Research map / Graph learning / GNN architectures
Graph Neural Networks Use Graphs When They Shouldn't
Maya Bechler-Speicher, Ido Amos, Ran Gilad-Bachrach, Amir Globerson
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies when GNNs should ignore the provided graph structure, using the paper's abstract framing; the supplied full text is actually the AAAI author template, so the card relies mainly on the abstract.
Problem
Graph neural networks receive a graph as input, but in some tasks the best predictions come from ignoring the graph structure; it is unclear whether GNNs learn to do so reliably.
Approach
Examines whether GNNs can learn to ignore graph structure when it is unhelpful; the provided text does not include the method details, so the specific technique is not stated.
Limitations
- Full text provided is the AAAI formatting template, not the paper body
- Abstract is truncated; results and method are not available
Closest papers by meaning
- Backward Oversmoothing: why is it hard to train deep Graph Neural Networks? (ICML 2026 · similarity 0.92)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.91)
- Graph Neural Networks Do Not Always Oversmooth (NeurIPS 2024 · similarity 0.90)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.90)
- On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning (NeurIPS 2025 · similarity 0.89)
- What do Graph Neural Networks learn? Insights from Tropical Geometry (NeurIPS 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.
