.png){kind=icon}
.png){kind=icon}
Return
ESA*: A generic framework for semi-supervised inductive learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2021.03.051.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Semi-supervised learning is crucial in many applications where accessing class labels is unaffordable or costly. The most promising approaches are graph-based but they are transductive and they do not provide a generalized model working on inductive scenarios. To address this problem, we propose a generic framework, ESA*, for inductive semi-supervised learning based on three components: an ensemble of semi-supervised autoencoders providing a new data representation that leverages the knowledge supplied by the reduced amount of available labels; a graph-based step that helps augmenting the training set with pseudo-labeled instances and, finally, a classifier trained with labeled and pseudo-labeled instances. Additionally, we also introduce two variants of our framework adopting different graph-based pseudo-labeling strategies: the first, ESA(LP), is based on a confidence-aware label propagation algorithm, while the second, ESA(GAT), on a graph convolutional attention network. The experimental results show that our framework outperforms state-of-the-art inductive semi-supervised methods. (C) 2021 Elsevier B.V. All rights reserved.
Keywords:
Semi-supervised learning
Graph-based algorithms
Inductive methods
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.