Antti Honkela

Professor, Department of Computer Science, University of Helsinki
Coordinating Professor of Research Programme in Privacy-preserving and Secure AI, Finnish Center for Artificial Intelligence (FCAI)
D.Sc. (Tech.), Docent in Statistical Machine Learning (Aalto University)

Open postdoc and/or PhD positions in probabilistic modelling with differential privacy

Antti Honkela is a Professor of Data Science (Machine Learning and AI) at the Department of Computer Science, University of Helsinki. Prior to his current appointment, he was an Assistant Professor of Statistics at the Department of Mathematics and Statistics and the Department of Public Health, University of Helsinki. He is the coordinating professor of Research Programme in Privacy-preserving and Secure AI at the Finnish Center for Artificial Intelligence (FCAI), a flagship of research excellence appointed by the Academy of Finland, and leader of the Privacy and infrastructures WP in European Lighthouse in Secure and Safe AI (ELSA), a European network of excellence in secure and safe AI. He serves in multiple advisory positions for the Finnish government in privacy of health data.

Prof. Honkela's research interests include privacy-preserving machine learning and differential privacy, Bayesian machine learning and probabilistic modelling, as well as their applications in computational biology and health.

Prof. Honkela is an action editor for the Transactions on Machine Learning and regularly serves as area chair for NeurIPS, ICML and AISTATS.

News

Started as a full professor in the beginning of 2023.
New paper Strong pathogen competition in neonatal gut colonisation published in Nature Communications.
European Lighthouse in Secure and Safe AI funded by Horizon Europe.
New paper Differentially Private Bayesian Inference for Generalized Linear Models accepted to ICML 2021.
New paper Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT accepted to AISTATS 2021.
Data Literacy for Responsible Decision-making project funded by the Strategic Research Council at the Academy of Finland.
I am co-organising the Privacy-Preserving Machine Learning workshop at NeurIPS 2020.
Two papers accepted to AISTATS 2020: Learning Rate Adaptation for Differentially Private Learning and Computing Tight Differential Privacy Guarantees Using FFT
New paper Differentially Private Markov Chain Monte Carlo accepted as a spotlight at NeurIPS 2019.
I am co-organising the Privacy in Machine Learning workshop at NeurIPS 2019.
New paper Representation transfer for differentially private drug sensitivity prediction published at ISMB/ECCB 2019.
I have started as an associate professor (tenure track) of data science at the Department of Computer Science at the University of Helsinki.
I am co-organising the Machine Learning Open Source Software 2018: Sustainable communities workshop at NeurIPS 2018
I am co-organising the Privacy in Machine Learning and Artificial Intelligence workshop at the Federated AI Meetings 2018 in Stockholm.
New paper Differentially private Bayesian learning on distributed data accepted to NIPS 2017.
I am co-organising the ICML 2017 Workshop on Privacy and Secure Machine Learning

Research group

Postdocs

Joonas Jälkö
Razane Tajeddine

PhD students

Elio Nushi
Ossi Räisä
Marlon Tobaben
Aki Rehn
Gauri Pradhan
Talal Alrawajfeh

Alumni

Onur Dikmen (Postdoc)
Mikko Heikkilä (PhD student)
Liisa Ilvonen (Postdoc)
Antti Koskela (Postdoc)
Tommi Mäklin (PhD student)
Ola Salman (Postdoc)
Hande Topa (PhD student)

Selected projects

Contact information

Room D228 at the Department of Computer Science, Exactum, Kumpula campus, University of Helsinki
Telephone: +358 2941 51253
Email: antti.honkela@helsinki.fi
Mobile: +358 50 311 2483

Mailing address:

Department of Computer Science
University of Helsinki
P.O. Box 68 (Pietari Kalmin katu 5)
00014 University of Helsinki, Finland

Software

Differential privacy software on GitHub.
My group's software releases on GitHub.
BitSeq software for transcript-level expression and differential expression estimation from RNA-sequencing data is available as a standalone C++ package and in BitSeq Bioconductor package.
The tigre package implementing the transcription factor target ranking method from our recent PNAS paper is available in Bioconductor. A Matlab implementation used to produce the results reported in the paper is also available.
tigreBrowser is a web-based browser for displaying and ranking genomic modelling results. It allows easy viewing, sorting and filtering of visualisations of models from tigre or other tools.
Older free software tools I have created are available on the pages of the Bayes and IVGA groups.

