用最小消息长度学习逻辑规则，兼顾准确与泛化。
Learning Logical Rules using Minimum Message Length
- 基于贝叶斯框架，通过先验偏好通用程序、似然偏好精确程序。
- 在游戏和药物设计任务中显著优于传统最小描述长度方法。
- 仅需正例即可学习，对数据不平衡不敏感，适合小样本场景。
统一概率与逻辑学习是人工智能中的关键挑战。我们提出一种贝叶斯归纳逻辑编程方法，从噪声数据中学习最小消息长度假设。该方法通过先验（偏好更通用的程序）与似然（偏好更准确的程序）平衡假设复杂度与数据拟合度。在游戏博弈与药物设计等多个领域上的实验表明，本方法显著优于先前的最小描述长度学习方法。结果还显示，该方法具备数据高效性，对样本分布不敏感，甚至可仅用正例完成学习。
原文摘要 · Abstract (English)
Unifying probabilistic and logical learning is a key challenge in AI. We introduce a Bayesian inductive logic programming approach that learns minimum message length hypotheses from noisy data. Our approach balances hypothesis complexity and data fit through priors, which favour more general programs, and a likelihood, which favours accurate programs. Our experiments on several domains, including game playing and drug design, show that our method significantly outperforms previous methods, notably those that learn minimum description length programs. Our results also show that our approach is data-efficient and insensitive to example balance, including the ability to learn from exclusively positive examples.
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。