Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Node2Seq: Towards Trainable Convolutions in Graph Neural Networks

About

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.

Hao Yuan, Shuiwang Ji• 2021

Related benchmarks

TaskDatasetResultRank
Node ClassificationChameleon
Accuracy69.4
549
Node ClassificationSquirrel
Accuracy58.8
500
Node ClassificationCornell
Accuracy58.7
426
Node ClassificationWisconsin
Accuracy60.3
410
Node ClassificationTexas
Accuracy0.637
410
Node ClassificationActor
Accuracy31.4
237
Showing 6 of 6 rows

Other info

Follow for update