# Graph Node-Feature Convolution for Representation Learning

arXiv: https://arxiv.org/abs/1812.00086 · HTML: https://mlsanity.com/paper/1812.00086/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2018.

## Built on by (most cited first, 2 of 2)

- [BoundaryNet: An Attentive Deep Network with Fast Marching Distance Maps for Semi-automatic Layout Annotation](https://mlsanity.com/paper/2108.09433/) (2021)
- [MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation](https://mlsanity.com/paper/2110.08818/) (2021)

## Abstract (arXiv)

Graph convolutional network (GCN) is an emerging neural network approach. It learns new representation of a node by aggregating feature vectors of all neighbors in the aggregation process without considering whether the neighbors or features are useful or not. Recent methods have improved solutions by sampling a fixed size set of neighbors, or assigning different weights to different neighbors in the aggregation process, but features within a feature vector are still treated equally in the aggregation process. In this paper, we introduce a new convolution operation on regular size feature maps constructed from features of a fixed node bandwidth via sampling to get the first-level node representation, which is then passed to a standard GCN to learn the second-level node representation. Experiments show that our method outperforms competing methods in semi-supervised node classification tasks. Furthermore, our method opens new doors for exploring new GCN architectures, particularly deeper GCN models.