Teaching

University of Helsinki:
Autumn 2022: DATA11007 Statistics for Data Science; DATA20019 Trustworthy Machine Learning
Autumn 2021: DATA20019 Trustworthy Machine Learning
Autumn 2020: MAST32001 Computational statistics I; DATA20019 Trustworthy Machine Learning
Autumn 2019: MAST32001 Computational statistics I; DATA20019 Trustworthy Machine Learning
Autumn 2018: MAST32001 Computational statistics I
Spring 2018: Statistical methods of medical research
Autumn 2017: MAST32001 Computational statistics I
Spring 2017: Statistical methods of medical research
Autumn 2016: 58316301 Seminar on Probabilistic Programming; 582746 Modelling and Analysis in Bioinformatics
Autumn 2015: 582746 Modelling and Analysis in Bioinformatics
Autumn 2014: 58314301 Seminar in Probabilistic Models for Big Data
Spring 2014: 582637 Project in Probabilistic Models
Spring 2013: 582637 Project in Probabilistic Models
Spring 2012: 582637 Project in Probabilistic Models
Spring 2011: 582637 Project in Probabilistic Models

Helsinki University of Technology:
Spring 2009: T-61.6070 Special Course in Bioinformatics I: Learning and Inference in Dynamic Models of Biological Networks
Autumn 2008: T-61.5110 Modelling of biological networks
2006-2007: Scientific coordinator of the International Master's Programme in Machine Learning and Data Mining - Macadamia
Spring 2007: T-61.152 Informaatiotekniikan seminaari: tiedonhaku (Seminar in Computer and Information Science: Information retrieval)
Autumn 2006: T-61.6010 Special Course in Computer and Information Science I: Gaussian Processes for Machine Learning
Spring 2006: T-61.152 Informaatiotekniikan seminaari: ydinfunktiomenetelmät (Seminar in Computer and Information Science: Kernel methods)
2005-2006: Coordinator for the lab of Computer and Information Science for the department of Computer Science and Engineering B.Sc. seminar (Kandidaattiseminaari)
Autumn 2004: T-61.182 Information Theory and Machine Learning
Autumn 2001: T-61.181 Independent Component Analysis

Publications

Google Scholar
Pubmed

Journal articles

A. Honkela, J. Peltonen, H. Topa, I. Charapitsa, F. Matarese, K. Grote, H.G. Stunnenberg, G. Reid, N.D. Lawrence and M. Rattray.
Genome-wide modelling of transcription kinetics reveals patterns of RNA production delays.
PNAS (2015).
doi:10.1073/pnas.1420404112, arXiv:1503.01081 [q-bio.GN].

J. Hensman, P. Papastamoulis, P. Glaus, A. Honkela, and M. Rattray.
Fast and accurate approximate inference of transcript expression from RNA-seq data.
Bioinformatics (2015).
doi:10.1093/bioinformatics/btv483, arXiv:1412.5995 [q-bio.QM].
(Earlier version as arXiv:1308.5953 [q-bio.GN])

K. Uziela and A. Honkela.
Probe region expression estimation for RNA-seq data for improved microarray comparability.
PLoS ONE 10(5):e0126545 (2015).
DOI:10.1371/journal.pone.0126545, arXiv:1304.1698 [q-bio.GN]

H. Topa, Á Jónás, R. Kofler, C. Kosiol, and A. Honkela.
Gaussian process test for high-throughput sequencing time series: application to experimental evolution.
Bioinformatics 31(11):1762-1770 (2015).
doi:10.1093/bioinformatics/btv014, arXiv:1403.4086 [q-bio.PE].

J. C. Costello, L. M. Heiser, E. Georgii, M. Gönen, M. P. Menden, N. J. Wang, M. Bansal, M. Ammad-ud-din, P. Hintsanen, S. A. Khan, J-P. Mpindi, O. Kallioniemi, A. Honkela, T. Aittokallio, K. Wennerberg, NCI DREAM Community, J. J. Collins, D. Gallahan, D. Singer, J. Saez-Rodriguez, S. Kaski, J. W. Gray, and G. Stolovitzky.
A community effort to assess and improve drug sensitivity prediction algorithms.
Nature Biotechnology 32:1202-1212 (2014).
doi:10.1038/nbt.2877

S. Seth, N. Välimäki, S. Kaski, and A. Honkela.
Exploration and retrieval of whole-metagenome sequencing samples.
Bioinformatics 30(17):2471-2479 (2014).
doi:10.1093/bioinformatics/btu340, arXiv:1308.6074 [q-bio.GN]

C. wa Maina, A. Honkela, F. Matarese, K. Grote, H. G. Stunnenberg, G. Reid, N. D. Lawrence, and M. Rattray.
Inference of RNA Polymerase II Transcription Dynamics from Chromatin Immunoprecipitation Time Course Data.
PLoS Comput Biol 10(5):e1003598 (2014).
doi:10.1371/journal.pcbi.1003598, arXiv:1303.4926 [q-bio.QM]

