Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a flexible notion of characteristic functions defined on graph vertices to describe the distribution of vertex features at multiple scales. We introduce FEATHER, a computationally efficient algorithm to calculate a specific variant of these characteristic functions where the probability weights of the characteristic function are defined as the transition probabilities of random walks. We argue that features extracted by this procedure are useful for node level machine learning tasks. We discuss the pooling of these node representations, resulting in compact descriptors of graphs that can serve as features for graph classification algorithms. We analytically prove that FEATHER describes isomorphic graphs with the same representation and exhibits robustness to data corruption. Using the node feature characteristic functions we define parametric models where evaluation points of the functions are learned parameters of supervised classifiers. Experiments on real world large datasets show that our proposed algorithm creates high quality representations, performs transfer learning efficiently, exhibits robustness to hyperparameter changes and scales linearly with the input size.
Original languageEnglish
Title of host publicationProceedings of the 29th ACM International Conference on Information & Knowledge Management
Place of PublicationNew York, NY, USA
PublisherACM Association for Computing Machinery
Pages1325–1334
Number of pages10
ISBN (Print)9781450368599
DOIs
Publication statusPublished - 19 Oct 2020
Event29th ACM International Conference on Information and Knowledge Management - Omline Conference
Duration: 19 Oct 202023 Oct 2020
https://www.cikm2020.org/index.html

Conference

Conference29th ACM International Conference on Information and Knowledge Management
Abbreviated titleCIKM 2020
CityOmline Conference
Period19/10/2023/10/20
Internet address

Keywords

  • graph neural network
  • node embedding
  • node classification
  • graph fingerprint
  • graph embedding
  • graph classification

Fingerprint

Dive into the research topics of 'Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models'. Together they form a unique fingerprint.

Cite this