Kernel methods for predicting yields of chemical reactions

AL Haywood, J Redshaw… - Journal of Chemical …, 2021 - ACS Publications
The use of machine learning methods for the prediction of reaction yield is an emerging
area. We demonstrate the applicability of support vector regression (SVR) for predicting …

Inductive graph unlearning

CL Wang, M Huai, D Wang - 32nd USENIX Security Symposium …, 2023 - usenix.org
As a way to implement the" right to be forgotten" in machine learning, machine unlearning
aims to completely remove the contributions and information of the samples to be deleted …

Kergnns: Interpretable graph neural networks with graph kernels

A Feng, C You, S Wang, L Tassiulas - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Graph kernels are historically the most widely-used technique for graph classification tasks.
However, these methods suffer from limited performance because of the hand-crafted …

Random walk graph neural networks

G Nikolentzos, M Vazirgiannis - Advances in Neural …, 2020 - proceedings.neurips.cc
In recent years, graph neural networks (GNNs) have become the de facto tool for performing
machine learning tasks on graphs. Most GNNs belong to the family of message passing …

Graph kernels: A survey

G Nikolentzos, G Siglidis, M Vazirgiannis - Journal of Artificial Intelligence …, 2021 - jair.org
Graph kernels have attracted a lot of attention during the last decade, and have evolved into
a rapidly develo** branch of learning on structured data. During the past 20 years, the …

The curious decline of linguistic diversity: Training language models on synthetic text

Y Guo, G Shang, M Vazirgiannis, C Clavel - ar** semi-supervised annotation method for potential suicidal messages
RWA Caicedo, JMG Soriano, HAM Sasieta - Internet Interventions, 2022 - Elsevier
The suicide of a person is a tragedy that deeply affects families, communities, and countries.
According to the standardized rate of suicides per number of inhabitants worldwide, in 2022 …