arXiv AI October 27, 2026 By Bohan Yoon, Hyejin Jang

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Oct 24

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

Graph Neural Networks are widely used to learn structural representations of relational data. Hierarchical graph pooling learns multi-level representations by progressively coarsening graphs; however,...

benchmarks safety

arXiv Machine Learning

Jul 7

Heterogeneous Graph Condensation via Role-Aware Clustering

arXiv:2607. 03097v1 Announce Type: new Abstract: Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains computationally prohibitive.

By Fuyan Ou, Yulin Hu, Ye Yuan

rag benchmarks

arXiv Machine Learning

Jun 2

OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

arXiv:2605. 15511v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning.

By Louisa Cornelis, Johan Mathe, Louis Van Langendonck, Guillermo Bern\'ardez, Nina Miolane

benchmarks

arXiv AI

Jun 11

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

arXiv:2510. 04567v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundational Models (GFMs).

By Weishuo Ma, Yanbo Wang, Xiyuan Wang, Lei Zou, Muhan Zhang

llms

arXiv Machine Learning

Sep 30

Message Passing Does More with Less for In-Context Learning on Graphs

arXiv:2609.37057v1 Announce Type: new Abstract: Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeat...

By Dooho Lee, Jinmo Lee, Minho Jeong, Kijung Shin, Jaemin Yoo

llms

arXiv AI

Aug 28

Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning

The paper reinterprets graph neural networks (GNNs) as retrieval-augmented models, where each layer uses an MLP on a node representation and a permutation‑invariant summary of retrieved graph context instead of traditional message passing. It introduces RTA, a lightweight MLP‑based framework that replaces structural message passing with label‑aware retrieval and propagation, and provides theoretical links to softmax‑attention message passing and robustness to mis‑retrieved outliers. Experiments on text‑attributed graph benchmarks demonstrate that RTA matches or surpasses strong GNN and graph LLM baselines while improving efficiency and robustness.

By Jintang Li, Yuhong Chen, Ruofan Wu, Binli Luo, Jiayi Ji, Hui Li, Rongrong Ji

llms rag benchmarks

One email a morning, machine-written

Related stories

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

Heterogeneous Graph Condensation via Role-Aware Clustering

OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

Message Passing Does More with Less for In-Context Learning on Graphs

Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning