Ata Kaban - Publications

2013

• A. Kaban and R.J. Durrant. Dimension-Adaptive Bounds on Compressive FLD Classification. The 24th International Conference on Algorithmic Learning Theory (ALT 2013). Accepted.
• R.J. Durrant and A. Kaban. Random Projections as Regularisers: Learning a Linear Discriminant Ensemble from Fewer Observations than Dimensions. The 5th Asian Conference on Machine Learning (ACML 2013). Accepted. Supplemenatary material.
• J. Bootkrajang and A. Kaban. Boosting in the Presence of Label Noise. Proceedings of the 29^th Conference on Uncertainty in Artificial Intelligence (UAI 2013), pp. 82-90, 2013.
• R.J. Durrant and A. Kaban. Sharp Generalization Error Bounds for Randomly-projected Classifiers. 30th International Conference on Machine Learning (ICML 2013), Journal of Machine Learning Research-Proceedings Track 28(3):693-701, 2013. Slides.
  [Erratum: in the printed version Sec. 4.1.2 line 3, tan(theta) should read tan(theta/2).]
• A. Kaban, J. Bootkrajang, R.J. Durrant. Towards Large Scale Continuous EDA: A Random Matrix Theory Perspective. 22^nd International Conference on Genetic Algorithms and 18^th Annual Genetic Programming Conference (GECCO 2013), Amsterdam, The Netherlands, July 6-10. Best Paper Award in GDS/EDA track. Slides. Code.
  [Erratum: in the printed version, in l.h.s. of eq. (8) sigma^4 should read k sigma^4; also typo in r.h.s. of eq. (7) missed the k-dependent factors. All corrected on the above link.]
• A. Kaban. Fractional-norm Regularisation: Learning with Very Few Relevant Features. IEEE Transactions on Neural Networks and Learning Systems, Volume 24, Issue 6, 2013, pp. 953-963.
• J. Bootkrajang and A. Kaban. Classification of Mislabelled Microarrays using Robust Sparse Logistic Regression. Bioinformatics. 29(7): 870-877, 2013.
• J. Bootkrajang and A. Kaban. Learning a Label-noise Robust Logistic Regression: Analysis and Experiments. Proc. IDEAL 2013, LNCS 8206, 2013. (c) Springer
• S. Ali-Pitchay and A. Kaban. Estimating the Regularisation Parameter in Huber MRF for Image Resolution Enhancement. Proc. IDEAL 2013, LNCS 8206, pp. 295-302, 2013. (c) Springer
• S. Ali-Pitchay and A. Kaban. Single-frame Signal Recovery using a Similarity Prior. Mathematical Methodologies in Pattern Recognition and Machine Learning, Vol. 30, 2013, pp.83-98. (c) Springer

2012

• J. Bootkrajang and A. Kaban. Label-noise Robust Logistic Regression and its Applications. Proc. ECML-PKDD(1) 2012, pp. 143-158.
• S. Ali-Pitchay and A. Kaban. Multi-task Signal Recovery by Higher Level Hyper-parameter Sharing. Proc. 21^st Int. Conference on Pattern Recognition (ICPR 2012).
• H. Al-Baity, S. Meshoul and A. Kaban. On Extending Quantum-Behaved Particle Swarm Optimization to Multi-Objective Context. Proc. IEEE Congress on Evolutionary Computation (CEC 2012), 2012, pp. 1-8.
• H. Al-Baity, S. Meshoul and A. Kaban. Constrained multi-objective optimization using a quantum behaved particle swarm. Neural Information Processing, Lecture Notes in Computer Science, Vol. 7665, 2012, pp. 456-464.
• R.J. Durrant and A. Kaban. Error Bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert Space. 15-th International Conference on Artificial Intelligence and Statistics (AiStats 2012), Journal of Machine Learning Research-Proceedings Track 22: 337-345, 2012.
• S. Ali-Pitchay and A. Kaban. Single-frame signal recovery using a similarity prior based on Pearson type VII MRF. 1-st International Conference on Pattern Recognition Applications and Methods (ICPRAM 2012), Vilamoura, Algarve, Portugal, 6-8 February 2012.
• R.J. Durrant and A. Kaban. A tight bound on the performance of Fisher`s linear discriminant in randomly projected data spaces. Pattern Recognition Letters, ICPR2010 Awards special issue, 33(7):911-919, 2012.
• A. Kaban and S. Ali Pitchay. Single-frame Image Recovery using a Pearson type VII MRF. Neurocomputing, MLSP2010 special issue. 80: 111-119, 2012.
• A. Kaban. Non-parametric Detection of Meaningless Distances in High-Dimensional Data. Statistics and Computing. 22(1): 375-385. code

