Research map / Graph learning / GNN architectures
What Can Neural Networks Reason About?
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Deep Sets instead of an MLP | Maximum value difference · Maximum value difference test | test accuracy: 9% -> 96% | Helped |
| Sort treasures by value before applying the MLP | MLP · Maximum value difference test | test accuracy | Helped |
| Use a one-iteration GNN instead of Deep Sets for pairwise comparison | Furthest pair · Furthest pair test | test accuracy: 21% vs more than 90% | Helped |
| Use four GNN iterations rather than seven | GNN · Monster trainer test | test accuracy: 94% vs 95% | No clear effect |
| Use an exhaustive-search-aligned NES architecture instead of the other tested models | Subset sum · Subset sum test | test accuracy | Helped |
Closest papers by meaning
- Systematic Relational Reasoning With Epistemic Graph Neural Networks (ICLR 2025 · similarity 0.88)
- Deep Equilibrium Algorithmic Reasoning (NeurIPS 2024 · similarity 0.87)
- Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs (ICLR 2025 · similarity 0.86)
- Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace (NeurIPS 2026 · similarity 0.86)
- When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning (NeurIPS 2025 · similarity 0.86)
- Primal-Dual Neural Algorithmic Reasoning (ICML 2025 · similarity 0.86)
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.