mypic

I am a senior scientist at The Netherlands Organization for Applied Scientific Research.
Email: evgeni.tsivtsivadze[at]tno.nl


Currently my main research interests are in statistical machine learning. I am working on multi-view kernel-based methods as well as their applications in systems biology, automated reasoning, and information retrieval.

Projects

Oral Health. Funded by TIFN (Ongoing). We develop multi-view statistical algorithms for learning from large scale clinical, microbiological, and immunological datasets to identify biomarkers that promote oral health.

Learning2Reason. Funded by NWO (Ongoing). The general aim of this project is to develop machine learning algorithms suitable for mining large corpora of formally expressed knowledge that are available in the fields of formal mathematics and software verification.

Microbial Growth Prediction. Funded by TIFN (Ongoing). We apply probabilistic, semi-supervised machine learning methods to model growth, interaction, and effects of various microbial species on spoilage process.

GENEUSS (GEne NEtworks Underlying Synaptic Signaling). Funded by NWO (Past). Within this project we develop and apply machine learning techniques to construct a dynamic model for the presynaptic gene network underlying short-term plasticity in neuronal synapses.

Bio Text. Funded by TEKES (Past). We combine structural natural language processing with machine learning methods to address the general and domain-specific challenges of information extraction in biomedical domain.


Publications (bibtex file)


2014

Giske Biesbroek , Evgeni Tsivtsivadze , Elisabeth A.M. Sanders , Roy Montijn , Reinier H. Veenhoven , Bart J.F. Keijser , and Debby Bogaert.
Early Respiratory Microbiota Composition Determines Bacterial Succession Patterns and Respiratory Health in Children.
Blue Journal (American Journal of Respiratory and Critical Care Medicine), 2014. [ bib | http ]

Sultan Imangaliyev, Bart Keijser, Wim Crielaard, and Evgeni Tsivtsivadze.
Personalized microbial network inference via co-regularized spectral clustering.
IEEE International Conference on Bioinformatics, 2014. [ bib | http ]

Hanneke Borgdorff, Evgeni Tsivtsivadze, Rita Verhelst, Massimo Marzorati, Suzanne Jurriaans, Ndayisaba Gilles François, Frank H Schuren, and Janneke van de Wijgert.
On Cervicovaginal Microbiome and HIV/STI.
Nature Publishing Group, ISME Journal , 2014. [ bib | http ]

Armand Paauw, Hein Trip, Marcin Niemcewicz, Ricela Sellek, Jonathan M.E. Heng, Roos H. Mars-Groenendijk, Ad L. de Jong, Joanna A. Majchrzykiewicz-Koehorst, Jaran S. Olsen, and Evgeni Tsivtsivadze.
OmpU as a biomarker for rapid discrimination between toxigenic and epidemic Vibrio cholerae O1/O139 and non-epidemic Vibrio cholerae in a modified MALDI-TOF MS assay.
BMC Microbiology , 2014. [ bib | http ]

Daniël van Schalkwijk, Albert de Graaf, Evgeni Tsivtsivadze, Laurence Parnell, Bianca van der Werff-van der Vat, Ben van Ommen, Jan van der Greef, and José M. Ordovás.
Lipoprotein Metabolism Indicators Improve Cardiovascular Risk Prediction.
PLoS One, 2014. [To appear]

2013

Sultan Imangaliyev, Bart Keijser, Wim Crielaard, and Evgeni Tsivtsivadze.
Online Semi-supervised Learning: Algorithm and Application in Metagenomics.
IEEE International Conference on Bioinformatics, 2013. [ bib | http ]

Evgeni Tsivtsivadze and Tom Heskes.
Semi-supervised Ranking Pursuit.
Preprint at ArXiv [stat.ML] , 2013. [ bib | http ]

Evgeni Tsivtsivadze, Hanneke Borgdorff, Janneke van de Wijgert, Frank Schuren, Rita Verhelst, and Tom Heskes.
Neighborhood Co-regularized Multi-view Spectral Clustering of Microbiome Data.
Partially Supervised Learning, 2013. [ bib | .pdf ]

Evgeni Tsivtsivadze, Eveline Lommen, Roy Montijn, and Jos van der Vossen.
Semi-supervised Multi-view Gaussian Processes for Microbial Growth Prediction.
Intelligent Systems for Molecular Biology (ISMB/ECCB), 2013. [ bib | http ] (poster)

Evgeni Tsivtsivadze, Tom Heskes and Armand Paauw.
Multi-view Multi-class Classification for Identification of Pathogenic Bacterial Strains.
Multiple Classifier Systems, 2013. [ bib | .pdf | supplement]

2012

Lennart Niels Cornelisse, Evgeni Tsivtsivadze, Marieke Meijer, Tjeerd M.D. Dijkstra, Tom Heskes, and Matthijs Verhage.
Molecular machines in the synapse: Overlapping protein sets control distinct steps in neurosecretion.
PLoS Computation Biology, 2012. [bib  | http]