2011

• A. Kaban. On the Distance Concentration Awareness of Certain Data Reduction Techniques. Pattern Recognition. Vol. 44, Issue 2, Feb 2011, pp.265-277.
• J. Bootkrajang and A. Kaban. Multiclass learning with labeling errors. 19-th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2011), 23-29 April 2011, Bruges, Belgium.

2010

• R.J. Durrant and A. Kaban. Compressed Fisher Linear Discriminant Analysis: Classification of Randomly Projected Data. Proceedings of the 16^th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2010) July 25-28, 2010, Washington, DC, USA; Session track: KDD methodology; pp.1119-1128, 2010.
• R.J. Durrant and A. Kaban. A bound on the performance of LDA in randomly projected data spaces. Proc. 20^th International Conference on Pattern Recognition (ICPR 2010) August 23-26, 2010, Istanbul, Turkey - IBM Best Student Paper Award, Track: Pattern Recognition and Machine Learning.
• J. Sun and A. Kaban. A Fast Algorithm for Robust Mixtures in the Presence of Measurement Errors. IEEE Transactions on Neural Networks. Vol. 21, Issue 8, pp. 1206-1220, 2010.
• J. Sun, A. Kaban, J.M. Garibaldi. Robust Mixture Modeling Using the Pearson Type VII Distribution. Pattern Recognition Letters. . Vol. 31, Issue 16, Dec 2010, pp. 2447-2454.
• A. Kaban and S.Ali-Pitchay. Single-frame Image Super-resolution using a Pearson type VII MRF. Proc. IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010). August 29 - September 1, 2010, Kittila, Finland.

2009

• R. J. Durrant and A. Kaban. When is 'Nearest Neighbor' Meaningful: A Converse Theorem and Implications Journal of Complexity. Volume 25, Issue 4, August 2009, pp. 385-397. pdf. Nr 3 in Science Direct 25 Hottest Articles for Journal of Complexity Oct 2009-Sept 2010.
• E. Bingham, A. Kaban, M. Fortelius. The aspect Bernoulli model: Multiple causes of presences and absences. Pattern Analysis and Applications Vol. 12, No 1 / Feb, pp. 55-78, 2009. code
• D. Peavoy and A. Kaban. Bayesian Learning of Genetic Network Structure in the Space of Differential Equation Models. BioSysBio Conference, Cambridge, 23 - 25 March, 2009. slides

2008

• X. Wang and A. Kaban. A dynamic bibliometric model for identifying online communities. Data Mining and Knowledge Discovery, vol. 16 Nr. 1, pp. 67-107, 2008.
• A. Kaban and E. Bingham. Factorisation and denoising of 0-1 data: A variational approach. Neurocomputing, Vol 71, Issues 10-12, June 2008, pp. 2291-2308.
• A. Kaban and R.J. Durrant. Learning with Lq<1 vs L1-norm regularization with exponentially many irrelevant features. Proc. of the 1^9th European Conference on Machine Learning (ECML08), 15-19 Sept 2008, Antwerp, Belgium. W. Daelemans et al. (eds.): LNAI 5211, pp. 580-596. (c) Springer. slides code
• A. Kaban. A probabilistic neighborhood translation approach for non-standard text categorization. Proc. Discovery Science (DS08), 13-16 October 2008, Budapest, Hungary. LNAI (c) Springer, J.-F Boulicaut, M.R Berthold and T. Horvath (eds): LNAI 5255, pp. 332-343, 2008. (c) Springer.

