高级检索

    基于元素分离与整体注意力的图卷积网络框架

    Element Separation and Holistic Attention Based Graph Convolutional Network Framework

    • 摘要: 目前,图卷积网络在处理图数据等非结构化数据方面具有很大的潜力,然而在处理稠密连接图时仍面临一定的挑战,因为其基于节点的邻域信息聚合机制容易导致整个网络图出现过度平滑现象从而弱化网络图的表达能力. 稀疏图的构建在一定程度上能够缓解网络图在卷积过程中的过度平滑现象,但是稀疏图容易丢失信息且稀疏化的过程缺乏统一标准,从而影响模型的一致性和可解释性. 为此,提出了一种基于元素分离与整体注意力的图卷积网络框架(EH-GCN). 该框架无需建立在稀疏图的基础之上,不仅能够在稠密连接图分别学习图的连接特征和节点特征,而且采用全局注意力机制进行连接特征和节点特征的整合,从而克服了传统图卷积网络框架在应对稠密连接图时的局限性,提高了网络图的特征表达能力. 首先在ADNI,ABIDE和AIBL这3个脑影像数据集上构建全连接脑网络,验证了EH-GCN在稠密连接图分类任务中的有效性. 随后,所提模型在FRANKENSTEIN化学分子图数据集上进行了测试,证明了其强大的泛化能力. 此外,所提模型的可解释性分析结果与先前的神经病理学研究一致,进一步证明了所提模型的生物学基础.

       

      Abstract: Currently, graph convolutional network (GCN) holds significant potential in processing graph data and other unstructured data. However, GCN faces challenges when dealing with densely connected graphs, as their node-based neighborhood information aggregation mechanism can lead to excessive smoothing, thereby weakening the expressive power of the network graph. The construction of sparse graphs can alleviate the phenomenon of excessive smoothing during the convolution process to some extent, but sparse graphs are prone to information loss and the sparsification process lacks unified standards, affecting the model’s consistency and interpretability. To address this, we propose element separation and holistic attention graph convolutional network framework (EH-GCN). This framework does not require the basis of sparse graphs and can learn the connectivity and node features of densely connected graphs separately. Moreover, it employs a global attention mechanism to integrate connectivity and node features, thus overcoming the limitations of traditional GCN frameworks in handling densely connected graphs and enhancing the feature expression capability of the network graph. We firstly construct fully connected brain networks on three brain imaging datasets: ADNI, ABIDE, and AIBL, verifying the effectiveness of the EH-GCN model in classifying densely connected graphs. Subsequently, the model is tested on the FRANKENSTEIN chemical molecular graph dataset, demonstrating its robust generalization capability. Additionally, the interpretability analysis of the framework aligns with previous neuropathological research, further substantiating the biological basis of the framework.

       

    /

    返回文章
    返回