GrAMME: Semi-Supervised Learning using Multi-layered Graph Attention Models
Uday Shankar Shanthamallu∗, Jayaraman J. Thiagarajan†, Huan Song‡, and Andreas Spanias∗ ∗SenSIP Center, School of ECEE, Arizona State University, †Lawrence Livermore National Labs, ‡Bosch Research North America
Abstract
Modern data analysis pipelines are becoming increasingly complex due to the presence of multi-view information sources. While graphs are effective in modeling complex relationships, in many scenarios a single graph is rarely sufficient to succinctly represent all interactions, and hence multi-layered graphs have become popular. Though this leads to richer representations, extending solutions from the single-graph case is not straightforward. Consequently, there is a strong need for novel solutions to solve classical problems, such as node classification, in the multi-layered case. In this paper, we consider the problem of semi-supervised learning with multi-layered graphs. Though deep network embeddings, e.g. DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective. To this end, we propose to use attention models for effective feature learning, and develop two novel architectures, GrAMME-SG and GrAMME-Fusion, that exploit the inter-layer dependencies for building multi-layered graph embeddings. Using empirical studies on several benchmark datasets, we evaluate the proposed ap
中文速览
多层图（multi-layered graph）中不同层之间的关系如何被有效利用，一直是半监督节点分类任务的难题——现有方法要么依赖DeepWalk等网络嵌入再接分类器、要么依赖复杂参数模型，效果和灵活性都有局限。本文提出GrAMME框架，核心思路是用图注意力机制（graph attention network）直接以端到端方式学习多层图的节点表示，并设计了两种架构：GrAMME-SG通过引入层间虚拟边构建"超图"来统一建模跨层依赖，GrAMME-Fusion则为每层独立训练注意力模型、再通过融合得到共识表示。一个重要发现是，即便数据集没有节点属性，直接用随机特征作为输入也能取得很好的效果，不必依赖DeepWalk这类预训练嵌入。在多个基准多层图数据集上的实验表明，GrAMME在节点分类准确率上显著超越现有最优方法，这为多视角关系数据的分析提供了一种简洁而强大的新思路。
原文 arXiv:1810.01405;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1810.01405v2