Neuro-symbolic computing with spiking neural networks
This addresses the challenge of applying spiking neural networks to symbolic data like knowledge graphs, which is incremental as it builds on prior spike-based graph algorithms.
The paper tackles the problem of enabling symbolic reasoning over knowledge graphs using spiking neural networks, by developing a framework that encodes symbolic and multi-relational information with spiking neurons, demonstrated through a spiking relational graph neural network.
Knowledge graphs are an expressive and widely used data structure due to their ability to integrate data from different domains in a sensible and machine-readable way. Thus, they can be used to model a variety of systems such as molecules and social networks. However, it still remains an open question how symbolic reasoning could be realized in spiking systems and, therefore, how spiking neural networks could be applied to such graph data. Here, we extend previous work on spike-based graph algorithms by demonstrating how symbolic and multi-relational information can be encoded using spiking neurons, allowing reasoning over symbolic structures like knowledge graphs with spiking neural networks. The introduced framework is enabled by combining the graph embedding paradigm and the recent progress in training spiking neural networks using error backpropagation. The presented methods are applicable to a variety of spiking neuron models and can be trained end-to-end in combination with other differentiable network architectures, which we demonstrate by implementing a spiking relational graph neural network.