Graph Attribute Aggregation Network with Progressive Margin Folding

2019-05-14 · Penghui Sun, Jingwei Qu, Xiaoqing Lyu, Haibin Ling, Zhi Tang

Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregation methods between different convolution graph layers. In this paper, we introduce a graph attribute aggregation network (GAAN) architecture. Different from the conventional pooling operations, a graph-transformation-based aggregation strategy, progressive margin folding, PMF, is proposed for integrating graph features. By distinguishing internal and margin elements, we provide an approach for implementing the folding iteratively. And a mechanism is also devised for preserving the local structures during progressively folding. In addition, a hypergraph-based representation is introduced for transferring the aggregated information between different layers. Our experiments applied to the public molecule datasets demonstrate that the proposed GAAN outperforms the existing GCNN models with significant effectiveness.

📄 PDF Abstract BibTeX arXiv:1905.05347

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Methods 이 논문이 사용한 방법론

GaAN Gated Attention Networks (GaAN) is a new architecture for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads,…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Toward a multilevel representation of protein molecules: comparative approaches to the aggregation/folding propensity problem

2014-07-28 · Lorenzo Livi, Alessandro Giuliani, Antonello Rizzi

This paper builds upon the fundamental work of Niwa et al. [34], which provides the unique possibility to analyze the relative aggregation/folding propensity of the elements of the entire Escherichia coli (E. coli) prote…

Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization

2026-05-12 · Jaerin Lee, Kanggeon Lee, Kyoung Mu Lee arxiv

Differentiable vector graphics have enabled powerful gradient-based optimization of vector primitives directly from raster images. However, existing frameworks formulate this as a flat optimization problem, forcing hundr…

Marginal Nodes Matter: Towards Structure Fairness in Graphs

2023-10-23 · Xiaotian Han, Kaixiong Zhou, Ting-Hsiang Wang, Jundong Li 외

In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protectin…

Fairness

Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation

2023-04-15 · Tongya Zheng, Xinchao Wang, Zunlei Feng, Jie Song 외

Temporal graphs exhibit dynamic interactions between nodes over continuous time, whose topologies evolve with time elapsing. The whole temporal neighborhood of nodes reveals the varying preferences of nodes. However, pre…

Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs

2022-10-08 · Silvia Beddar-Wiesing, Giuseppe Alessio D'Inverno, Caterina Graziani, Veronica Lachi 외

Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GN…