NeurIPS paper: substructure-aware graph pooling boosts hierarchical GNN tasks
JeremyCMorgan · x · 2026-11-20
A NeurIPS 2026 paper proposes Pooled-Substructure-Aware GNNs, which explicitly preserve substructures uncovered by structure-based graph pooling. The design increases expressive power per the Weisfeiler-Lehman test, introduces two synthetic datasets with controllable hierarchy plus a metric for hierarchy prevalence in real benchmarks, and outperforms matched pooling baselines on hierarchical tasks. Code and datasets are public.
More from Research
- Perception verbs alone identify fiction with 90% accuracy, decision tree shows — _akpiper · 2026-11-20
- Ai2 launches open-source Theorizer in Asta: AI proposes testable scientific theories — allen_ai · 2026-11-20
- AI2 launches Theorizer in Asta, an AI that proposes testable scientific theories from literature — allen_ai · 2026-11-20
- Cross-institutional survey asks whether mechanistic interpretability actually makes AI safer — sarahookr · 2026-11-20
- μSAM2 released: SOTA microscopy segmentation trained on 30M+ annotated cells — alxndrkalinin · 2026-11-20
- SnakeBench: frontier models still fail to plan more than 2-3 moves ahead — GregKamradt · 2026-11-20