Abstract
Social data analytics is often taken as the most commonly used method for community discovery, product recommendations, knowledge graph, and so on. In this study, social data are firstly represented in different feature spaces by using various feature extraction algorithms. Then we build a transfer learning model to leverage knowledge from multiple feature spaces. During modeling, since the assumption that the training and the testing data have the same distribution is always true, we give a theorem and its proof which asserts the necessary and sufficient condition for achieving a minimum testing error. We also theoretically demonstrate that maximizing the classification error consistency across different feature spaces can improve the classification performance. Additionally, the cluster assumption derived from semi-supervised learning is introduced to enhance knowledge transfer. Finally, a Tagaki-Sugeno-Kang (TSK) fuzzy system-based learning algorithm is proposed, which can generate interpretable fuzzy rules. Experimental results not only demonstrate the promising social data classification performance of our proposed approach but also show its interpretability which is missing in many other models.
- [1] . 2008. The impact of EEG/MEG signal processing and modeling in the diagnostic and management of epilepsy. IEEE Reviews in Biomedical Engineering 1 (2008), 143–156.Google Scholar
Cross Ref
- [2] . 2013. Modeling noninvasive neurostimulation in epilepsy as stochastic interference in brain networks. IEEE Transactions on Neural Systems and Rehabilitation Engineering 21, 3 (May 2013), 354–363.Google Scholar
Cross Ref
- [3] . 2016. A novel method for automated diagnosis of epilepsy using complex-valued classifiers. IEEE Journal of Biomedical and Health Informatics 20, 1 (Jan. 2016), 108–118.Google Scholar
Cross Ref
- [4] . 2016. Switching EEG headsets made easy: Reducing offline calibration effort using active weighted adaptation regularization. IEEE Transactions on Neural Systems and Rehabilitation Engineering 24, 11 (Nov. 2016), 1125–1137.Google Scholar
Cross Ref
- [5] . 2017. Driver drowsiness estimation from EEG signals using online weighted adaptation regularization for regression (OwARR). IEEE Transactions on Fuzzy Systems 25, 6 (Dec. 2017), 1522–1535.Google Scholar
Digital Library
- [6] . 2016. Co-labeling for multi-view weakly labeled learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 6 (1 June 2016), 1113–1125.Google Scholar
Cross Ref
- [7] . 2015. Multi-view intact space learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 12 (1 Dec. 2015), 2531–2544.Google Scholar
Digital Library
- [8] . 2019. A survey of multi-view representation learning. In IEEE Transactions on Knowledge and Data Engineering 31, 10 (1 Oct. 2019), 1863–1883.Google Scholar
Cross Ref
- [9] . 2014. Transductive domain adaptive learning for epileptic electroencephalogram recognition. Artif. Intell. Med. 62, 3 (Nov. 2014), 165–177.Google Scholar
Cross Ref
- [10] 2017. Seizure classification from EEG signals using transfer learning, semi-supervised learning and TSK fuzzy system. IEEE Transactions on Neural Systems and Rehabilitation Engineering 25, 12 (Dec. 2017), 2270–2284.Google Scholar
Cross Ref
- [11] . 2021. EEG-based driver drowsiness estimation using an online multi-view and transfer TSK fuzzy system. IEEE Transactions on Intelligent Transportation Systems 22, 3 (2021), 1752–1764.
DOI: Google ScholarDigital Library
- [12] . 2015. Multitask TSK fuzzy system modeling by mining intertask common hidden structure. IEEE Transactions on Cybernetics 45, 3 (March 2015), 534–547.Google Scholar
Cross Ref
- [13] . 2007. Multi-task feature learning. In NIPS. MIT Press, (2007), 41.Google Scholar
- [14] . 2007. Co-clustering based classification for out-of-domain documents. In KDD, (2007), 210–219.Google Scholar
- [15] . 2008. Self-taught clustering. In ICML, (2008), 200–207.Google Scholar
- [16] . 2009. Domain transfer SVM for video concept detection. CVPR, 1375–1381, (2009).Google Scholar
- [17] . Transfer learning via dimensionality reduction. In Proceedings of AAAI, 677–682.Google Scholar
Digital Library
- [18] . 2007. Self-taught learning: Transfer learning from unlabeled data. In ICML, (2007), 766–763.Google Scholar
- [19] . 2008. Multi-task Gaussian process prediction. NIPS 20, (2008), 153–160.Google Scholar
- [20] . 2004. Learning to learn with the informative vector machine. In ICML, (2004), 65.Google Scholar
- [21] . 2007. Boosting for transfer learning. In ICML, (2007), 200–207.Google Scholar
- [22] . 2004. Learning and evaluating classifiers under sample selection bias. In ICML, (2004).Google Scholar
- [23] . 2021. Selective transfer classification learning with classification-error-based consensus regularization. IEEE Transactions on Emerging Topics in Computational Intelligence 5, 2 (2021), 178–190.
DOI: Google ScholarCross Ref
- [24] . 2009. Deep transfer via second-order Markov logic. In ICML, (2009), 217–224.Google Scholar
- [25] . 2007. Mapping and revising Markov logic networks for transfer learning. In AAAI 22, (2007), 608–613.Google Scholar
- [26] . 2008. Transfer learning by mapping with minimal target data. In Proceedings of the AAAI-08 Workshop on Transfer Learning for Complex Tasks.Google Scholar
- [27] . 2020. Multi-view scaling support vector machines for classification and feature selection. IEEE Transactions on Knowledge and Data Engineering 32, 7 (2020), 1419–1430.
