Q-HeteLearn: A Progressive Learning approach for Classifying Meta-Paths in Heterogeneous Information Networks

Sadhana Kodali
2020 International Journal of Emerging Trends in Engineering Research  
Reinforcement learning is a machine learning paradigm which has a number of applications in gaming, stock prediction, robot navigation etc. The reinforcement learning can be applied to complex real-world tasks which have adjustable problem spaces. In this paper a novel approach called Q-HeteLearn a Progressive Learning method is introduced to classify the objects by traversing the meta-paths in the Heterogeneous Information Networks. The proposed approach showed best results when compared to a
more » ... raditional learning strategy called the Q-Learning and also the comparative study showed a better result with Deep Q-Learning. The concept of Q-HeteLearn which is a Progressive Learning technique is introduced to improve the swift traversal of the objects in the meta-paths and to classify them.
doi:10.30534/ijeter/2020/35832020 fatcat:m6xvtws7mzhyzb526w4eme57da