Semantics-Aware Caching for Concept Learning
This work significantly improves the efficiency of concept learning for researchers and practitioners working with description logics and knowledge bases, particularly for complex problems.
This paper addresses the runtime challenge in concept learning, which often requires thousands of instance retrieval calls. The authors introduce a semantics-aware caching approach that reduces the runtime of concept retrieval and learning by an order of magnitude across 5 datasets and various reasoners.
Concept learning is a form of supervised machine learning that operates on knowledge bases in description logics. State-of-the-art concept learners often rely on an iterative search through a countably infinite concept space. In each iteration, they retrieve instances of candidate solutions to select the best concept for the next iteration. While simple learning problems might require a few dozen instance retrieval calls to find a fitting solution, complex learning problems might necessitate thousands of calls. We alleviate the resulting runtime challenge by presenting a semantics-aware caching approach. Our cache is essentially a subsumption-aware map that links concepts to a set of instances via crisp set operations. Our experiments on 5 datasets with 4 symbolic reasoners, a neuro-symbolic reasoner, and 5 popular pagination policies demonstrate that our cache can reduce the runtime of concept retrieval and concept learning by an order of magnitude while being effective for both symbolic and neuro-symbolic reasoners.