2007

• A. Kaban. Predictive Modelling of Heterogeneous Sequence Collections by Topographic Ordering of Histories. Machine Learning Journal, Vol. 68, Nr 1 / July, 2007, pp.63-95. (c) Springer. code
• A. Kaban. On Bayesian Classification with Laplace Priors. Pattern Recognition Letters vol. 28 issue 10, July 2007, pp. 1271-1282. (c) Elsevier.
• M. Harva and A. Kaban. Variational Learning for Rectified Factor Analysis. Signal Processing, 87(3), pp.509-527. (c) Elsevier, 2007
• L. Nolan, S. Raychaudhury and A. Kaban. Young stellar populations in early-type galaxies in the Sloan Digital Sky Survey. Mon. Not. of the Royal Astron. Soc., 375 (1), 381-387, Blackwell Publisher, 2007. code
• J. Sun, A. Kaban and S. Raychaudhury. Robust mixtures in the presence of measurement errors. In Proceedings of the 24-th Annual International Conference on Machine Learning 2007 (ICML07), (Ed.) Z. Ghahramani. June 20-24, Oregon State University, Corvallis, OR, USA, pp. 847-854. slides code
• J. Sun, A. Kaban and S. Raychaudhury. Robust visual mining of data with error information. The 11-th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD07). 17-21 September 2007, Warsaw, Poland, pp.573-580.

2006

• LA Nolan, M Harva, A Kaban and S Raychaudhury, A data-driven Bayesian approach to finding young stellar populations in early-type galaxies from their UV-optical spectra, Mon. Not. of the Royal Astron. Soc., Blackwell Publisher. 366(1), pp. 321-338, 2006

• A Kaban and X Wang. Deconvolutive Clustering of Markov States. The 17th European Conference on Machine Learning (ECML06), LNAI 4212, pp. 246-257, 2006. (c) Springer; (Eds.) J Fuernkranz, T Scheffer and M Spiliopoulou. slides
• A Kaban and E Bingham. ICA-based Binary Feature Construction. Proc. of the 6-th International Conference on Independent Component Analysis and Blind Source Separation (ICA06). Charleston, March 5-8, South Carolina, USA. (c) Springer. Eds: J Rosca, D Erdogmus, J.C Principe, S Haykin. pp. 140-148,2006. LNCS 3889, ISBN 3-540-32630-8. slides

• A Kaban, J Sun, S Raychaudhury, L Nolan. On class visualisation for high dimensional data: Exploring scientific data sets. Proc. of the 9-th International Conference on Discovery Science (DS06), October 2006, Barcelona, Spain. LNAI 4265, (c) Springer. slides
• X Wang and A Kaban. Model-based Estimation of Word Saliency in Text. Proc. of the 9-th International Conference on Discovery Science (DS06), October 2006, Barcelona, Spain. LNAI 4265, (c) Springer.
• X Wang and A Kaban. State Aggregation in Higher-Order Markov Chains for Finding Online Communities. 7-th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL06). Sept 2006, Burgos, Spain.

2005

• M Girolami and A Kaban. Sequential Activity Profiling: Latent Dirichlet Allocation of Markov Chains. Data Mining and Knowledge Discovery. 10, pp. 175--196, 2005. code
• I Nabney, Y Sun, P Tino and A Kaban: Semisupervised Learning of Hierarchical Latent Trait Models for Data Visualization. IEEE Transactions on Knowledge and Data Engineering.  17(3), 2005.
• A Kaban, L Nolan and S Raychaudhury. Finding Young Stellar Populations in Elliptical Galaxies from Independent Components of Optical Spectra. Proc. SIAM International Conference on Data Mining (SDM05), 21--24 April 2005, Newport Beach California, USA, pp. 183--194.
• M Harva and A Kaban, A Variational Bayesian Method for Rectified Factor Analysis. Proc. IEEE International Joint Conference on Neural Networks (IJCNN05), Montreal, pp. 185-190.

