Research map / Graph learning / GNN architectures

Hierarchical Graph Representation Learning with Pooling-Induced Substructures

NeurIPS 2026 · Graph learning › GNN architectures · approach: Graph structure learning

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.

Proposes a hierarchical graph representation learning approach that explicitly preserves the substructures induced by graph pooling, for graph-level tasks needing reasoning beyond local neighborhoods.

Problem

Hierarchical graph-level tasks requiring reasoning over substructures beyond local neighborhoods are challenging for standard GNNs; existing graph pooling methods often fail to explicitly preserve the substructures they induce, leading to inconsistent performance.

Approach

Explicitly preserve the substructures induced by pooling within hierarchical graph representations, rather than relying on coarsening alone. Abstract is truncated, so further specifics are not available.

Closest papers by meaning

• Geometry-Aware Edge Pooling for Graph Neural Networks (NeurIPS 2025 · similarity 0.91)
• SkipPool: Improved Sparse Hierarchical Graph Pooling with Differentiable Exploration (AAAI 2025 · similarity 0.90)
• Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 2024 · similarity 0.89)
• Graph Parsing Networks (ICLR 2024 · similarity 0.88)
• ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks (ICML 2025 · similarity 0.88)
• Boosting Graph Pooling with Persistent Homology (NeurIPS 2024 · similarity 0.88)