M. Titsias^*, A. Honkela^*, N. D. Lawrence, and M. Rattray.
Identifying targets of multiple co-regulating transcription factors from expression time-series by Bayesian model comparison.
BMC Systems Biology 6:53 (2012).
doi:10.1186/1752-0509-6-53

P. Glaus, A. Honkela^*, and M. Rattray^*.
Identifying differentially expressed transcripts from RNA-seq data with biological variation.
Bioinformatics 28(13):1721-1728 (2012).
doi:10.1093/bioinformatics/bts260, arXiv:1109.0863 [q-bio.GN]

U. Remes, K. J. Palomäki, T. Raiko, A. Honkela, and M. Kurimo.
Missing-feature reconstruction with bounded nonlinear state-space model.
IEEE Signal Processing Letters 18(10):563-566 (2011).
doi:10.1109/LSP.2011.2163508

A. Honkela, P. Gao, J. Ropponen, M. Rattray, N. D. Lawrence.
tigre: Transcription factor Inference through Gaussian process Reconstruction of Expression for Bioconductor.
Bioinformatics 27(7):1026-1027 (2011).
doi:10.1093/bioinformatics/btr057

A. Honkela^*, T. Raiko^*, M. Kuusela, M. Tornio, and J. Karhunen.
Approximate Riemannian conjugate gradient learning for fixed-form variational Bayes.
Journal of Machine Learning Research 11(Nov):3235-3268 (2010).
(Also available: Pre-print pdf)

A. Honkela, C. Girardot, E. H. Gustafson, Y.-H. Liu, E. E. M. Furlong, N. D. Lawrence and M. Rattray.
Model-based method for transcription factor target identification with limited data.
Proc. Natl. Acad. Sci. U S A 107(17):7793-7798 (2010).
doi:10.1073/pnas.0914285107

P. Gao, A. Honkela, M. Rattray, and N. D. Lawrence.
Gaussian process modelling of latent chemical species: applications to inferring transcription factor activities.
Bioinformatics 24(16):i70-i75 (2008).
Appeared in Proceedings of ECCB 2008.
doi:10.1093/bioinformatics/btn278

A. Honkela, J. Seppä, and E. Alhoniemi.
Agglomerative Independent Variable Group Analysis.
Neurocomputing 71(7-9):1311-1320 (2008).
Appeared in Special Issue for the 15th European Symposium on Artificial Neural Networks (ESANN 2007).
doi:10.1016/j.neucom.2007.11.024

A. Honkela, H. Valpola, A. Ilin, and J. Karhunen.
Blind Separation of Nonlinear Mixtures by Variational Bayesian Learning.
Digital Signal Processing 17(5):914-934 (2007).
Appeared in Special Issue on Bayesian Source Separation.
doi:10.1016/j.dsp.2007.02.009

E. Alhoniemi, A. Honkela, K. Lagus, J. Seppä, P. Wagner, and H. Valpola.
Compact Modeling of Data Using Independent Variable Group Analysis.
IEEE Transactions on Neural Networks 18(6):1762-1776 (2007).
doi:10.1109/TNN.2007.900809

A. Honkela and H. Valpola.
Variational learning and bits-back coding: an information-theoretic view to Bayesian learning.
IEEE Transactions on Neural Networks 15(4):800-810 (2004).
Appeared in Special Issue on Information Theoretic Learning.
doi:10.1109/TNN.2004.828762

A. Honkela, H. Valpola and J. Karhunen.
Accelerating Cyclic Update Algorithms for Parameter Estimation by Pattern Searches.
Neural Processing Letters 17(2):191-203 (2003).
doi:10.1023/A:1023655202546

H. Valpola, E. Oja, A. Ilin, A. Honkela and J. Karhunen.
Nonlinear Blind Source Separation by Variational Bayesian Learning.
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E86-A(3):532-541 (2003).
Publisher electronic edition

Book chapters

N. Lawrence, M. Rattray, A. Honkela, and M. Titsias.
Gaussian Process Inference for Differential Equation Models of Transcriptional Regulation.
In M. P. H. Stumpf, D. J. Balding, and M. Girolami, eds., Handbook of Statistical Systems Biology, pp. 376-394, John Wiley & Sons, Chichester, UK (2011).
doi:10.1002/9781119970606.ch19

H. Lappalainen and A. Honkela.
Bayesian Nonlinear Independent Component Analysis by Multi-Layer Perceptrons.
In M. Girolami, editor, Advances in Independent Component Analysis, pp. 93 - 121, Springer (2000).
Also available as a PostScript version (420 kb).

