异质信息网络是一种信息网络,包含了节点和边,并且该节点和边具有一种或多种类型,异质信息网络包含了更更丰富的语义信息。

信息网络被定义为一个有向网络图G=(V,E),其中,V是所有实体结点的集合,E是所有关系边的集合。并且存在着一个结点类型的映射函数φ:V→A和一个边类型的映射函数Ψ:E→R,对于每个对象v∈V属于一种特殊的对象类型φ(v)∈A,每个链接e∈E属于一种特殊的关系类型Ψ(e)∈R,那么这种网络类型就是信息网络。当对象类型的种类|A|>1或者关系类型的种类|R|>1时,这种信息网络是异质信息网络,否则,它是一种同质信息网络

VIP内容

异质信息网络(HINs)也称为异质图,它是一种由多种类型的节点和边组成的复杂网络,包含了全面的信息和丰富的语义。图神经网络(GNNs)作为处理图结构数据的强大工具,在网络分析任务中表现出了卓越的性能。最近相继提出了许多基于图神经网络的异质图模型,并取得了巨大的成功。图神经网络旨在通过节点属性间的传播和聚合操作来完成图表示学习任务,因而完备的节点属性是算法运行的必要前提。

然而,大多数真实世界的场景通常存在信息不完备的问题,表现在异质信息网络中即为:常存在某些类型节点的属性完全缺失的现象,比如在包含三种类型节点的引文网络ACM中,只有paper节点含有原始属性,author和subject节点没有属性。不同于同构网络中某些结点的属性缺失或节点属性在某些维度上的缺失,异质网络中的属性缺失程度更大、更为复杂。已有的一些异质网络表示学习方法主要针对模型的改进来提高算法性能,对于属性的缺失采用一些简单的手工插补方法(例如平均插补、one-hot向量插补)进行补全。这些方法将属性补全与图表示学习过程分开,忽略了准确的属性对于下游任务的重要性,因此很难使用简单插补后的属性来保证模型的性能。实际上,准确的输入是任何模型实现性能提升的基础,在异质网络更为复杂的属性缺失情况下,准确的属性变得更为重要。

因此,本文认为与设计新的模型相比,科学准确地补全缺失的属性应该成为异质网络分析任务的另一个重要研究方向,并且属性补全和模型设计可以相互增强。基于此,本文提出以可学习的方式来补全缺失的属性,并通过采用属性补全与图神经网络模型相互增强的模式来构建一个针对属性缺失异质网络的异质图神经网络通用框架(HGNN-AC)。

HGNN-AC共包含四个关键设计:基于拓扑结构的先验知识预学习、基于注意力机制的属性补全、弱监督重构损失的设计和端到端模型的构建。本文在三个真实世界的异质网络上进行了大量的实验,结果表明所提出的框架优于最新的基准。

成为VIP会员查看完整内容
0
8

热门内容

Events are happening in real-world and real-time, which can be planned and organized occasions involving multiple people and objects. Social media platforms publish a lot of text messages containing public events with comprehensive topics. However, mining social events is challenging due to the heterogeneous event elements in texts and explicit and implicit social network structures. In this paper, we design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network (HIN) integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model. We propose a Knowledgeable meta-paths Instances based social Event Similarity (KIES) between events and build a weighted adjacent matrix as input to the PP-GCN model. Comprehensive experiments on real data collections are conducted to compare various social event detection and clustering tasks. Experimental results demonstrate that our proposed framework outperforms other alternative social event categorization techniques.

0
8
下载
预览

最新内容

Graph Convolutional Network (GCN) has achieved extraordinary success in learning effective task-specific representations of nodes in graphs. However, regarding Heterogeneous Information Network (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness and interpretability; (2) they often need to generate intermediate meta-path based dense graphs, which leads to high computational complexity. To address the above issues, we propose an interpretable and efficient Heterogeneous Graph Convolutional Network (ie-HGCN) to learn the representations of objects in HINs. It is designed as a hierarchical aggregation architecture, i.e., object-level aggregation first, followed by type-level aggregation. The novel architecture can automatically extract useful meta-paths for each object from all possible meta-paths (within a length limit), which brings good model interpretability. It can also reduce the computational cost by avoiding intermediate HIN transformation and neighborhood attention. We provide theoretical analysis about the proposed ie-HGCN in terms of evaluating the usefulness of all possible meta-paths, its connection to the spectral graph convolution on HINs, and its quasi-linear time complexity. Extensive experiments on three real network datasets demonstrate the superiority of ie-HGCN over the state-of-the-art methods.

0
0
下载
预览

最新论文

Graph Convolutional Network (GCN) has achieved extraordinary success in learning effective task-specific representations of nodes in graphs. However, regarding Heterogeneous Information Network (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness and interpretability; (2) they often need to generate intermediate meta-path based dense graphs, which leads to high computational complexity. To address the above issues, we propose an interpretable and efficient Heterogeneous Graph Convolutional Network (ie-HGCN) to learn the representations of objects in HINs. It is designed as a hierarchical aggregation architecture, i.e., object-level aggregation first, followed by type-level aggregation. The novel architecture can automatically extract useful meta-paths for each object from all possible meta-paths (within a length limit), which brings good model interpretability. It can also reduce the computational cost by avoiding intermediate HIN transformation and neighborhood attention. We provide theoretical analysis about the proposed ie-HGCN in terms of evaluating the usefulness of all possible meta-paths, its connection to the spectral graph convolution on HINs, and its quasi-linear time complexity. Extensive experiments on three real network datasets demonstrate the superiority of ie-HGCN over the state-of-the-art methods.

0
0
下载
预览
Top