Probabilistic feature selection and classification vector machine

Jiang，Bingbing1; Li，Chang2; De Rijke，Maarten2; Yao，Xin3; Chen，Huanhuan1

2019-05-01

10.1145/3309541

ACM Transactions on Knowledge Discovery from Data   影响因子和分区

1556-4681

1556-472X

Sparse Bayesian learning is a state-of-the-art supervised learning algorithm that can choose a subset of relevant samples from the input data and make reliable probabilistic predictions. However, in the presence of high-dimensional data with irrelevant features, traditional sparse Bayesian classifiers suffer from performance degradation and low efficiency due to the incapability of eliminating irrelevant features. To tackle this problem, we propose a novel sparse Bayesian embedded feature selection algorithm that adopts truncated Gaussian distributions as both sample and feature priors. The proposed algorithm, called probabilistic feature selection and classification vector machine (PFCVM) is able to simultaneously select relevant features and samples for classification tasks. In order to derive the analytical solutions, Laplace approximation is applied to compute approximate posteriors and marginal likelihoods. Finally, parameters and hyperparameters are optimized by the type-II maximum likelihood method. Experiments on three datasets validate the performance of PFCVM along two dimensions: classification performance and effectiveness for feature selection. Finally, we analyze the generalization performance and derive a generalization error bound for PFCVM. By tightening the bound, the importance of feature selection is demonstrated.

EEG emotion recognition Feature selection Probabilistic classification model Sparse Bayesian learning Supervised learning

SCI ; EI

英语

其他

Netherlands Organisation for Scientific Research (NWO)[CI-14-25, 652.002.001] ; Netherlands Organisation for Scientific Research (NWO)[612.001.551] ; Netherlands Organisation for Scientific Research (NWO)[652.001.003]

Computer Science

Computer Science, Information Systems ; Computer Science, Software Engineering

WOS:000495426500008

ASSOC COMPUTING MACHINERY

20192106952366

Clustering algorithms ; Data mining ; Feature extraction ; Learning algorithms ; Machine learning ; Maximum likelihood ; Supervised learning

Data Processing and Image Processing:723.2 ; Information Sources and Analysis:903.1 ; Probability Theory:922.1

2-s2.0-85065804414

Scopus

1.School of Computer Science and TechnologyUniversity of Science and Technology of China,Hefei, Anhui,230027,China
2.Informatics InstituteUniversity of Amsterdam,Amsterdam,Netherlands
3.Department of Computer Science and EngineeringShenzhen Key Laboratory of Computational IntelligenceSouthern University of Science and Technology,Shenzhen, Guangdong,518055,China

Jiang，Bingbing,Li，Chang,De Rijke，Maarten,et al. Probabilistic feature selection and classification vector machine[J]. ACM Transactions on Knowledge Discovery from Data,2019,13(2).

Jiang，Bingbing,Li，Chang,De Rijke，Maarten,Yao，Xin,&Chen，Huanhuan.(2019).Probabilistic feature selection and classification vector machine.ACM Transactions on Knowledge Discovery from Data,13(2).

Jiang，Bingbing,et al."Probabilistic feature selection and classification vector machine".ACM Transactions on Knowledge Discovery from Data 13.2(2019).