Knowledge Enhanced Neural Networks
Alessandro Daniele, Luciano Serafini · Frontiers in artificial intelligence and applications · 2025
In the recent past, there has been a growing interest in Neural-Symbolic Integration frameworks, i.e., hybrid systems that integrate connectionist (neural networks) and symbolic approaches: on the one hand, connectionist approaches show remarkable abilities to learn from a large amount of data in presence of noise, on the other, pure symbolic methods can perform reasoning as well as learning from few samples. In theory, by combining the two paradigms, it could be possible to obtain a system that can both learn from data and apply inference over some background knowledge. This chapter introduces KENN (Knowledge Enhanced Neural Networks), a Neural-Symbolic architecture that injects prior knowledge, codified in a set of universally quantified FOL clauses, into a neural network model. In KENN, clauses are used to generate a new final layer of the neural network which modifies the initial predictions based on the knowledge. Among the advantages of this strategy, there is the possibility to include additional learnable parameters, the clause weights, each of which represents the strength of a specific clause, meaning that the model can learn the impact of the clause on the final predictions. As a special case, if the training data contradicts a constraint, KENN learns to ignore it, making the system robust to the presence of wrong knowledge. Another advantage of KENN resides in its scalability, thanks to a flexible treatment of dependencies between the rules obtained by stacking multiple logical layers.