Research map / Graph learning / GNN architectures
Towards a Complete Logical Framework for GNN Expressiveness
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a logical framework for GNN expressiveness, linking GNN architectures to first-order logic extensions to characterize the graph patterns they can capture (abstract truncated).
Problem
Weisfeiler-Lehman tests are the main measure of GNN expressiveness, but high-order WL tests are opaque about which graph patterns they capture, so a clearer logical characterization is needed.
Approach
Uses the connection between WL tests and first-order logic to build a logical framework for GNN expressiveness that aims to make the captured graph patterns explicit; the abstract is truncated so the specific construction is not stated.
Closest papers by meaning
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness (ICLR 2024 · similarity 0.95)
- An Empirical Study of Realized GNN Expressiveness (ICML 2024 · similarity 0.94)
- Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization (NeurIPS 2025 · similarity 0.92)
- What Expressivity Theory Misses: Message Passing Complexity for GNNs (NeurIPS 2025 · similarity 0.91)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.90)
- Recurrent Graph Neural Networks and Their Connections to Bisimulation and Logic (AAAI 2024 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.