arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.04537cs.LGcs.IR
收藏

通过深度强化学习实现DBSCAN自动化

Automating DBSCAN via Deep Reinforcement Learning

Beihang University(北京航空航天大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校);Macquarie University(麦考瑞大学)

Ruitong Zhang, Hao Peng, Yingtong Dou, Jia Wu, Qingyun Sun, Jingyi Zhang, Philip S. Yu

摘要:

DBSCAN以其简单实用的特点被广泛应用于科学和工程领域。然而,由于它的高敏感性参数,聚类结果的准确性在很大程度上依赖于实际经验。在本文中,我们首先提出了一种新的深度强化学习引导的自动DBSCAN参数搜索框架,即DRL-DBSCAN。该框架将聚类环境视为马尔可夫决策过程,将参数搜索方向的调整过程建模,以在不需要人工辅助的情况下找到最佳聚类参数。DRL-DBSCAN通过与聚类交互,使用弱监督奖励训练策略网络学习不同特征分布的最佳聚类参数搜索策略。此外,我们还提出了一个递归搜索机制驱动的规模的数据,以有效地和可控地处理大参数空间。基于所提出的四种工作模式,在五个人工和真实世界的数据集上进行了广泛的实验。离线和在线任务的结果表明,DRL-DBSCAN不仅持续提高DBSCAN聚类精度分别高达26%和25%,而且可以稳定地找到具有高计算效率的主导参数。该代码可在https://github.com/RingBDStack/DRL-DBSCAN上获得。

英文摘要:

DBSCAN is widely used in many scientific and engineering fields because of its simplicity and practicality. However, due to its high sensitivity parameters, the accuracy of the clustering result depends heavily on practical experience. In this paper, we first propose a novel Deep Reinforcement Learning guided automatic DBSCAN parameters search framework, namely DRL-DBSCAN. The framework models the process of adjusting the parameter search direction by perceiving the clustering environment as a Markov decision process, which aims to find the best clustering parameters without manual assistance. DRL-DBSCAN learns the optimal clustering parameter search policy for different feature distributions via interacting with the clusters, using a weakly-supervised reward training policy network. In addition, we also present a recursive search mechanism driven by the scale of the data to efficiently and controllably process large parameter spaces. Extensive experiments are conducted on five artificial and real-world datasets based on the proposed four working modes. The results of offline and online tasks show that the DRL-DBSCAN not only consistently improves DBSCAN clustering accuracy by up to 26% and 25% respectively, but also can stably find the dominant parameters with high computational efficiency. The code is available at https://github.com/RingBDStack/DRL-DBSCAN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