Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation
This addresses a limitation in inductive logic programming for applications with uncertain data, though it appears incremental as it builds on existing ILP methods.
The paper tackles the problem of learning inductive logic programs from probabilistic background knowledge, such as noisy sensory data, by proposing Propper, which integrates neurosymbolic inference and relaxation techniques, achieving learning from as few as 8 examples and outperforming binary ILP and Graph Neural Networks.
Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such as a Graph Neural Network.