Get Started
Research questionHow can graph pooling preserve global-to-local topology while adapting granularity for graph classification?Graph pooling must reduce a graph to a compact representation without discarding important structural patterns. Fixed-granularity, node-focused coarsening can lose relationships between whole-graph structure and local topology.
AI
Machine Learning
Latest papersRecent research connected to this question, newest first.Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-BallThe setting is graph pooling for graph classification, using both node embeddings and graph topology. The source describes multi-granularity representations that range from whole-graph structure to local subdomains and reports results on benchmark datasets.research paper · Sep 4, 2026
Related questions
How can graph neural networks capture long-range interactions without oversmoothing or oversquashing on diverse large graphs?How can reservoir-based graph neural networks aggregate multi-hop information without over-smoothing?How can node-level over-smoothing diagnostics guide virtual-node selection to alleviate over-squashing in GNNs?How can graph topology inference from node observations be unified with generating new graph instances?
Home
Topics
Search
Library