WANG Xuesong, CHENG Yuhu, JI Jie, “Semi-Supervised Regression Algorithm Based on Optimal Combined Graph,” Chinese Journal of Electronics, vol. 22, no. 4, pp. 724-728, 2013,
Citation: WANG Xuesong, CHENG Yuhu, JI Jie, “Semi-Supervised Regression Algorithm Based on Optimal Combined Graph,” Chinese Journal of Electronics, vol. 22, no. 4, pp. 724-728, 2013,

Semi-Supervised Regression Algorithm Based on Optimal Combined Graph

Funds:  This work is supported by the National Natural Science Foundation of China (No.60974050, No.61072094, No.61273143), Program for New Century Excellent Talents in University (No.NCET-08-0836, No.NCET-100765), Specialized Research Fund for the Doctoral Program of Higher Education of China (No.20110095110016), Fok Ying-Tung Education Foundation for Young Teachers (No.121066).
More Information
  • Corresponding author: WANG Xuesong, CHENG Yuhu, JI Jie
  • Received Date: 2012-09-01
  • Rev Recd Date: 2012-11-01
  • Publish Date: 2013-09-25
  • In order to construct a high-quality graph to improve the learning accuracy, a new semi-supervised regression algorithm is proposed. According to all labeled and unlabeled samples, multiple graphs with different structures are constructed by using different edgeselection strategies and edge-measurement methods. Each graph corresponds to a basic graph kernel. Following that, a combined graph kernel is created by carrying out a convex optimization operation on these basic graph kernels. We can further obtain an optimal combined graph by calculating a pseudo-inverse of the combined graph kernel. Based on the optimal combined graph, a harmonic function is applied to solving the semi-supervised regression problem. Experimental results on typical artificial function and UCI real datasets show that, compared with other graphbased semi-supervised regression algorithms, the proposed algorithm has higher prediction accuracy even though its control parameters are not settled as optimum values.
  • loading
  • J.W.Wan, M. Yang, Y.J. Chen, “Cost sensitive semi-supervisedL aplacian support vector machine”, Acta Electronica Sinica,Vol.40, No.7, pp.1410-1415, 2012. (in Chinese)
    Z.H. Zhou, M. Li, “Semi-supervised regression with co-trainings tyle algorithm”, IEEE Transactions on Knowledge and DataE ngineering, Vol.19, No.11, pp.1479-1493, 2007.
    J.J. Verbeek, N. Vlassis, “Gaussian fields for semi-supervisedr egression and correspondence learning”, Pattern Recognition,Vol.39, No.10, pp.1864-1875, 2006.
    K.I. Kim, F. Steinke, M. Hein, “Semi-supervised regression usingh essian energy with an application to semi-supervised dimensionalityr eduction”, Proceedings of the Advances in NeuralI nformation Processing Systems, Vancouver, Canada, pp.979-9 87, 2009.
    C.Q. Hou, L.C. Jiao, “Graph based co-training algorithm forw eb page classification”, Acta Electronica Sinica, Vol.37, No.10,p p.2173-2180, 2009. (in Chinese)
    J. Luo, H. Cheng, Y. Tang, “Analysis of graph-based semisupervisedr egression”, Proceedings of the 5th International Conference on Fuzzy Systems and Knowledge Discovery, Jinan, China, pp.111-115, 2008.
    Y.Y. Lin, T.L. Liu, C.S. Fuh, “Multiple kernel learning for dimensionalityr eduction”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.33, No.6, pp.1147-1160, 2011.
    A. Argyriou, M. Herbster, M. Pontil, “Combining graph laplaciansf or semi-supervised learning”, Proceedings of the Advancesi n Neural Information Processing Systems, Nevada,U SA, pp.67-74, 2005.
    S.H. Feng, C.Y. Lang, D. Xu, “Combining graph learning andr egion saliency analysis for content based image retrieval”, ActaE lectronica Sinica, Vol.39, No.10, pp.2288-2294, 2011. (in Chinese)
    A. Argyriou, C.A. Micchelli, M. Pontil, “Learning convex combinations of continuously parameterized basic kernels”, Proceedings of the 18th Annual Conference on Learning Theory, Bertinoro,I taly, pp.338-352, 2005.
    X.J. Zhu, Z.B. Ghahramani, J. Lafferty, “Semi-supervised learningu sing Gaussian fields and harmonic functions”, Proceedings of the 20th International Conference on Machine Learning,W ashington, DC, USA, pp.912-919, 2003.
    P.G. Doyle, J.L. Snell, Random Walks and Electric Networks,M athematical Association of America, Washington, DC, USA,1 984.
  • 加载中


    通讯作者: 陈斌,
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (469) PDF downloads(1297) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint