Learning through structure: towards deep neuromorphic knowledge graph embeddings

TL;DR

This paper introduces a novel approach combining frozen graph neural networks with knowledge graph embeddings, enabling efficient, neuromorphic-compatible reasoning with speed and memory benefits, and pioneering event-based sparse algorithms for neuromorphic hardware.

Contribution

It proposes mapping deep graph learning architectures to neuromorphic systems using frozen GNNs and extends this to spiking neural networks for event-based processing.

Findings

Significant speedup and memory reduction on conventional hardware.

Competitive performance maintained with frozen GNNs.

Novel event-based sparse knowledge graph embedding algorithm for neuromorphic hardware.

Abstract

Computing latent representations for graph-structured data is an ubiquitous learning task in many industrial and academic applications ranging from molecule synthetization to social network analysis and recommender systems. Knowledge graphs are among the most popular and widely used data representations related to the Semantic Web. Next to structuring factual knowledge in a machine-readable format, knowledge graphs serve as the backbone of many artificial intelligence applications and allow the ingestion of context information into various learning algorithms. Graph neural networks attempt to encode graph structures in low-dimensional vector spaces via a message passing heuristic between neighboring nodes. Over the recent years, a multitude of different graph neural network architectures demonstrated ground-breaking performances in many learning tasks. In this work, we propose a strategy to map deep graph learning architectures for knowledge graph reasoning to neuromorphic architectures. Based on the insight that randomly initialized and untrained (i.e., frozen) graph neural networks are able to preserve local graph structures, we compose a frozen neural network with shallow knowledge graph embedding models. We experimentally show that already on conventional computing hardware, this leads to a significant speedup and memory reduction while maintaining a competitive performance level. Moreover, we extend the frozen architecture to spiking neural networks, introducing a novel, event-based and highly sparse knowledge graph embedding algorithm that is suitable for implementation in neuromorphic hardware.