Efficient multi-relational network representation using primes

Multi-relational networks play an important role in today's world and are utilized to capture complex relationships between the data. Their applications span many domains such as biomedical, financial, social, etc., and because of their increasing usability, it becomes crucial to find efficient ways to deal with the added complexity of multiple layers. In this work, we propose a novel approach to represent these complex networks using a single aggregated adjacency matrix, by utilizing primes as surrogates for the relations. Due to the fundamental theorem of arithmetic, this allows for a lossless, compact representation of the whole multi-relational graph, using a single adjacency matrix. Moreover, this representation enables the fast computation of multi-hop adjacency matrices, that can be useful for a variety of downstream tasks. We present simple and complex tasks in which this representation can be useful and showcase its efficiency and performance. Finally, we also provide insights on the advantages and the open challenges that still need to be addressed and motivate future work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/17/2023

Analysing Biomedical Knowledge Graphs using Prime Adjacency Matrices

Most phenomena related to biomedical tasks are inherently complex, and i...
research
01/20/2023

Exploring ordered patterns in the adjacency matrix for improving machine learning on complex networks

The use of complex networks as a modern approach to understanding the wo...
research
05/05/2022

Relational Representation Learning in Visually-Rich Documents

Relational understanding is critical for a number of visually-rich docum...
research
02/13/2021

Bridging Graph Neural Networks and Statistical Relational Learning: Relational One-Class GCN

We consider the problem of learning Graph Convolutional Networks (GCNs) ...
research
04/29/2021

Matrix function-based centrality measures for layer-coupled multiplex networks

Centrality measures identify the most important nodes in a complex netwo...
research
09/09/2016

Some Advances in Role Discovery in Graphs

Role discovery in graphs is an emerging area that allows analysis of com...
research
07/29/2022

Similarity matrix average for aggregating multiplex networks

We introduce a methodology based on averaging similarity matrices with t...

Please sign up or login with your details

Forgot password? Click here to reset