Symbolic Snapshot Ensembles
This work addresses efficiency and accuracy in ILP ensemble methods, which is incremental as it builds on existing ensemble techniques by reducing computational cost.
The paper tackles the problem of learning multiple hypotheses in inductive logic programming (ILP) by training an ILP algorithm only once and saving intermediate hypotheses, combined with a minimum description length weighting scheme, resulting in a 4% improvement in predictive accuracy with less than 1% computational overhead.
Inductive logic programming (ILP) is a form of logical machine learning. Most ILP algorithms learn a single hypothesis from a single training run. Ensemble methods train an ILP algorithm multiple times to learn multiple hypotheses. In this paper, we train an ILP algorithm only once and save intermediate hypotheses. We then combine the hypotheses using a minimum description length weighting scheme. Our experiments on multiple benchmarks, including game playing and visual reasoning, show that our approach improves predictive accuracy by 4% with less than 1% computational overhead.