Flow Graph Neural Networks
Keywords: Graph Neural Networks, Graph Attention Networks, Directed Acyclic Graphs, Power Grids, Electronic Circuits
Abstract: Graph Neural Networks (GNNs) have become essential for learning from graph-structured data. However, existing GNNs do not consider the conservation law inherent in graphs associated with a flow of physical resources, such as electrical current in power grids or traffic in transportation networks. To address this limitation and enhance the performance on tasks where accurate modeling of resource flows is crucial, we propose Flow Graph Neural Networks (FlowGNNs). This novel GNN framework adapts existing graph attention mechanisms to reflect the conservation of resources by distributing a node's message among its outgoing edges instead of allowing arbitrary duplication of the node's information. We further extend this framework to directed acyclic graphs (DAGs), enabling discrimination between non-isomorphic flow graphs that would otherwise be indistinguishable for standard GNNs tailored to DAGs. We validate our approach through extensive experiments on two different flow graph domains—electronic circuits and power grids—and demonstrate that the proposed framework enhances the performance of traditional GNN architectures on both graph-level classification and regression tasks.
Primary Area: learning on graphs and other geometries & topologies
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10563
Loading