一次训练生成多个逻辑假设，提升预测准确率4%。
Symbolic Snapshot Ensembles
- 单次训练保存中间假设，用最小描述长度加权融合
- 在游戏与视觉推理任务上准确率提升4%，计算开销低于1%
- 适合需要高效高精度逻辑学习的场景
归纳逻辑编程（ILP）是一种逻辑机器学习方法。多数ILP算法仅通过一次训练得到单一假设。集成方法则多次运行以生成多个假设。本文提出仅运行一次ILP算法，保存中间假设，并采用最小描述长度加权策略进行融合。在多个基准测试中，包括游戏推理和视觉推理任务，该方法使预测准确率提升4%，计算开销不足1%。结果表明，该方法在保持极低额外开销的同时显著提升性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。