DOI: Google ScholarCross Ref
- [28] . 2015. Multi-view intact space learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 12 (1 Dec. 2015), 2531–2544.Google Scholar
Digital Library
- [29] . 2015. Robust subspace clustering for multi-view data by exploiting correlation consensus. IEEE Transactions on Image Processing 24, 11 (Nov. 2015), 3939–3949.Google Scholar
Digital Library
- [30] . 2012. Multiview semi-supervised learning with consensus. IEEE Transactions on Knowledge and Data Engineering 24, 11 (Nov. 2012), 2040–2051.Google Scholar
Digital Library
- [31] . 2008. Multi-view learning over structured and non-identical outputs. In UAI, (2008), 204–211.Google Scholar
- [32] . 2011. Multi-view transfer learning with a large margin approach. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’11). Association for Computing Machinery, New York, NY, USA, 1208–1216.Google Scholar
Digital Library
- [33] . 2011. Convergence and equivalence results for the Jensen's inequality—application to time-delay and sampled-data systems. IEEE Transactions on Automatic Control 56, 7 (July 2011), 1660–1665.Google Scholar
Cross Ref
- [34] . 2016. Takagi–Sugeno–Kang transfer learning fuzzy logic system for the adaptive recognition of epileptic electroencephalogram signals. IEEE Transactions on Fuzzy Systems 24, 5 (Oct. 2016), 1079–1094.Google Scholar
Cross Ref
- [35] 2019. Deep multi-view feature learning for EEG-based epileptic seizure detection. IEEE Transactions on Neural Systems and Rehabilitation Engineering 27, 10 (Oct. 2019), 1962–1972.Google Scholar
Cross Ref
- [36] . 2015. Minimax probability TSK fuzzy system classifier: A more transparent and highly interpretable classification model. IEEE Transactions on Fuzzy Systems 23, 4 (Aug. 2015), 813–826.Google Scholar
Digital Library
- [37] . 2016. Parzen window density estimator-based probabilistic power flow with correlated uncertainties. IEEE Transactions on Sustainable Energy 7, 3 (July 2016), 1170–1181.Google Scholar
Cross Ref
- [38] 2011. KEEL data-mining software tool: Data set repository integration of algorithms and experimental analysis framework. J. Multiple-Valued Log. Soft Comput. 17, 2 (2011), 255–287.Google Scholar
- [39] . 2010. EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst. Appl. 37, 12 (Dec. 2010), 8659–8666.Google Scholar
Digital Library
- [40] 2017. Recognition of epileptic EEG signals using a novel multiview TSK fuzzy system. IEEE Transactions on Fuzzy Systems 25, 1 (Feb. 2017), 3–20.Google Scholar
Cross Ref
- [41] . 2014. Transfer learning with graph co-regularization. IEEE Trans. Knowl. Data Eng. 26, 7 (Jul. 2014), 1805–1818.Google Scholar
Cross Ref
- [42] . 2014. Adaptation regularization: A general framework for transfer learning. IEEE Transactions on Knowledge and Data Engineering 26, 5 (May 2014), 1076–1089.Google Scholar
Digital Library
- [43] . 2006. Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7 (2006), 1–30.Google Scholar
Digital Library
- [44] . 1979. A simple sequentially rejective multiple test procedure. Scand. J. Statist. 6, 2 (1979), 65–70.Google Scholar
- [45] . Consensus learning for distributed fuzzy neural network in big data environment. In IEEE Transactions on Emerging Topics in Computational Intelligence.
DOI: Google ScholarCross Ref
- [46] . Fuzzy and real coded chemical reaction optimization for intrusion detection in industrial big data environment. In IEEE Transactions on Industrial Informatics.
DOI: Google ScholarCross Ref
- [47] . Smart supervision of cardiomyopathy based on fuzzy Harris Hawks Optimizer and wearable sensing data optimization: A new model. In IEEE Transactions on Cybernetics.
DOI: Google ScholarCross Ref
- [48] . A majority rule-based measure for Atanassov type intuitionistic membership grades in MCDM. In IEEE Transactions on Fuzzy Systems.
DOI: Google ScholarDigital Library
- [49] . 2019. Shared nearest-neighbor quantum game-based attribute reduction with hierarchical coevolutionary spark and its application in consistent segmentation of neonatal cerebral cortical surfaces. In IEEE Transactions on Neural Networks and Learning Systems 30, 7 (July 2019), 2013–2027.Google Scholar
Cross Ref
- [50] . 2019. SVM-based feature selection for differential space fusion and its application to diabetic fundus image classification. In IEEE Access 7 (2019), 149493–149502.Google Scholar
Cross Ref
Index Terms
Mutual Supervised Fusion & Transfer Learning with Interpretable Linguistic Meaning for Social Data Analytics
Recommendations
Semi-Supervised Learning via Regularized Boosting Working on Multiple Semi-Supervised Assumptions
Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various strategies. To our knowledge, however, none of them takes ...
Semi-supervised learning using hidden feature augmentation
The novel feature augmentation method, which utilizes the hidden features, the raw features, and zero vectors, is proposed.The novel hidden feature transformation model is proposed based on the maximum joint probability principle.With hinge loss ...
Semi-supervised learning using label mean
ICML '09: Proceedings of the 26th Annual International Conference on Machine LearningSemi-Supervised Support Vector Machines (S3VMs) typically directly estimate the label assignments for the unlabeled instances. This is often inefficient even with recent advances in the efficient training of the (supervised) SVM. In this paper, we show ...






Comments