Tackling Provably Hard Representative Selection via Graph Neural Networks

05/20/2022
by   Seyed Mehran Kazemi, et al.
0

Representative selection (RS) is the problem of finding a small subset of exemplars from an unlabeled dataset, and has numerous applications in summarization, active learning, data compression and many other domains. In this paper, we focus on finding representatives that optimize the accuracy of a model trained on the selected representatives. We study RS for data represented as attributed graphs. We develop RS-GNN, a representation learning-based RS model based on Graph Neural Networks. Empirically, we demonstrate the effectiveness of RS-GNN on problems with predefined graph structures as well as problems with graphs induced from node feature similarities, by showing that RS-GNN achieves significant improvements over established baselines that optimize surrogate functions. Theoretically, we establish a new hardness result for RS by proving that RS is hard to approximate in polynomial time within any reasonable factor, which implies a significant gap between the optimum solution of widely-used surrogate functions and the actual accuracy of the model, and provides justification for the superiority of representation learning-based approaches such as RS-GNN over surrogate functions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2022

Measuring and Improving the Use of Graph Information in Graph Neural Networks

Graph neural networks (GNNs) have been widely used for representation le...
research
03/17/2023

Distill n' Explain: explaining graph neural networks using simple surrogates

Explaining node predictions in graph neural networks (GNNs) often boils ...
research
10/08/2022

Break the Wall Between Homophily and Heterophily for Graph Representation Learning

Homophily and heterophily are intrinsic properties of graphs that descri...
research
02/08/2021

A Systematic Comparison Study on Hyperparameter Optimisation of Graph Neural Networks for Molecular Property Prediction

Graph neural networks (GNNs) have been proposed for a wide range of grap...
research
08/26/2020

Learning Robust Node Representation on Graphs

Graph neural networks (GNN), as a popular methodology for node represent...
research
08/02/2020

Detecting Relevant Feature Interactions for Recommender Systems via Graph Neural Networks

Feature interactions are essential for achieving high accuracy in recomm...
research
01/27/2023

An Arithmetic Theory for the Poly-Time Random Functions

We introduce a new bounded theory RS^1_2 and show that the functions whi...

Please sign up or login with your details

Forgot password? Click here to reset