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

05/16/2020
by   Benedek Rozemberczki, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2019

Efficient Representation Learning Using Random Walks for Dynamic graphs

An important part of many machine learning workflows on graphs is vertex...
research
06/13/2022

Graph Comparison Based on Adjacency Function Matrix

In this paper, we present a new metric distance for comparing two large ...
research
04/28/2017

Deep Feature Learning for Graphs

This paper presents a general graph representation learning framework ca...
research
09/14/2017

A Framework for Generalizing Graph-based Representation Learning Methods

Random walks are at the heart of many existing deep learning algorithms ...
research
02/07/2018

Learning Role-based Graph Embeddings

Random walks are at the heart of many existing network embedding methods...
research
08/29/2022

The PWLR Graph Representation: A Persistent Weisfeiler-Lehman scheme with Random Walks for Graph Classification

This paper presents the Persistent Weisfeiler-Lehman Random walk scheme ...

Please sign up or login with your details

Forgot password? Click here to reset