Semi-Supervised Classification via Hypergraph Convolutional Extreme Learning Machine
Source abstract
Abstract
Extreme Learning Machine (ELM) is characterized by simplicity, generalization ability, and computational efficiency. However, previous ELMs fail to consider the inherent high-order relationship among data points, resulting in being powerless on structured data and poor robustness on noise data. This paper presents a novel semi-supervised ELM, termed Hypergraph Convolutional ELM (HGCELM), based on using hypergraph convolution to extend ELM into the non-Euclidean domain. The method inherits all the advantages from ELM, and consists of a random hypergraph convolutional layer followed by a hypergraph convolutional regression layer, enabling it to model complex intraclass variations. We show that the traditional ELM is a special case of the HGCELM model in the regular Euclidean domain. Extensive experimental results show that HGCELM remarkably outperforms eight competitive methods on 26 classification benchmarks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and ELM · Domain Adaptation and Few-Shot Learning · MicroRNA in disease regulation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science, China University of Geosciences, Wuhan 430078, China
Guangxi Key Laboratory of Marine Disaster in the Beibu Gulf, Beibu Gulf University, Qinzhou 535011, China
Funding
National Natural Science Foundation of China (NSFC) · Fundamental Research Founds for National University, China University of Geosciences(Wuhan)
References (39)
Show source-provided references
1. Trends in extreme learning machines: A review10.1016/j.neunet.2014.10.001 ↗
2. Extreme learning machine: Theory and applications10.1016/j.neucom.2005.12.126 ↗
3. An unsupervised parameter learning model for RVFL neural network10.1016/j.neunet.2019.01.007 ↗
4. Extreme Learning Machine for Regression and Multiclass Classification10.1109/TSMCB.2011.2168604 ↗
5. Hierarchical ensemble of extreme learning machine10.1016/j.patrec.2018.06.015 ↗
6. Automatic epileptic seizure detection in EEGs based on optimized sample entropy and extreme learning machine10.1016/j.jneumeth.2012.07.003 ↗
7. Traffic Sign Recognition Using Kernel Extreme Learning Machines with Deep Perceptual Features
8. A Reliable Intelligent System for Real-Time Dynamic Security Assessment of Power Systems10.1109/TPWRS.2012.2183899 ↗
9. Electricity Price Forecasting With Extreme Learning Machine and Bootstrapping10.1109/TPWRS.2012.2190627 ↗
10. A survey of randomized algorithms for training neural networks10.1016/j.ins.2016.01.039 ↗
11. A review on neural networks with random weights10.1016/j.neucom.2017.08.040 ↗
12. A multiobjective optimization-based sparse extreme learning machine algorithm10.1016/j.neucom.2018.07.060 ↗
13. Memetic Extreme Learning Machine10.1016/j.patcog.2016.04.003 ↗
14. A self-adaptive kernel extreme learning machine for short-term wind speed forecasting10.1016/j.asoc.2020.106917 ↗
15. Ensemble extreme learning machines for compound-fault diagnosis of rotating machinery10.1016/j.knosys.2019.105012 ↗
16. Local Receptive Fields Based Extreme Learning Machine10.1109/MCI.2015.2405316 ↗
17. Densely connected convolutional extreme learning machine for hyperspectral image classification10.1016/j.neucom.2020.12.064 ↗
18. BS-Nets: An End-to-End Framework for Band Selection of Hyperspectral Image10.1109/TGRS.2019.2951433 ↗
19. Joachims, T. (1999, January 27–30). Transductive inference for text classification using support vector machines. Proceedings of the ICML, Bled, Slovenia.
20. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples
21. Semi-Supervised and Unsupervised Extreme Learning Machines10.1109/TCYB.2014.2307349 ↗
22. Adaptive multiple graph regularized semi-supervised extreme learning machine10.1007/s00500-018-3109-x ↗
23. A Comprehensive Survey on Graph Neural Networks10.1109/TNNLS.2020.2978386 ↗
24. Daumé, H., and Singh, A. (2020, January 12–18). Generalization and Representational Limits of Graph Neural Networks. Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria.
25. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
26. Graph Convolutional Subspace Clustering: A Robust Subspace Clustering Framework for Hyperspectral Image10.1109/TGRS.2020.3018135 ↗
27. Chaudhuri, K., and Salakhutdinov, R. (2019, January 9–15). Self-Attention Graph Pooling. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
28. Li, Q., Han, Z., and Wu, X.M. (2018, January 2–7). Deeper insights into graph convolutional networks for semi-supervised learning. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11604 ↗
29. Chaudhuri, K., and Salakhutdinov, R. (2019, January 9–15). Simplifying Graph Convolutional Networks. Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA.
30. Feng, Y., You, H., Zhang, Z., Ji, R., and Gao, Y. (February, January 27). Hypergraph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
31. Hypergraph convolution and hypergraph attention10.1016/j.patcog.2020.107637 ↗
32. Zhang, Z., Cai, Y., Gong, W., Liu, X., and Cai, Z. (2020, January 19–24). Graph Convolutional Extreme Learning Machine. Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.10.1109/IJCNN48605.2020.9206649 ↗
33. Schölkopf, B., Platt, J., and Hofmann, T. (2007). Learning with Hypergraphs: Clustering, Classification, and Embedding. Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference, MITP.
34. Jin, T., Cao, L., Zhang, B., Sun, X., Deng, C., and Ji, R. (2019, January 10–16). Hypergraph Induced Convolutional Manifold Networks. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China.10.24963/ijcai.2019/371 ↗
35. Cai, Y., Zhang, Z., Cai, Z., Liu, X., and Jiang, X. (2021). Hypergraph-Structured Autoencoder for Unsupervised and Semisupervised Classification of Hyperspectral Image. IEEE Geosci. Remote Sens. Lett., 1–5.10.1109/LGRS.2021.3054868 ↗
36. Defferrard, M., Bresson, X., and Vandergheynst, P. (2016, January 4–9). Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS’16), Barcelona, Spain.
37. Hamilton, W.L., Ying, R., and Leskovec, J. (2017, January 4–9). Inductive Representation Learning on Large Graphs. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
38. Spectral-Spatial Classification of Hyperspectral Image Based on Kernel Extreme Learning Machine10.3390/rs6065795 ↗
39. A self-training semi-supervised SVM algorithm and its application in an EEG-based brain computer interface speller system10.1016/j.patrec.2008.01.030 ↗