paper-with-me

홈 › Papers

Hierarchical graph neural nets can capture long-range interactions

2021-07-15 · Ladislav Rampášek, Guy Wolf

Graph neural networks (GNNs) based on message passing between neighboring nodes are known to be insufficient for capturing long-range interactions in graphs. In this project we study hierarchical message passing models that leverage a multi-resolution representation of a given graph. This facilitates learning of features that span large receptive fields without loss of local information, an aspect not studied in preceding work on hierarchical GNNs. We introduce Hierarchical Graph Net (HGNet), which for any two connected nodes guarantees existence of message-passing paths of at most logarithmic length w.r.t. the input graph size. Yet, under mild assumptions, its internal hierarchy maintains asymptotic size equivalent to that of the input graph. We observe that our HGNet outperforms conventional stacking of GCN layers particularly in molecular property prediction benchmarks. Finally, we propose two benchmarking tasks designed to elucidate capability of GNNs to leverage long-range interactions in graphs.

📄 PDF Abstract BibTeX arXiv:2107.07432

Code (1)

rampasek/HGNet 공식 구현 pytorch

Tasks

BenchmarkingMolecular Property PredictionProperty Prediction

Methods 이 논문이 사용한 방법론

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

HI-MeshGraphNets: Efficient and Accurate Mesh-based Physics Learning with Hierarchical Multi-scale Graph Neural Networks

2026-08-13 · SiHun Lee, Dong-Hyuk Park, Taesoo Bang, Seung-Hoon Kang arxiv

Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers. Among them, graph neural networks (GNNs) are well suited for representing simulation meshes and learning nodal…

Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets

2025-12-07 · Chang Liu, Vivian Li, Linus Leong, Vladimir Radenkovic 외 arxiv

Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical inter…

Hierarchical Residuals Exploit Brain-Inspired Compositionality

2025-02-21 · Francisco M. López, Jochen Triesch

We present Hierarchical Residual Networks (HiResNets), deep convolutional neural networks with long-range residual connections between layers at different hierarchical levels. HiResNets draw inspiration on the organizati…

MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy

2023-09-21 · NeurIPS 2023 11

Graph neural networks, which typically exchange information between local neighbors, often struggle to capture long-range interactions (LRIs) within the graph. Building a graph hierarchy via graph pooling methods is a pr…

EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data

2022-11-23 · Minghao Xu, Yuanfan Guo, Yi Xu, Jian Tang 외

Modeling spatial relationship in the data remains critical across many different tasks, such as image classification, semantic segmentation and protein structure understanding. Previous works often use a unified solution…

image-classificationImage ClassificationInstance Segmentationobject-detection+4