Subgraph Mining for Graph Neural Networks
Keywords: graph learning, graph neural networks, graph representation learning, subgraph mining, subgraph isomorphism
Abstract: While Graph Neural Networks (GNNs) are state-of-the-art models for graph learning, they are only as expressive as the basic first-order Weisfeiler-Leman graph isomorphism test algorithm. To enhance their expressiveness one can incorporate complex structural information as attributes of the nodes in input graphs. However, this approach typically demands significant human effort and specialised domain knowledge, which is not always available. In this paper, we demonstrate the feasibility of automatically extracting such structural information through subgraph mining and feature selection techniques. Our extensive experimental evaluation, conducted across graph classification tasks, reveals that GNNs extended with automatically selected features obtained using subgraph mining can achieve comparable or even superior performance to GNNs relying on manually crafted features.
Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)
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/2024/AuthorGuide.
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: 5689
Loading