Learning Higher-Order Programs without Meta-Interpretive Learning
This work addresses the problem of automating program learning for AI researchers, offering an incremental improvement over existing higher-order ILP systems.
The paper tackled the challenge of learning complex programs in inductive logic programming by extending the Learning From Failures paradigm with higher-order definitions, resulting in significantly improved learning performance without requiring burdensome human guidance.
Learning complex programs through inductive logic programming (ILP) remains a formidable challenge. Existing higher-order enabled ILP systems show improved accuracy and learning performance, though remain hampered by the limitations of the underlying learning mechanism. Experimental results show that our extension of the versatile Learning From Failures paradigm by higher-order definitions significantly improves learning performance without the burdensome human guidance required by existing systems. Our theoretical framework captures a class of higher-order definitions preserving soundness of existing subsumption-based pruning methods.