Skip to Content

Representative Selection with Graph Neural Networks

Posted on One min read
A T-SNE plot of embeddings.
Example embeddings with representatives learned and selected by RS-GNN.

paper · pdf · code

TL;DR

Selecting Representative Points with Graph Neural Networks.

In this paper:

  • We establish a new hardness result for representative selection problem in the absence of a graph structure.
  • We develop RS-GNN, a representation learning-based RS model based on Graph Neural Networks.
  • We demonstrate the effectiveness of RS-GNN on problems with predefined graph structures as well as problems with graphs induced from node features.