SpikE: spike-based embeddings for multi-relational graph data

TL;DR

This paper introduces SpikE, a spike-based embedding method for multi-relational knowledge graphs, enabling efficient, hardware-compatible inference that extends spiking neural networks to new industrial applications.

Contribution

The paper presents a novel spike-based algorithm for embedding knowledge graphs, representing nodes and relations through spike times, compatible with neuromorphic hardware.

Findings

Compatible with neuromorphic hardware systems

Enables spike-based inference on knowledge graphs

Extends spiking neural networks to industrial applications

Abstract

Despite the recent success of reconciling spike-based coding with the error backpropagation algorithm, spiking neural networks are still mostly applied to tasks stemming from sensory processing, operating on traditional data structures like visual or auditory data. A rich data representation that finds wide application in industry and research is the so-called knowledge graph - a graph-based structure where entities are depicted as nodes and relations between them as edges. Complex systems like molecules, social networks and industrial factory systems can be described using the common language of knowledge graphs, allowing the usage of graph embedding algorithms to make context-aware predictions in these information-packed environments. We propose a spike-based algorithm where nodes in a graph are represented by single spike times of neuron populations and relations as spike time differences between populations. Learning such spike-based embeddings only requires knowledge about spike times and spike time differences, compatible with recently proposed frameworks for training spiking neural networks. The presented model is easily mapped to current neuromorphic hardware systems and thereby moves inference on knowledge graphs into a domain where these architectures thrive, unlocking a promising industrial application area for this technology.