How can we generalise learning distributed representations of graphs?
We propose a general framework to construct unsupervised models capable of learning distributed representations of discrete structures such as graphs based on R-Convolution kernels and distributed semantics research. Our framework combines the insights and observations of Deep Graph Kernels and Graph2Vec towards a unified methodology for performing similarity learning on graphs of arbitrary size. This is exemplified by our own instance G2DR which extends Graph2Vec from labelled graphs towards unlabelled graphs and tackles issues of diagonal dominance through pruning of the subgraph vocabulary composing graphs. These changes produce new state of the art results in the downstream application of G2DR embeddings in graph classification tasks over datasets with small labelled graphs in binary classification to multi-class classification on large unlabelled graphs using an off-the-shelf support vector machine.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationClassificationGraph ClassificationMulti-class ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Step-wise Sensitivity Analysis: Identifying Partially Distributed Representations for Interpretable Deep Learning
In this paper, we introduce a novel method, called step-wise sensitivity analysis, which makes three contributions towards increasing the interpretability of Deep Neural Networks (DNNs). First, we are the first to sugge…
SensitivityObservement as Universal Measurement
Measurement theory is the cornerstone of science, but no equivalent theory underpins the huge volumes of non-numerical data now being generated. In this study, we show that replacing numbers with alternative mathematical…
Distributed representations of graphs for drug pair scoring
In this paper we study the practicality and usefulness of incorporating distributed representations of graphs into models within the context of drug pair scoring. We argue that the real world growth and update cycles of …
Transductive LearningGeneralisation of structural knowledge in the hippocampal-entorhinal system
A central problem to understanding intelligence is the concept of generalisation. This allows previously learnt structure to be exploited to solve tasks in novel situations differing in their particularities. We take ins…
graph2vec: Learning Distributed Representations of Graphs
Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs. However, many graph analytics tasks such a…
ClusteringGeneral ClassificationGraph ClassificationGraph Embedding+2