Saved in:
Bibliographic Details
Main Authors: Karamete, B. Kaan, Glaser, Eli
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15906
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915088605118464
author Karamete, B. Kaan
Glaser, Eli
author_facet Karamete, B. Kaan
Glaser, Eli
contents This paper discusses how to generate general graph node embeddings from knowledge graph representations. The embedded space is composed of a number of sub-features to mimic both local affinity and remote structural relevance. These sub-feature dimensions are defined by several indicators that we speculate to catch nodal similarities, such as hop-based topological patterns, the number of overlapping labels, the transitional probabilities (markov-chain probabilities), and the cluster indices computed by our recursive spectral bisection (RSB) algorithm. These measures are flattened over the one dimensional vector space into their respective sub-component ranges such that the entire set of vector similarity functions could be used for finding similar nodes. The error is defined by the sum of pairwise square differences across a randomly selected sample of graph nodes between the assumed embeddings and the ground truth estimates as our novel loss function. The ground truth is estimated to be a combination of pairwise Jaccard similarity and the number of overlapping labels. Finally, we demonstrate a multi-variate stochastic gradient descent (SGD) algorithm to compute the weighing factors among sub-vector spaces to minimize the average error using a random sampling logic.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15906
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Ad-hoc graph node vector embedding algorithm for general knowledge graphs using Kinetica-Graph
Karamete, B. Kaan
Glaser, Eli
Machine Learning
Artificial Intelligence
This paper discusses how to generate general graph node embeddings from knowledge graph representations. The embedded space is composed of a number of sub-features to mimic both local affinity and remote structural relevance. These sub-feature dimensions are defined by several indicators that we speculate to catch nodal similarities, such as hop-based topological patterns, the number of overlapping labels, the transitional probabilities (markov-chain probabilities), and the cluster indices computed by our recursive spectral bisection (RSB) algorithm. These measures are flattened over the one dimensional vector space into their respective sub-component ranges such that the entire set of vector similarity functions could be used for finding similar nodes. The error is defined by the sum of pairwise square differences across a randomly selected sample of graph nodes between the assumed embeddings and the ground truth estimates as our novel loss function. The ground truth is estimated to be a combination of pairwise Jaccard similarity and the number of overlapping labels. Finally, we demonstrate a multi-variate stochastic gradient descent (SGD) algorithm to compute the weighing factors among sub-vector spaces to minimize the average error using a random sampling logic.
title An Ad-hoc graph node vector embedding algorithm for general knowledge graphs using Kinetica-Graph
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.15906