Node2Seq: Towards Trainable Convolutions in Graph Neural Networks

TL;DR

Node2Seq introduces a trainable convolutional layer for graph neural networks that explicitly learns weights for neighboring nodes, utilizing attention-based sorting and 1D CNNs to enhance node feature learning.

Contribution

The paper proposes a novel Node2Seq layer that enables trainable weights for neighbors and incorporates non-local information adaptively, advancing graph neural network capabilities.

Findings

Node2Seq outperforms existing methods on benchmark datasets.

Explicit neighbor weighting improves node embedding quality.

Adaptive non-local information enhances feature learning.

Abstract

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.