamic graphs, focusing on their design as dynamical systems. Throughout this work, we provide theoretical and empirical evidence to demonstrate the effectiveness of our proposed architectures in propagating and preserving long-term dependencies between nodes, and in learning complex spatio-temporal patterns from irregular and sparsely sampled dynamic graphs. In summary, this thesis provides a comprehensive exploration of the intersection between graphs, deep learning, and dynamical systems, offering insights and advancements for the field of graph representation learning and paving the way for more effective and versatile graph-based learning models.
Machine Learning (cs.LG); Social and Information Networks (cs.SI)
arXiv:2410.10464 [cs.LG]
(or arXiv:2410.10464v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2410.10464 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 277 words
Related coverage
A Dynamical Systems Perspective on the Analysis of Neural Networks
arXiv · Jun 17, 2026
GLL: A Differentiable Graph Learning Layer for Neural Networks
arXiv · Oct 15, 2026
Graph-centric agentic intelligence
Amazon Science · Oct 1, 2026
Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
arXiv · Jul 31, 2026