• A Kaban, A Scalable Generative Topographic Mapping for Sparse Data Sequences. Proc. IEEE International Conference on Information Technology: Coding and Computing (ITCC05), Track: Data Coding and Compression, April 4--6, 2005, Las Vegas, NV, USA, pp.51--56. slides

• X Wang and A Kaban, Finding Uninformative Features in Binary Data, Proc. of the Sixth International Conference on Intelligent Data Engineering and Automated Learning (IDEAL05), 6-8 July, Queensland, Australia, pp. 40-47. (c) Springer
• A Kaban. ICA-rn launch day poster. 15 April, 2005.

2004

• M Girolami and A Kaban. Simplicial Mixtures of Markov Chains: Distributed Modelling of Dynamic User Profiles. Advances in Neural Information Processing Systems 16 (NIPS), eds Sebastian Thrun, Lawrence Saul and Bernard Scholkopf, The MIT Press 2004, pp. 9-16.
• P Tino, A Kaban and Y Sun. A Generative Probabilistic Approach to Visualising Sets of Symbolic Sequences. Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - (KDD04), August 22-25, Seattle, Washington, USA, (eds.) R. Kohavi, J. Gehrke, W. DuMouchel, J. Ghosh. pp. 701-706, ACM Press, 2004.
• A Kaban, E Bingham and T Hirsimaki. Learning to Read Between the Lines: The Aspect Bernoulli Model, Proc. of the SIAM International Conference on Data Mining (SDM04), April 22-24 2004, Florida, USA, (eds.) Michael W. Berry, Umeshwar Dayal, Chandrika Kamath and David Skillicorn, pp.462-466. code
• A Kaban and X Wang. Context-Based Identification of User Communities from Internet Chat, Proc. IEEE International Joint Conference on Neural Networks (IJCNN04), special session On Machine Learning for Text Mining (invited paper). July, Budapest, Hungary, pp 3287--3292.

2003

• E Bingham, A Kaban and M Girolami. Topic identification in dynamical text by complexity pursuit, Neural Processing Letters 17: 1-15, 2003, pp. 69-83. Code: cp.m, test_cp.m

• Kaban, A and Girolami, M. Fast Extraction of Semantic Features from a Latent Semantic Indexed Corpus. Neural Processing Letters, vol. 15, issue 1, 2002, pp. 31-43.
• M Girolami and A Kaban. On an equivalence between PLSI and LDA, 26-th Annual International ACM Conference on Research and Development in Information Retrieval (SIGIR03), July 28-August 1, 2003, Toronto, Canada, pp 433-434.

2002

• Kaban, A. and Girolami, M: A Dynamic Probabilistic Model to Visualise Topic Evolution in Text Streams, Journal of Intelligent Information Systems, special issue on Automated Text Categorization, 18:2/3, 107-125, 2002.

• Kaban, A, Tino, P. and Girolami, M. A General Framework for a Principled Hierarchical Visualisation of Multivariate Data, the Third International Conference on Intelligent Data Engineering and Automated Learning (IDEAL02), pp. 17-23, Lecture Notes in Computer Science, Springer-Verlag, 2002.

2001

• Kaban, A and Girolami, M. A Combined Latent Class and Trait Model for the Analysis and Visualisation of Discrete Data IEEE Transactions on Pattern Analysis and Machine Intelligence 23(8), pp. 859-872, 2001. code

• Lorincz, A, Szatmary, B. and Kaban, A. Sign-changing filters similar to cells in primary visual cortex emerge by independent component analysis of temporally convolved natural image sequences, Neurocomputing 38-40, 2001, pp. 1437-1442.
• Bingham, E, Kaban, A. and Girolami, M. Finding topics in dynamical text: application to chat line discussions. WWW10, May 1--5, 2001, Hong Kong, Poster Proceedings pp. 198--199.

