← Back to all news
arXiv Machine Learning

Hierarchical Graph Representation Learning with Pooling-Induced Substructures

The paper introduces Pooled-Substructure-Aware GNNs, a graph pooling method that explicitly preserves substructures identified by structure-based pooling, thereby improving the expressive power of pooling-based GNNs as measured by the Weisfeiler–Lehman test. The authors also present two synthetic datasets with controllable hierarchical structure and a metric for assessing hierarchical patterns in real-world graph-level benchmarks. Experiments show that the proposed approach outperforms matched pooling baselines on tasks with hierarchical structure while remaining competitive on simpler benchmarks.

Related stories

arXiv AI
Oct 27

Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks

Graph-Dependent Pooling (GDPool) introduces a dynamic approach to hierarchical graph pooling, allowing each graph to determine its own pooling granularity rather than relying on fixed cluster numbers or ratios. The method employs self-attention to select graph-specific anchors and uses soft node assignment to build coarser graphs, addressing optimization conflicts identified through gradient alignment analysis. Experiments on metal‑organic framework and molecular graph datasets demonstrate that GDPool outperforms existing methods in predictive accuracy, modularity, and exhibits stable behavior across various hyperparameters.

By Bohan Yoon, Hyejin Jang
benchmarkssafety
More like this →
arXiv AI
Oct 2

Graph Hierarchical Recurrence for Long-Range Generalization

Graph Hierarchical Recurrence (GHR) is a new framework that enhances Graph Neural Networks and Graph Transformers by jointly processing the input graph and a pooled hierarchical abstraction. It addresses the limitation of existing models in handling predictions that depend on correlations between distant graph regions, especially under out-of-range generalization where test instances require interactions beyond training distances. Across many long-range benchmarks, GHR consistently improves performance, achieving state‑of‑the‑art or competitive results on multiple tasks.

By Stefano Carotti, Marco Pacini, Alessio Gravina, Davide Bacciu, Bruno Lepri, Sebastiano Bontorin
llmsbenchmarks
More like this →
arXiv Machine Learning
Aug 28

Inductive Correlation Clustering with Graph Neural Networks

The paper introduces Inductive Correlation Clustering, a new framework that uses Graph Neural Networks to solve the Correlation Clustering problem on unseen graph instances. By learning common structural patterns and node features, the method generalizes to new graphs with minimal computational overhead, achieving inference times up to five orders of magnitude faster while maintaining an approximation ratio within about 10% of the best baseline. It also demonstrates competitive performance on standard transductive benchmarks and serves as an efficient learnable pooling layer for graph classification tasks.

By Francesco Paolo Nerini, Francesco Bonchi, Arijit Khan, Andr\'e Panisson
benchmarks
More like this →