Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning

2025-05-07

AI Summary

DBSCAN suffers from degraded clustering performance on multi-density-scale data due to its sensitivity to the hyperparameters ε and MinPts. To address this, we propose AR-DBSCAN, an adaptive framework based on multi-agent deep reinforcement learning (DRL). Its core contributions include: (i) a novel density-aware two-level encoding tree for self-adaptive data partitioning; (ii) a weakly supervised multi-agent DRL system formulated as a Markov decision process, which jointly optimizes ε and MinPts via information-theoretic uncertainty quantification and recursive parameter-space search; and (iii) scalable parameter discovery. Evaluated on nine synthetic and one real-world dataset, AR-DBSCAN achieves average improvements of 144.1% in normalized mutual information (NMI) and 175.3% in adjusted Rand index (ARI) over baseline methods, demonstrating significantly enhanced robustness in identifying dominant parameters under heterogeneous density distributions.

Technology Category

• Multiagent Systems: Adversarial Agents
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

DBSCAN, a well-known density-based clustering algorithm, has gained widespread popularity and usage due to its effectiveness in identifying clusters of arbitrary shapes and handling noisy data. However, it encounters challenges in producing satisfactory cluster results when confronted with datasets of varying density scales, a common scenario in real-world applications. In this paper, we propose a novel Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning cluster framework, namely AR-DBSCAN. First, we model the initial dataset as a two-level encoding tree and categorize the data vertices into distinct density partitions according to the information uncertainty determined in the encoding tree. Each partition is then assigned to an agent to find the best clustering parameters without manual assistance. The allocation is density-adaptive, enabling AR-DBSCAN to effectively handle diverse density distributions within the dataset by utilizing distinct agents for different partitions. Second, a multi-agent deep reinforcement learning guided automatic parameter searching process is designed. The process of adjusting the parameter search direction by perceiving the clustering environment is modeled as a Markov decision process. Using a weakly-supervised reward training policy network, each agent adaptively learns the optimal clustering parameters by interacting with the clusters. Third, a recursive search mechanism adaptable to the data's scale is presented, enabling efficient and controlled exploration of large parameter spaces. Extensive experiments are conducted on nine artificial datasets and a real-world dataset. The results of offline and online tasks show that AR-DBSCAN not only improves clustering accuracy by up to 144.1% and 175.3% in the NMI and ARI metrics, respectively, but also is capable of robustly finding dominant parameters.

Problem

• Adapting DBSCAN to datasets with varying density scales
• Automating clustering parameter search via multi-agent reinforcement learning
• Enhancing clustering accuracy and robustness in diverse density distributions

Innovation

• Adaptive density partitions with two-level encoding tree
• Multi-agent reinforcement learning for parameter optimization
• Recursive search mechanism for large parameter spaces