Feature-Attention Graph Convolutional Networks for Noise Resilient Learning
Feature-Attention Graph Convolutional Networks for Noise Resilient Learning
复制标题
用于抗噪学习的特征注意图卷积网络
DOI：
10.1109/tcyb.2022.3143798
复制
发表时间：
2022
影响因子：
11.8
通讯作者：
Liu, Jianxun
中科院分区：
文献类型：
--
作者：
Shi, Min;Tang, Yufei;Zhu, Xingquan;Zhuang, Yuan;Lin, Maohua;Liu, Jianxun
噪声和不一致通常存在于现实世界的信息网络中，这是由于人类或用户隐私问题固有的容易出错的性质。迄今为止，通过集成节点内容和拓扑结构，已经做出了巨大的努力来推进网络的特征学习，包括最新的图卷积网络（GCNs）或注意力GCN。然而，现有的所有方法都将网络视为无错误源，并将每个节点中的特征内容视为独立的，对建模节点关系同等重要。噪声节点内容与稀疏特征相结合，对现有方法在实际噪声网络中的应用提出了重大挑战。在本文中，我们提出了基于特征的注意GCN (FA-GCN)，一种特征-注意图卷积学习框架，用于处理带有噪声和稀疏节点内容的网络。为了解决每个节点的噪声和稀疏内容，FA-GCN首先使用LSTM（长短期记忆）网络学习每个节点特征的密集表示。为了对相邻节点之间的交互建模，引入了特征注意机制，允许相邻节点根据其连接学习和改变特征的重要性。通过使用基于谱的图卷积聚合过程，允许每个节点更多地关注与相应学习任务一致的最具决定性的邻域特征。实验和验证表明，在不同的噪声水平下，FA-GCN在无噪声和有噪声网络环境下都比最先进的方法取得了更好的性能。
Noise and inconsistency commonly exist in real-world information networks, due to the inherent error-prone nature of human or user privacy concerns. To date, tremendous efforts have been made to advance feature learning from networks, including the most recent graph convolutional networks (GCNs) or attention GCN, by integrating node content and topology structures. However, all existing methods consider networks as error-free sources and treat feature content in each node as independent and equally important to model node relations. Noisy node content, combined with sparse features, provides essential challenges for existing methods to be used in real-world noisy networks. In this article, we propose feature-based attention GCN (FA-GCN), a feature-attention graph convolution learning framework, to handle networks with noisy and sparse node content. To tackle noise and sparse content in each node, FA-GCN first employs a long short-term memory (LSTM) network to learn dense representation for each node feature. To model interactions between neighboring nodes, a feature-attention mechanism is introduced to allow neighboring nodes to learn and vary feature importance, with respect to their connections. By using a spectral-based graph convolution aggregation process, each node is allowed to concentrate more on the most determining neighborhood features aligned with the corresponding learning task. Experiments and validations, w.r.t. different noise levels, demonstrate that FA-GCN achieves better performance than the state-of-the-art methods in both noise-free and noisy network environments.