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 2502.02302cs.LGcs.AI
收藏

EdgeGFL:重新思考图特征偏好学习中的边信息

EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning

College of Cyber Security, Jinan University(暨南大学网络空间安全学院);School of Management, Jinan University(暨南大学管理学院);School of Computer, Sun Yat-sen University(中山大学计算机学院);School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);Guangdong Key Laboratory of Data Security and Privacy Preserving(广东省数据安全与隐私保护重点实验室)

Shengda Zhuo, Jiwang Fang, Hongguang Lin, Yin Tang, Min Chen, Changdong Wang, Shuqiang Huang

AI总结:

本文提出EdgeGFL框架,通过多维边特征矩阵构建多通道滤波器并融合关系表示学习,解决GNN中节点与边特征学习脱节问题,提升节点表示质量,在四个异构图数据集上验证了有效性。

摘要:

图神经网络(GNN)在处理非欧几里得数据方面具有显著优势,已被广泛应用于各个领域,因此近年来受到越来越多的关注。GNN模型的框架主要包括信息传播阶段和聚合阶段,分别将节点和边视为信息实体和传播通道。然而,大多数现有GNN模型面临节点特征信息与边特征信息相互脱节的挑战,因为这些模型通常将边特征和节点特征的学习视为相互独立的任务。为了解决这一局限性,我们旨在开发一个边赋能的图特征偏好学习框架,该框架能够捕获边嵌入以辅助节点嵌入。通过利用学习到的多维边特征矩阵,我们构建多通道滤波器,以更有效地捕获准确的节点特征,从而获得非局部结构特征和细粒度的高阶节点特征。具体而言,多维边信息的引入增强了GNN模型的功能性和灵活性,使其能够更有效地处理复杂多样的图数据。此外,将关系表示学习集成到消息传递框架中,使图节点能够接收到更有用的信息,从而促进节点表示学习。最后,在四个真实世界异构图上的实验证明了所提出模型的有效性。

英文摘要:

Graph Neural Networks (GNNs) have significant advantages in handling non-Euclidean data and have been widely applied across various areas, thus receiving increasing attention in recent years. The framework of GNN models mainly includes the information propagation phase and the aggregation phase, treating nodes and edges as information entities and propagation channels, respectively. However, most existing GNN models face the challenge of disconnection between node and edge feature information, as these models typically treat the learning of edge and node features as independent tasks. To address this limitation, we aim to develop an edge-empowered graph feature preference learning framework that can capture edge embeddings to assist node embeddings. By leveraging the learned multidimensional edge feature matrix, we construct multi-channel filters to more effectively capture accurate node features, thereby obtaining the non-local structural characteristics and fine-grained high-order node features. Specifically, the inclusion of multidimensional edge information enhances the functionality and flexibility of the GNN model, enabling it to handle complex and diverse graph data more effectively. Additionally, integrating relational representation learning into the message passing framework allows graph nodes to receive more useful information, thereby facilitating node representation learning. Finally, experiments on four real-world heterogeneous graphs demonstrate the effectiveness of theproposed model.

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。

↑