Communication Dans Un Congrès Année : 2025

Deep QMiner: Towards a Generalized Deep Q-Learning Approach for Graph Pattern Mining

Résumé

Graph pattern mining presents significant challenges due to the computational complexity of subgraph isomorphism and the scalability limitations of traditional approaches. In this paper, we introduce Deep QMiner, a deep reinforcement learning framework for discovering frequent patterns in graphs. Our approach formulates pattern mining as a sequential decision-making process where multiple agents learn to construct patterns through graph exploration. Experimental results across synthetic and real-world datasets demonstrate that Deep QMiner achieves competitive performance, offering a flexible trade-off between pattern reliability and discovery completeness. While execution times are longer than specialized neural approaches, they remain significantly faster than traditional pattern mining algorithms.

Fichier principal
Vignette du fichier
2025-GbRPR.pdf (638.17 Ko) Télécharger le fichier

Dates et versions

hal-05553114 , version 1 (14-03-2026)

Licence

Identifiants

Citer

Assaad Zeghina, Aurélie Leborgne, Florence Le Ber, Antoine Vacavant. Deep QMiner: Towards a Generalized Deep Q-Learning Approach for Graph Pattern Mining. International Workshop on Graph-Based Representations in Pattern Recognition (GbRPR 2025), Jun 2025, Caen, France. pp.134-144, ⟨10.1007/978-3-031-94139-9_13⟩. ⟨hal-05553114⟩
90 Consultations
41 Téléchargements

Altmetric

Partager

  • More