W Xiong, T Hoang, WY Wang - arXiv preprint arXiv:1707.06690, 2017 - arxiv.org
… learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learn… based on knowledge graph embeddings, …
… Similarly, graph neural networks (GNNs) have also demonstrated their superior … in supervised learning for graphstructured data. In recent times, the fusion of GNN with DRL for graph-…
M Nie, D Chen, D Wang - IEEE Transactions on Emerging …, 2023 - ieeexplore.ieee.org
… on graphstructured environments. We show the times cited and publications over time of Graph ReinforcementLearning … 1 to prove the fusion of graph mining methods with RL for graph-…
… study the problem of using reinforcementlearning to search graph neural architectures, which has the potential to save a lot of manual work for designing graph neural architectures. …
… general framework for learning how to control such dynamic processes on graphs. … graphs. Our architecture prioritizes interventions on a temporal multi-graph by leveraging deep Graph …
C Shan, Y Shen, Y Zhang, X Li… - Advances in Neural …, 2021 - proceedings.neurips.cc
… To explain a graph label, we design a seed locator to learn the node that influences the graph label the most. Iterative graph generation is the key module in our method, which …
H Sun, J Zhong, Y Ma, Z Han, K He - arXiv preprint arXiv:2109.04101, 2021 - arxiv.org
… Temporal knowledge graph (TKG) reasoning is a crucial task that has gained … reinforcement learning method for forecasting. Specifically, the agent travels on historical knowledge graph …
… a graph mask, leveraging our knowledge graph at that timestep Gt to streamline the object decoding process. Formally, the graph … found within the knowledge graph Gt and vocabulary V …
… , we introduce Graph Pointer Networks (GPNs) trained using reinforcementlearning (RL) for … GPNs build upon Pointer Networks by introducing a graph embedding layer on the input, …