Relational representation learning with spike trains
This work addresses the challenge of merging event-based computing with relational data for energy-efficient AI, though it appears incremental as it builds on prior graph embedding methods using spiking neural networks.
The paper tackles the problem of relational representation learning for knowledge graphs by proposing a model that learns spike train-based embeddings, requiring only one neuron per graph element and utilizing the temporal domain of spike patterns. The result demonstrates how relational knowledge can be integrated into spike-based systems, enabling energy-efficient AI applications.
Relational representation learning has lately received an increase in interest due to its flexibility in modeling a variety of systems like interacting particles, materials and industrial projects for, e.g., the design of spacecraft. A prominent method for dealing with relational data are knowledge graph embedding algorithms, where entities and relations of a knowledge graph are mapped to a low-dimensional vector space while preserving its semantic structure. Recently, a graph embedding method has been proposed that maps graph elements to the temporal domain of spiking neural networks. However, it relies on encoding graph elements through populations of neurons that only spike once. Here, we present a model that allows us to learn spike train-based embeddings of knowledge graphs, requiring only one neuron per graph element by fully utilizing the temporal domain of spike patterns. This coding scheme can be implemented with arbitrary spiking neuron models as long as gradients with respect to spike times can be calculated, which we demonstrate for the integrate-and-fire neuron model. In general, the presented results show how relational knowledge can be integrated into spike-based systems, opening up the possibility of merging event-based computing and relational data to build powerful and energy efficient artificial intelligence applications and reasoning systems.