2 Hits in 2.2 sec

MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks [article]

Jihoon Ko, Kyuhan Lee, Kijung Shin, Noseong Park
2020 arXiv   pre-print
In this work, we present an inductive machine learning method, called Monte Carlo Simulator (MONSTOR), for estimating the influence of given seed nodes in social networks unseen during training.  ...  Since it is an NP-hard problem, many approximate/heuristic methods have been developed, and a number of them repeat Monte Carlo (MC) simulations over and over to reliably estimate the influence (i.e.,  ...  This research was results of a study on the "HPC Support" Project, supported by the 'Ministry of Science and ICT' and NIPA.  ... 
arXiv:2001.08853v5 fatcat:rzi2l4kv4vf6pkkwdiq3hs2hjy

Learning to Pool in Graph Neural Networks for Extrapolation [article]

Jihoon Ko, Taehyung Kwon, Kijung Shin, Juho Lee
2021 arXiv   pre-print
Graph neural networks (GNNs) are one of the most popular approaches to using deep learning on graph-structured data, and they have shown state-of-the-art performances on a variety of tasks.  ...  We verify experimentally that simply using GNP for every aggregation and readout operation enables GNNs to extrapolate well on many node-level, graph-level, and set-related tasks; and GNP sometimes performs  ...  Since the original GNP can only take non-negative inputs, we replaced ReLU to the absolute function for processing the inputs and then used an activation function.  ... 
arXiv:2106.06210v2 fatcat:dnctoyhxcnfitb4hr322766es4