A Degeneracy Framework for Graph Similarity

@inproceedings{Nikolentzos2018ADF,
  title={A Degeneracy Framework for Graph Similarity},
  author={Giannis Nikolentzos and Polykarpos Meladianos and Stratis Limnios and Michalis Vazirgiannis},
  booktitle={IJCAI},
  year={2018}
}
The problem of accurately measuring the similarity between graphs is at the core of many applications in a variety of disciplines. Most existing methods for graph similarity focus either on local or on global properties of graphs. However, even if graphs seem very similar from a local or a global perspective, they may exhibit different structure at different scales. In this paper, we present a general framework for graph similarity which takes into account structure at multiple different scales… 

Figures and Tables from this paper

A survey on graph kernels
TLDR
This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years and describes and categorizes graph kernels based on properties inherent to their design, such as the nature of their extracted graph features, their method of computation and their applicability to problems in practice.
Similarity Evaluation on Labeled Graphs via Hierarchical Core Decomposition
TLDR
This paper develops a novel graph similarity measure that overcomes the above limitations and identifies similar graphs and extends to large-scale graphs.
Graph Filtration Kernels
TLDR
This work proposes a family of graph kernels that incorporate existence intervals of features and empirically validate the expressive power of the graph kernels and show significant improvements over state-of-the-art graph kernels in terms of predictive performance on various real-world benchmark datasets.
Graph Edit Distance Computation via Graph Neural Networks
TLDR
This work proposes a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance, and suggests SimGNN provides a new direction for future research on graph similarity computation and graph similarity search.
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
TLDR
This work proposes a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance, and suggests SimGNN provides a new direction for future research on graph similarity computation and graph similarity search.
The core decomposition of networks: theory, algorithms and applications
TLDR
In this survey, an in-depth discussion of core decomposition is performed, focusing mainly on the basic theory and fundamental concepts, the algorithmic techniques proposed for computing it efficiently under different settings, and the applications that can benefit significantly from it.
Machine Learning on Graphs with Kernels
TLDR
This tutorial is to offer a comprehensive presentation of a wide range of graph kernels, and to describe their key applications, and will also offer to the participants hands-on experience in applying graph kernels to classification problems.
Using Laplacian Spectrum as Graph Feature Representation
TLDR
This work first reminds and shows that GLS satisfies the aforementioned key attributes, using a graph perturbation approach, and derives bounds for the distance between two GLS that are related to the \textit{divergence to isomorphism}, a standard computationally expensive graph divergence.
About Graph Degeneracy, Representation Learning and Scalability
TLDR
This paper presents two techniques taking advantage of a degeneracy property of Graphs - the K-Core Decomposition to reduce the time and memory consumption of walk-based Graph Representation Learning algorithms.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 32 REFERENCES
Matching Node Embeddings for Graph Similarity
TLDR
This paper presents a graph kernel based on the Pyramid Match kernel that finds an approximate correspondence between the sets of vectors of the two graphs and evaluates the proposed methods on several benchmark datasets for graph classification and compares their performance to state-of-the-art graph kernels.
Global graph kernels using geometric embeddings
TLDR
Empirical results on classification of synthesized graphs with important global properties as well as established benchmark graph datasets are given, showing that the accuracy of the kernels is better than or competitive to existing graph kernels.
Weisfeiler-Lehman Graph Kernels
TLDR
A family of efficient kernels for large graphs with discrete node labels based on the Weisfeiler-Lehman test of isomorphism on graphs that outperform state-of-the-art graph kernels on several graph classification benchmark data sets in terms of accuracy and runtime.
Learning with Similarity Functions on Graphs using Matchings of Geometric Embeddings
TLDR
This work develops and applies the Balcan-Blum-Srebro (BBS) theory of classification via similarity functions (which are not necessarily kernels) to the problem of graph classification and shows that classifying graphs using matchings of geometric embeddings outperforms the previous state-of-the-art methods.
CoreCluster: A Degeneracy Based Graph Clustering Framework
TLDR
This article presents CORECLUSTER, an efficient graph clustering framework based on the concept of graph degeneracy, that can be used along with any knowngraph clustering algorithm.
Subgraph Matching Kernels for Attributed Graphs
TLDR
It is shown that subgraph matching kernels generalize several known kernels and is proposed a graph-theoretical algorithm inspired by a classical relation between common subgraphs of two graphs and cliques in their product graph observed by Levi (1973).
Shortest-path kernels on graphs
TLDR
This work proposes graph kernels based on shortest paths, which are computable in polynomial time, retain expressivity and are still positive definite, and shows significantly higher classification accuracy than walk-based kernels.
Propagation kernels: efficient graph kernels from propagated information
TLDR
It is shown that if the graphs at hand have a regular structure, one can exploit this regularity to scale the kernel computation to large databases of graphs with thousands of nodes, and can be considerably faster than state-of-the-art approaches without sacrificing predictive performance.
Shortest-Path Graph Kernels for Document Similarity
TLDR
Experimental results on a range of datasets showed that the proposed approach outperforms traditional techniques and is capable of measuring more accurately the similarity between two documents.
The Multiscale Laplacian Graph Kernel
TLDR
The Multiscale Laplacian Graph kernels (MLG kernels) that are defined in this paper can account for structure at a range of different scales by building a hierarchy of nested subgraphs by introducing a randomized projection procedure.
...
1
2
3
4
...