Incremental and Decremental Max-Flow for Online Semi-Supervised Learning

Max-flow has been adopted for semi-supervised data modelling, yet existing algorithms were derived only for the learning from static data. This paper proposes an online max-flow algorithm for the semi-supervised learning from data streams. Consider a graph learned from labelled and unlabelled data, and the graph being updated dynamically for accommodating online data adding and retiring. In learning from the resulting non stationary graph, we augment and de-augment paths to update max-flow with a theoretical guarantee that the updated max-flow equals to that from batch retraining. For classification, we compute min-cut over current max-flow, so that minimized number of similar sample pairs are classified into distinct classes. Empirical evaluation on real-world data reveals that our algorithm outperforms state-of-the-art stream classification algorithms.

[1]  Niloy Ganguly,et al.  Fair bandwidth allocation in wireless mobile environment using max-flow , 2010, 2010 International Conference on High Performance Computing.

[2]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[3]  Li Guo,et al.  Mining Data Streams with Labeled and Unlabeled Training Examples , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[4]  Li Guo,et al.  Classifier and Cluster Ensembles for Mining Concept Drifting Data Streams , 2010, 2010 IEEE International Conference on Data Mining.

[5]  Sultan Imangaliyev,et al.  Online semi-supervised learning: Algorithm and application in metagenomics , 2013, 2013 IEEE International Conference on Bioinformatics and Biomedicine.

[6]  S. Kumar,et al.  An Incremental Algorithm for the Maximum Flow Problem , 2003, J. Math. Model. Algorithms.

[7]  Gregory Ditzler,et al.  Semi-supervised learning in nonstationary environments , 2011, The 2011 International Joint Conference on Neural Networks.

[8]  Gustavo Carneiro,et al.  Incremental on-line semi-supervised learning for segmenting the left ventricle of the heart from ultrasound data , 2011, 2011 International Conference on Computer Vision.

[9]  B. Yver,et al.  Online semi-supervised learning: Application to dynamic learning from RADAR data , 2009, 2009 International Radar Conference "Surveillance for a Safer World" (RADAR 2009).

[10]  Avrim Blum,et al.  Learning from Labeled and Unlabeled Data using Graph Mincuts , 2001, ICML.

[11]  Thomas S. Huang,et al.  Semisupervised Learning of Classifiers With Application to Human -Computer Interaction , 2003 .

[12]  C.-C. Jay Kuo,et al.  A semi-supervised learning approach to online audio background detection , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Ravindra K. Ahuja,et al.  Network Flows: Theory, Algorithms, and Applications , 1993 .

[14]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[15]  Yi Zhang,et al.  Research on Method of Traffic Network Bottleneck Identification based on Max-flow Min-cut Theorem , 2011, Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE).

[16]  Yuri Boykov,et al.  Energy Based Multi-model Fitting & Matching for 3D Reconstruction , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern (FBCSP) algorithm using online adaptive and semi-supervised learning , 2011, The 2011 International Joint Conference on Neural Networks.

[18]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[19]  Niloy Ganguly,et al.  Smart Association Control in Wireless Mobile Environment Using Max-Flow , 2012, IEEE Transactions on Network and Service Management.

[20]  A. Fabijanska,et al.  Min-Cut/max-flow segmentation of hydrocephalus in children from CT datasets , 2012, 2012 International Conference on Signals and Electronic Systems (ICSES).

[21]  Oliver Kosut Max-flow min-cut for power system security index computation , 2014, 2014 IEEE 8th Sensor Array and Multichannel Signal Processing Workshop (SAM).

[22]  Weimin Huang,et al.  Shape prior regularized continuous max-flow approach to image segmentation , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[23]  Cuntai Guan,et al.  Online semi-supervised learning with KL distance weighting for Motor Imagery-based BCI , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  José Antonio Lozano Alonso,et al.  On the optimal usage of labelled examples in semi-supervised multi-class classification problems , 2015 .

[25]  Paul Newman,et al.  Choosing where to go: Complete 3D exploration with stereo , 2011, 2011 IEEE International Conference on Robotics and Automation.

[26]  Éva Tardos,et al.  Algorithm design , 2005 .

[27]  Yi Liu,et al.  SemiBoost: Boosting for Semi-Supervised Learning , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  R. Zabih,et al.  Exact voxel occupancy with graph cuts , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).