Qi Sun

Direct and indirect reinforcement learning

2021 · International Journal of Intelligent Systems

Reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision-making and control tasks. In this paper, we classify RL into direct and indirect RL according to how they seek the …

Stochastic Training of Residual Networks: a Differential Equation\n Viewpoint

2018 · arXiv (Cornell University)

During the last few years, significant attention has been paid to the\nstochastic training of artificial neural networks, which is known as an\neffective regularization approach that helps improve the generalization\ncapability of trained models. In this work, …

Research on Maintenance Testing Technology of Information Equipment Based on Cloud Testing

2024

Aiming at the low degree of network, intelligence and universality in the maintenance and testing of information equipment in current weapons and equipment, this paper explores the key cloud testing technologies of “network sharing of …

Federated Subgraph Learning via Global-Knowledge-Guided Node Generation

2025 · Sensors

Federated graph learning (FGL) is a combination of graph representation learning and federated learning that utilizes graph neural networks (GNNs) to process complex graph-structured data while addressing data silo issues. However, during the local training …

Imbalanced Graph Classification based on Graph-of-Graph Neural Networks and Augmented Graph Generator

2025

Graph classification has significant applications in various domains, including chemical molecular structure prediction, social network analysis, recommendation systems, and biological network analysis, and has received considerable attention in recent years. However, real-world graph datasets often …