Research map / Graph learning / GNN architectures
Rethinking and Extending the Probabilistic Inference Capacity of GNNs
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.
Analyzes the expressive power of GNNs from a probabilistic inference perspective, relating GNN capacity to probabilistic graphical model inference rather than WL tests.
Problem
Understanding what GNNs can and cannot learn beyond Weisfeiler-Lehman-based expressiveness analyses.
Approach
Examines GNN expressive power from a probabilistic perspective by establishing a connection between GNNs and probabilistic inference, instead of the WL-test framework used by prior work.
Experimental setup
Builds on: Weisfeiler-Lehman test
Closest papers by meaning
- Towards a Complete Logical Framework for GNN Expressiveness (ICLR 2025 · similarity 0.92)
- An Empirical Study of Realized GNN Expressiveness (ICML 2024 · similarity 0.92)
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness (ICLR 2024 · similarity 0.92)
- Almost Surely Asymptotically Constant Graph Neural Networks (NeurIPS 2024 · similarity 0.90)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.90)
- Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks (ICLR 2024 · similarity 0.89)
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.