Journal Article10.1016/j.eswa.2022.119164
Semi-supervised learning with graph convolutional extreme learning machines
25
TL;DR: In this article , a semi-supervised learning framework, termed Graph Convolutional Extreme Learning Machines (GCELM), based on extending the traditional ELM to the non-Euclidean domain was proposed.
read more
Abstract: Extreme Learning Machine (ELM) has been widely used for various classification problems. However, the traditional ELMs are typically based on the regular Euclidean data, thus ignoring the intrinsic structured information among data and resulting in poor robustness. In this paper, we present a novel semi-supervised learning framework, termed Graph Convolutional Extreme Learning Machines (GCELM), based on extending the traditional ELM to the non-Euclidean domain. Technically, we recast ELM layers into a randomized graph convolutional embedding layer followed by a graph convolutional regression layer, which endows ELM with the capability to handle graphs in the non-Euclidean domain. Benefiting from the diversity of the randomized graph convolution, we further propose an enhanced GCELM, i.e., Voting-based GCELM (V-GCELM), by using a simple voting ensemble strategy. The proposed methods preserve the advantages of ELMs, thus being more efficient than the gradient-based graph convolutional networks but without loss of graph learning ability. Extensive experiments on 36 benchmark datasets demonstrate that the proposed methods significantly outperform many previous semi-supervised classification methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A scalable graph reinforcement learning algorithm based stochastic dynamic dispatch of power system under high penetration of renewable energy
TL;DR: In this article , a graph-based representation of system state is proposed to capture the implicit correlation of the uncertainty corresponding to the system topology, and a graph reinforcement learning (GRL) algorithm was proposed to learn the optimal policy which maps graph represented system state to DED decision.
15
Anomaly Detection in Dynamic Graphs: A Comprehensive Survey
Ocheme Anthony Ekle,William Eberle +1 more
TL;DR: A comprehensive survey on anomaly detection in dynamic graphs focusing on existing graph-based techniques and their applications to dynamic networks. The survey includes a review framework, discussion of graphical representation, and potential challenges.
10
A high-performance voting-based ensemble model of graph convolutional extreme learning machines for identifying geochemical anomalies related to mineralization
Jiaxing Chen,Yongliang Chen +1 more
TL;DR: A voting-based ensemble model of graph convolutional extreme learning machines (V-GCELM) outperforms traditional models in identifying geochemical anomalies related to mineralization, achieving an AUC of 0.9989 and lift index of 28.6 in the Baishan area of Jilin Province, China.
8
Stochastic Dynamic Power Dispatch With Human Knowledge Transfer Using Graph-GAN Assisted Inverse Reinforcement Learning
Jian Chen,Tao Yu,Zhen Ning Pan,Mengyue Zhang,Guanhua Lu,Kedong Zhu +5 more
TL;DR: A novel approach for dynamic economic dispatch (DED) of distribution networks, based on graph-generative adversarial network (Graph-GAN) assisted inverse reinforcement learning (IRL) with human knowledge transfer via demonstration is proposed, which outperforms traditional IRL methods and achieves supply-demand balance.
5
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Advances in Neural Information Processing Systems 28
Peter A. Flach,Meelis Kull +1 more
- 12 Dec 2015
13.6K
Advances in Neural Information Processing Systems 29
Onur Teymur,Kostas Zygalakis,Ben Calderhead +2 more
- 01 Jan 2016
11K
Extreme Learning Machine for Regression and Multiclass Classification
Guang-Bin Huang,Hongming Zhou,Xiaojian Ding,Rui Zhang +3 more
- 01 Apr 2012
TL;DR: ELM provides a unified learning platform with a widespread type of feature mappings and can be applied in regression and multiclass classification applications directly and in theory, ELM can approximate any target continuous function and classify any disjoint regions.
5.7K