Jesse Alama, Daniel Kühlwein, Evgeni Tsivtsivadze, Josef Urban, and Tom Heskes.
Premise selection for mathematics by corpus analysis and kernel methods.
Journal of Automated Reasoning, 2012. [ bib | http ]

Evgeni Tsivtsivadze, Katja Hoffman, and Tom Heskes.
Large Scale Co-regularized Ranking.
ECAI Workshop on Preference Learning, 2012. (extension of the paper below) [ bib | .pdf ]

Tom de Ruijter, Evgeni Tsivtsivadze, and Tom Heskes.
Online Co-regularized Algorithms.
Algorithmic Learning Theory/Discovery Science, 2012. [ bib | .pdf | code]

Daniel Kühlwein, Twan van Laarhoven, Evgeni Tsivtsivadze, Josef Urban and Tom Heskes.
Overview and Evaluation of Premise Selection Techniques for Large Theory Mathematics.
International Joint Conference on Automated Reasoning, 2012. [ bib | .http ]

2011

Evgeni Tsivtsivadze, Josef Urban, Herman Geuvers, and Tom Heskes.
Semantic graph kernels for automated reasoning.
SIAM International Conference on Data Mining, 2011. [ bib | .pdf ]

Evgeni Tsivtsivadze, Tapio Pahikkala, Jorma Boberg, Tapio Salakoski, and Tom Heskes.
Co-regularized least-squares for label ranking.
Preference Learning, 2011. [ bib | http ]

Daniel Kühlwein, Evgeni Tsivtsivadze, Josef Urban, and Tom Heskes.
Learning semantics for automated reasoning.
NIPS Workshop on Learning Semantics, 2011. [ bib | .pdf ]

Daniel Kühlwein, Josef Urban, Evgeni Tsivtsivadze, Herman Geuvers, and Tom Heskes.
Multi-output ranking for automated reasoning.
International Conference on Knowledge Discovery and Information Retrieval, 2011. [ bib | .pdf ]

Daniel Kühlwein, Josef Urban, Evgeni Tsivtsivadze, Herman Geuvers, and Tom Heskes.
Learning2reason.
Calculemus/MKM, pages 298-300, 2011. [ bib | http ]


2010

Tapio Pahikkala, Willem Waegeman, Evgeni Tsivtsivadze, Tapio Salakoski, and Bernard De Baets.
Learning intransitive reciprocal relations with kernel methods.
European Journal of Operational Research, 2010. [ bib | http ]

Evgeni Tsivtsivadze and Tom Heskes.
Sparse preference learning.
NIPS Workshop on Practical Application of Sparse Modeling: Open Issues and New Directions, 2010. [ bib | .pdf ]

Antolin Janssen, Evgeni Tsivtsivadze, Jorma Boberg, Tjeerd Dijkstra, and Tom Heskes.
Efficient remote homology detection.
Pattern Recognition in Bioinformatics, 2010. [ bib | .pdf ]

Tjeerd Dijkstra, Evgeni Tsivtsivadze, Elena Marchiori, and Tom Heskes, editors. Pattern Recognition in Bioinformatics - 5th IAPR International Conference, 2010, Nijmegen, The Netherlands, September 22-24, 2010. Proceedings, volume 6282 of Lecture Notes in Computer Science. Springer, 2010. [ bib | http ]


2009

Tapio Pahikkala, Evgeni Tsivtsivadze, Antti Airola, Jouni Järvinen, and Jorma Boberg.
An efficient algorithm for learning to rank from preference graphs.
Machine Learning, 2009. [ bib | http ]

Evgeni Tsivtsivadze, Tapio Pahikkala, Jorma Boberg, and Tapio Salakoski.
Locality kernels for sequential data and their applications to parse ranking.
Applied Intelligence, 2009. [ bib | http ]

Evgeni Tsivtsivadze, Botond Cseke, and Tom Heskes.
Kernel principal component ranking: Robust ranking on noisy data.
ECML/PKDD Workshop on Preference Learning, 2009. [ bib | .pdf  | code]

Niels Cornelisse, Evgeni Tsivtsivadze, Marieke Meijer, Tjeerd Dijkstra, Tom Heskes, and Matthijs Verhage.
Identification of presynaptic gene clusters in synaptic signaling using functional data from genetic perturbation studies in hippocampal autapses.
INCF Congress of Neuroinformatics, Frontiers in Neuroinformatics, 2009. [ bib | http ]

Tapio Pahikkala, Willem Waegeman, Evgeni Tsivtsivadze, Tapio Salakoski, and Bernard De Baets.
From ranking to intransitive preference learning: Rock-paper-scissors and beyond.
ECML/PKDD Workshop on Preference Learning, 2009. [ bib | .pdf ]


