arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.09708cs.LGcs.AI
收藏

GraphRARE:基于相对熵的强化学习增强图神经网络

GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy

Beihang University(北京航空航天大学);Nanyang Technological University(南洋理工大学);RMIT University(皇家墨尔本理工大学);Beijing University of Technology(北京工业大学)

Tianhao Peng, Wenjun Wu, Haitao Yuan, Zhifeng Bao, Zhao Pengrui, Xin Yu, Xuetao Lin, Yu Liang, Yanjun Pu

AI总结:

针对现有图神经网络在异质性图上表现不佳的问题,本文提出结合节点相对熵与深度强化学习的GraphRARE框架,通过优化图拓扑提升节点分类性能,在7个真实数据集上验证了有效性。

摘要:

图神经网络(GNNs)在基于图的分析任务中已展现出优势。然而,现有大多数方法都基于同质性假设,在异质性图上表现不佳——这类图中相连的节点具有不同的特征和类别标签,且语义相关的节点可能相距多跳。为解决这一局限,本文提出GraphRARE,这是一个基于节点相对熵和深度强化学习的通用框架,用于增强GNNs的表达能力。该框架采用一种兼顾节点特征与结构相似性的创新节点相对熵,来衡量节点对之间的互信息。此外,为避免远程节点的有用信息与噪声混合导致的次优解,本文开发了一种基于深度强化学习的算法来优化图拓扑结构,该算法根据定义的节点相对熵选择信息丰富的节点并丢弃噪声节点。本文在7个真实世界数据集上开展了大量实验,实验结果证明了GraphRARE在节点分类任务上的优越性,以及其优化原始图拓扑结构的能力。

英文摘要:

Graph neural networks (GNNs) have shown advantages in graph-based analysis tasks. However, most existing methods have the homogeneity assumption and show poor performance on heterophilic graphs, where the linked nodes have dissimilar features and different class labels, and the semantically related nodes might be multi-hop away. To address this limitation, this paper presents GraphRARE, a general framework built upon node relative entropy and deep reinforcement learning, to strengthen the expressive capability of GNNs. An innovative node relative entropy, which considers node features and structural similarity, is used to measure mutual information between node pairs. In addition, to avoid the sub-optimal solutions caused by mixing useful information and noises of remote nodes, a deep reinforcement learning-based algorithm is developed to optimize the graph topology. This algorithm selects informative nodes and discards noisy nodes based on the defined node relative entropy. Extensive experiments are conducted on seven real-world datasets. The experimental results demonstrate the superiority of GraphRARE in node classification and its capability to optimize the original graph topology.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