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.

Original post →

More from Research

Research channel →