2000

• Kaban, A. and Girolami, M. Initialised and Guided EM-Clustering of Sparse Binary Data with Applications to Text Based Documents. Proc. of the 15'th International Conference on Pattern Recognition ICPR00. Barcelona, Spain, September, 2000, IEEE Computer Press, vol.2, pp. 748--751.
• Kaban, A and Girolami, M. Clustering of Text Documents by Skewness Maximisation. Proc. of the 2'nd International Workshop on Independent Component Analysis and Blind Source Separation, ICA00, June 2000, Helsinki, pp. 435-440.
• Kaban, A. and Girolami, M. Initialised and Guided EM-Clustering of Binary Coded Text Based Documents Proc. EIS00, Paisley, July 2000.
• Girolami, M, Vinokourov, A and Kaban, A. The Organisation and Visualisation of Document Corpora: A Probabilistic Approach. Invited paper. Proc. of the 11?th International Conference and Workshop on Database and Expert Systems Applications DEXA00.
• Andras, P, Kaban, A, Bossanyi, R. Neural Network Approximation of Fuzzy Logic Operators. Annales Universitatis Occidentalis Timisiensis, Series Philosophia, Vol. XII, 2000, ISSN 1224-9688, pp. 147-152.

Technical Reports

• R.J Durrant and A Kaban. Flip Probabilities for Random Projections of θ-separated vectors. Technical Report CSR10-10, School of Computer Science, The University of Birmingham.
• R.J Durrant and A Kaban. Random Projections as Regularisers: Learning a Linear Discriminant Ensemble from Fewer Observations than Dimensions. Technical Report CSR-12-01, School of Computer Science, The University of Birmingham.

Other - Abstracts and workshop contributions

• Tutorial in Random Projections for Machine Learning and Data Mining: Theory and Practice at ECML-PKDD’2012 at Bristol, Sept. 2012 – with Bob Durrant.
• Learning and Regularisation with Random Projections. Simple’12, MPI Dresden, Germany, Sept. 2012.
• Distance concentration and detection of meaningless distances. Schloss Dagstuhl seminar on Information Visualisation, Visual Data Mining and Machine Learning, February 2012.
• A Kaban and R.J Durrant. Subspace-adaptiveness of Compressive FLD. ERCIM 2011 – invited talk for “High-dimensional statistics, sparsity and applications” by Gerard Biau and Pierre Alquier. 17-19 December 2011, Senate House, University of London, UK.
• R.J Durrant and A Kaban. Finite sample effects in compressed Fisher Discriminant Analysis. AISTATS 2010 ‘breaking news’ abstract. 13-15 May 2010.
• A Kaban. A statistical test to detect distance concentration from data sets. AISTATS 2010 ‘breaking news’ abstract. 13-15 May 2010.
• A Kaban. Lq-regularised sparse classifiers: A PAC-Bayes analysis. Workshop on Sparsity in Machine learning and Statistics, Cumberland Lodge, 1-3 April, 2009. slides poster
• R.J Durrant and A Kaban. Sparsity in the context of learning from high dimensional data. ICArn Workshop, Liverpool, September 2008.
• A Kaban and R.J Durrant. A norm-concentration argument for non-convex regularization. ICML/UAI/COLT Workshop on Sparse Optimization and Variable Selection, 9 July, 2008, Helsinki, Finland. slides
• A Kaban. The concentration of the L2 distance in latent variable models & some consequences. Workshop on Future Directions in High-Dimensional Data Analysis, Newton Institute of Mathematical Sciences, Cambridge, UK, 23-27 June 2008.
• A Kaban. Two applications of variational inference: Astrophysics and gene expression analysis. Research Kitchen on Approximate Inference, Bath, 8-9 May 2007.
• A Kaban, L Nolan and S Raychaudhury. Factorisation of Positive Valued Functions for Analysing Galaxy Spectra. ICA Research Network Workshop (ICArn06), September 2006, Liverpool. slides
• A Kaban. ICA-rn launch day poster. 15 April, 2005.