Attribute2vec: Deep Network Embedding Through Multi-Filtering GCN
This work addresses network embedding for tasks like link prediction and node classification, offering a novel multi-filtering approach that improves performance over existing methods, though it appears incremental as an enhancement to GCN-based techniques.
The paper tackles network embedding by proposing a multi-filtering Graph Convolutional Neural Network (GCN) framework that uses multiple local GCN filters per layer to capture different aspects of node features, achieving significant improvements over baseline methods in link prediction and node classification tasks, especially with limited training data.
We present a multi-filtering Graph Convolution Neural Network (GCN) framework for network embedding task. It uses multiple local GCN filters to do feature extraction in every propagation layer. We show this approach could capture different important aspects of node features against the existing attribute embedding based method. We also show that with multi-filtering GCN approach, we can achieve significant improvement against baseline methods when training data is limited. We also perform many empirical experiments and demonstrate the benefit of using multiple filters against single filter as well as most current existing network embedding methods for both the link prediction and node classification tasks.