Deep Graph Kernels
In this paper, we present Deep Graph Kernels (DGK), a unified framework to learn latent representations of sub-structures for graphs, inspired by latest advancements in language modeling and deep learning. Our framework leverages the dependency information between sub-structures by learning their latent representations. We demonstrate instances of our framework on three popular graph kernels, namely Graphlet kernels, Weisfeiler-Lehman subtree kernels, and Shortest-Path graph kernels. Our experiments on several benchmark datasets show that Deep Graph Kernels achieve significant improvements in classification accuracy over state-of-the-art graph kernels.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph ClassificationLanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Subgraph Matching Kernels for Attributed Graphs
We propose graph kernels based on subgraph matchings, i.e. structure-preserving bijections between subgraphs. While recently proposed kernels based on common subgraphs (Wale et al., 2008; Shervashidze et al., 2009) in ge…
General ClassificationGraph Kernels: A Survey
Graph kernels have attracted a lot of attention during the last decade, and have evolved into a rapidly developing branch of learning on structured data. During the past 20 years, the considerable research activity that …
Graph ClassificationSurveyGraph Kernels Based on Linear Patterns: Theoretical and Experimental Comparisons
Graph kernels are powerful tools to bridge the gap between machine learning and data encoded as graphs. Most graph kernels are based on the decomposition of graphs into a set of patterns. The similarity between two graph…
BIG-bench Machine LearningGraph ClassificationHAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification
In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most existing classical graph kernels, the pro…
Graph ClassificationFaster Kernels for Graphs with Continuous Attributes via Hashing
While state-of-the-art kernels for graphs with discrete labels scale well to graphs with thousands of nodes, the few existing kernels for graphs with continuous attributes, unfortunately, do not scale well. To overcome t…