paper-with-me

홈 › Papers

Multi-duplicated Characterization of Graph Structures using Information Gain Ratio for Graph Neural Networks

2022-12-24 · Yuga Oishi, Ken Kaneiwa

Various graph neural networks (GNNs) have been proposed to solve node classification tasks in machine learning for graph data. GNNs use the structural information of graph data by aggregating the features of neighboring nodes. However, they fail to directly characterize and leverage the structural information. In this paper, we propose multi-duplicated characterization of graph structures using information gain ratio (IGR) for GNNs (MSI-GNN), which enhances the performance of node classification by using an i-hop adjacency matrix as the structural information of the graph data. In MSI-GNN, the i-hop adjacency matrix is adaptively adjusted by two methods: (i) structural features in the matrix are selected based on the IGR, and (ii) the selected features in (i) for each node are duplicated and combined flexibly. In an experiment, we show that our MSI-GNN outperforms GCN, H2GCN, and GCNII in terms of average accuracies in benchmark graph datasets.

📄 PDF Abstract BibTeX arXiv:2212.12691

Code (0)

등록된 구현이 없습니다.

Tasks

Node Classification

Methods 이 논문이 사용한 방법론

fail 설명 없음
Residual Connection 설명 없음
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…
GCNII GCNII is an extension of a Graph Convolution Networks with two new techniques, initial residual and identify mapping, to tackle…

Similar Papers 제목 키워드 기반

Graph Classification Based on Skeleton and Component Features

2021-02-02 · Xue Liu, Wei Wei, Xiangnan Feng, Xiaobo Cao 외

Most existing popular methods for learning graph embedding only consider fixed-order global structural features and lack structures hierarchical representation. To address this weakness, we propose a novel graph embeddin…

ClassificationGeneral ClassificationGraph ClassificationGraph Embedding

Recognizing Reduplicated Forms: Finite-State Buffered Machines

2021-08-01 · ACL (SIGMORPHON) 2021 8 · Yang Wang

Total reduplication is common in natural language phonology and morphology. However, formally as copying on reduplicants of unbounded size, unrestricted total reduplication requires computational power beyond context-fre…

Algorithms for determining transposons in gene sequences

2015-06-08 · Yue Wang

Some genes can change their relative locations in a genome. Thus for different individuals of the same species, the orders of genes might be different. Such jumping genes are called transposons. A practical problem is to…

Characterizing and Identifying Separable Graphical Models

2026-07-01 · Christopher Meek, Kayvan Sadeghi arxiv

We study a broad class of graphical models whose independencies correspond to vertex separation in mixed graphs with directed, undirected, and bidirected edges, that are capable of encoding independence structures arisin…

A Conceptually Well-Founded Characterization of Iterated Admissibility Using an "All I Know" Operator

2019-07-22 · Joseph Y. Halpern, Rafael Pass

Brandenburger, Friedenberg, and Keisler provide an epistemic characterization of iterated admissibility (IA), also known as iterated deletion of weakly dominated strategies, where uncertainty is represented using LPSs (l…

All