Node2Seq: Towards Trainable Convolutions in Graph Neural Networks
This work provides an incremental improvement in graph neural network architectures by enabling more explicit and trainable weighting of neighboring node information, which could benefit researchers working on graph data analysis.
This paper addresses the challenge of learning explicit weights for neighboring nodes in graph neural networks. The authors propose Node2Seq, a novel graph network layer that sorts neighboring nodes using an attention mechanism and then applies 1D convolutional neural networks to learn trainable weights for information aggregation. The method also adaptively incorporates non-local information based on attention scores, demonstrating improved performance in feature learning.
Investigating graph feature learning becomes essentially important with the emergence of graph data in many real-world applications. Several graph neural network approaches are proposed for node feature learning and they generally follow a neighboring information aggregation scheme to learn node features. While great performance has been achieved, the weights learning for different neighboring nodes is still less explored. In this work, we propose a novel graph network layer, known as Node2Seq, to learn node embeddings with explicitly trainable weights for different neighboring nodes. For a target node, our method sorts its neighboring nodes via attention mechanism and then employs 1D convolutional neural networks (CNNs) to enable explicit weights for information aggregation. In addition, we propose to incorporate non-local information for feature learning in an adaptive manner based on the attention scores. Experimental results demonstrate the effectiveness of our proposed Node2Seq layer and show that the proposed adaptively non-local information learning can improve the performance of feature learning.