方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 贝叶斯关联规则× | 半监督关联规则× | |
|---|---|---|
| 领域 | 机器学习 | 机器学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 1994–1995 | 2003–2010s |
| 提出者≠ | Heckerman, D. et al.; Agrawal, R. & Srikant, R. | Liu, B.; Hsu, W.; Ma, Y. (and subsequent researchers) |
| 类型≠ | Probabilistic rule mining | Pattern mining with partial supervision |
| 开创性文献≠ | Heckerman, D., Geiger, D., & Chickering, D. M. (1995). Learning Bayesian networks: The combination of knowledge and statistical data. Machine Learning, 20(3), 197–243. DOI ↗ | Liu, B., Hsu, W., & Ma, Y. (2003). Integrating Classification and Association Rule Mining. In Proceedings of the 4th IEEE International Conference on Data Mining (ICDM), pp. 339–346. link ↗ |
| 别名 | Bayesian rule learning, probabilistic association rules, Bayesian itemset mining, BAR | semi-supervised ARM, label-guided association rule mining, constrained association rule mining, semi-supervised pattern discovery |
| 相关≠ | 6 | 4 |
| 摘要≠ | Bayesian Association Rules extend classical association rule mining by placing a prior probability distribution over rules and scoring them by their posterior probability given the data. Rather than thresholding on raw support and confidence counts, this Bayesian framework naturally penalises complexity, corrects for multiple comparisons, and produces calibrated probabilistic rule strengths across transactional or categorical datasets. | Semi-supervised association rule mining extends classical association rule learning by incorporating a small amount of labeled data alongside a larger unlabeled dataset. It uses known class information or user-provided constraints to guide the discovery of rules that are both statistically frequent and semantically meaningful, bridging unsupervised pattern mining with light supervision. |
| ScholarGate数据集 ↗ |
|
|