The graphlet spectrum

By Risi Kondor, Nino Shervashidze, Karsten M. Borgwardt. 2009

82 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Christopher Morris
2. Zhi-Li Zhang
3. Saurabh Verma
4. Nils M. Kriege
5. Fredrik D. Johansson
6. Petra Mutzel
7. Mathias Niepert
8. Hanghang Tong

In Computer Vision and Pattern Recognition

1. Christopher Morris
2. Zhi-Li Zhang
3. Saurabh Verma
4. Nils M. Kriege
5. Fredrik D. Johansson
6. Nino Shervashidze
7. Mathias Niepert
8. Konstantin Kutzkov

In Graph Learning

1. Christopher Morris
2. Zhi-Li Zhang
3. Saurabh Verma
4. Nils M. Kriege
5. Fredrik D. Johansson
6. William L. Hamilton
7. Karsten M. Borgwardt
8. Aynaz Taheri

Citations in the corpus

• Learning Convolutional Neural Networks for Graphs (2016, background): “Two representative classes of kernels are the skew spectrum kernel (Kondor & Borgwardt, 2008) and kernels based on graphlets (Kondor et al., 2009; Shervashidze et al., 2009).”
• Weisfeiler-Lehman Graph Kernels (2011, methodology): “Recently proposed group theoretical approaches for representing graphs, the skew spectrum (Kondor and Borgwardt, 2008) and the graphlet spectrum (Kondor et al., 2009) can also be used for defining similarity measures on graphs that are computable in polynomial time.”
• Graph Capsule Convolutional Neural Networks (2018, background): “Graphlet spectrum (Kondor et al., 2009) improves upon this work by including labeled information; it also accounts for the relative position of subgraphs within a graph.”
• A survey on graph kernels (2019, methodology): “To remedy this, Shervashidze et al. (2009) proposed two algorithms for speeding up the computation time of the feature map for k in { 3, 4 } .”
• Fast Random Walk Graph Kernel (2012, background): “There are three major groups in graph kernels: kernels based on walks and paths [9, 20, 10, 3, 42, 43], kernels based on limited-size subgraphs [16, 36, 21], and kernels based on subtree patterns [25, 35, 15].”
• Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs (2017, background): “And, 2 strong Graph Spectrums: the Skew Spectrum (SGS) [20], Graphlet Spectrum (GS) [22].”
• UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats (2020, background): “Whole-system provenance graphs can grow large quickly [100], so NP-complete [42], [95] and even polynomial algorithms [71], [122] are too computationally expensive for streaming settings.”