2008

Evgeni Tsivtsivadze, Tapio Pahikkala, Jorma Boberg, and Tapio Salakoski.
Kernels for text analysis.
Advances of Computational Intelligence, 2008. [ bib | http ]

Evgeni Tsivtsivadze, Fabian Gieseke, Tapio Pahikkala, Jorma Boberg, and Tapio Salakoski.
Leanring preferences with co-regularized least squares.
ECML/PKDD-Workshop on Preference Learning, 2008. [ bib | .pdf ]

Evgeni Tsivtsivadze, Tapio Pahikkala, Antti Airola, Jorma Boberg, and Tapio Salakoski.
A sparse regularized least-squares preference learning algorithm.
Scandinavian Conference on Artificial Intelligence, 2008. [ bib | .pdf ]

Tapio Pahikkala, Evgeni Tsivtsivadze, Antti Airola, Jorma Boberg, and Tapio Salakoski.
Regularized least-squares for learning non-transitive preferences between strategies.
Finnish Artificial Intelligence Conference, 2008. [ bib ]


2007

Evgeni Tsivtsivadze, Jorma Boberg, and Tapio Salakoski.
Locality kernels for protein classification.
International Workshop on Algorithms in Bioinformatics, 2007. [ bib | http ]

Tapio Pahikkala, Evgeni Tsivtsivadze, Antti Airola, Jorma Boberg, and Tapio Salakoski.
Learning to rank with pairwise regularized least-squares.
SIGIR Workshop on Learning to Rank for Information Retrieval, 2007. [ bib | .pdf ]


2006

Evgeni Tsivtsivadze, Tapio Pahikkala, Jorma Boberg, and Tapio Salakoski.
Locality-convolution kernel and its application to dependency parse ranking.
Conference on Applied Intelligent Systems, 2006. [ bib | .pdf ]

Tapio Pahikkala, Evgeni Tsivtsivadze, Jorma Boberg, and Tapio Salakoski.
Graph kernels versus graph representations: a case study in parse ranking.
MLG - Mining and Learning with Graphs, 2006. [ bib | .pdf ]


2005

Evgeni Tsivtsivadze, Tapio Pahikkala, Sampo Pyysalo, Jorma Boberg, Aleksandr Mylläri, and Tapio Salakoski.
Regularized least-squares for parse ranking.
Advances in Intelligent Data Analysis, 2005. [ bib | .pdf ]

Filip Ginter, Tapio Pahikkala, Sampo Pyysalo, Evgeni Tsivtsivadze, Jorma Boberg, Jouni Jarvinen, Aleksandr Myllari, and Tapio Salakoski.
Information extraction from biomedical text: The biotext project.
Conference on Human Language Technologies, 2005. [ bib | .pdf ]


CODE

Online Co-regularized Algorithm. The proposed algorithm is particularly applicable to learning tasks where large amounts of (unlabeled) data are available for training. The algorithm co-regularizes prediction functions on unlabeled data points and leads to improved performance in comparison to several baseline methods on UCI benchmarks and a real world natural language processing datasets.

Probabilistic Preference Learner/Ranker - ProbRank. The algorithm can learn a ranking function based on pairwise comparison data, that is, data about the ranking function values is provided in terms of pairwise comparisons at the given locations. This is accomplished in two ways: a) Approximating the marginal likelihood using expectation propagation and carrying out maximum likelihood procedure on the hyper-parameters. In this case the square exponential covariance function is used. b) Considering ranking as a regression with Gaussian noise and Gaussian processes prior, given the score differences.

Joint work with Botond Cseke. Download Matlab implementation of the probabilistic preference learning models described in "Kernel principal component ranking: Robust ranking on noisy data".

E-MaLeS 1.0 (3rd place in the FOF division of the CADE ATP System Competition). E-MaLeS 1.0 is an automated theorem prover which is based on E prover. E-MaleS 1.0 uses E with different strategies than the standard auto mode. Furthermore it employs strategy splitting, e.g. it runs several strategies. Note that this version is very CASC focused.

Joint work with Daniel Kuehlwein. Download the code.

Multi-Output Ranker for Automated Reasoning. Joint work with Daniel Kuehlwein. Download the code and the data used in the experiments of the paper "Multi-Output Ranking for Automated Reasoning".


Datasets

OmpU as a biomarker for rapid discrimination between toxigenic and epidemic Vibrio cholerae O1/O139 and non-epidemic Vibrio cholerae in a modified MALDI-TOF MS assay. Manuscript by Armand Paauw, Hein Trip, Marcin Niemcewicz, Ricela Sellek, Jonathan M.E. Heng, Roos H. Mars-Groenendijk, Ad L. de Jong, Joanna A. Majchrzykiewicz-Koehorst, Jaran S. Olsen, and Evgeni Tsivtsivadze


Links

  • TNO

  • Machine Learning Group

  • Turku BioNLP Group

  • CNCR

  • Student Projects