Conference papers

B. H. Menze, K. Van Leemput, A. Honkela, E. Konukoglu, M. A. Weber, N. Ayache, and P. Golland.
A Generative Approach for Image-Based Modeling of Tumor Growth.
In Proceedings of the 22nd International Conference on Information Processing in Medical Imaging (IPMI 2011), Kloster Irsee, Germany.
Vol. 6801 of Lecture Notes in Computer Science, pp. 735-747, Springer-Verlag (2011).
doi:10.1007/978-3-642-22092-0_60

V. Peltola and A. Honkela.
Variational Inference and Learning for Non-Linear State-Space Models with State-Dependent Observation Noise.
In Proceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010), Kittilä, Finland, pp. 190-195 (2010).

A. Honkela, M. Milo, M. Holley, M. Rattray, and N. D. Lawrence.
Ranking of Gene Regulators through Differential Equations and Gaussian Processes.
In Proceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010), Kittilä, Finland, pp. 154-159 (2010).

M. Kuusela, T. Raiko, A. Honkela, and J. Karhunen.
A Gradient-Based Algorithm Competitive with Variational Bayesian EM for Mixture of Gaussians.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN 2009), Atlanta, Georgia, June 15-19 (2009).

A. Honkela, M. Tornio, T. Raiko, and J. Karhunen.
Natural Conjugate Gradient in Variational Inference.
In Proceedings of the 14th International Conference on Neural Information Processing (ICONIP 2007), Kitakyushu, Japan.
Vol. 4985 of Lecture Notes in Computer Science, pp. 305-314, Springer-Verlag (2008).
doi:10.1007/978-3-540-69162-4_32

A. Honkela, J. Seppä, and E. Alhoniemi.
Agglomerative Independent Variable Group Analysis.
In Proceedings of the 15th European Symposium on Artificial Neural Networks (ESANN 2007), Bruges, Belgium, pp. 55-60 (2007).

M. Tornio, A. Honkela, and J. Karhunen.
Time Series Prediction with Variational Bayesian Nonlinear State-Space Models.
In Proceedings of the European Symposium on Time Series Prediction (ESTSP 2007), Espoo, Finland, pp. 11-19 (2007).

J. Nikkilä, A. Honkela, and S. Kaski.
Exploring the Independence of Gene Regulatory Modules.
In J. Rousu, S. Kaski, and E. Ukkonen, editors, Proc. Workshop on Probabilistic Modeling and Machine Learning in Structural and Systems Biology, Tuusula, Finland, pp. 131-136 (2006).

T. Raiko, M. Tornio, A. Honkela and J. Karhunen.
State Inference in Variational Bayesian Nonlinear State-Space Models.
In Proceedings of the Sixth International Conference Independent Component Analysis and Blind Signal Separation (ICA 2006), Charleston, South Carolina, USA.
Vol. 3889 of Lecture Notes in Computer Science, pp. 222 - 229, Springer-Verlag (2006).
doi:10.1007/11679363_28

M. Harva, T. Raiko, A. Honkela, H. Valpola and J. Karhunen.
Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework.
In Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence, Edinburgh, UK, pp. 259 - 266 (2005).

K. Lagus, E. Alhoniemi, J. Seppä, A. Honkela and P. Wagner.
Independent Variable Group Analysis in Learning Compact Representations for Data.
In Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR'05), Helsinki, Finland, pp. 49 - 56 (2005).

A. Honkela, T. Östman, R. Vigário.
Empirical evidence of the linear nature of magnetoencephalograms.
In Proceedings of the 13th European Symposium on Artificial Neural Networks (ESANN 2005), Bruges, Belgium, pp. 285 - 290 (2005).

A. Honkela and H. Valpola.
Unsupervised Variational Bayesian Learning of Nonlinear Models.
In L. Saul, Y. Weiss, and L. Bottou, editors, Advances in Neural Information Processing Systems 17, pp. 593 - 600, The MIT Press (2005).

A. Ilin and A. Honkela.
Postnonlinear Independent Component Analysis by Variational Bayesian Learning.
In Proceedings of the Fifth International Conference Independent Component Analysis and Blind Signal Separation (ICA 2004), Granada, Spain.
Vol. 3195 of Lecture Notes in Computer Science, pp. 766 - 773, Springer-Verlag (2004).
Publisher electronic edition

A. Honkela, S. Harmeling, L. Lundqvist and H. Valpola.
Using Kernel PCA for Initialisation of Variational Bayesian Nonlinear Blind Source Separation Method.
In Proceedings of the Fifth International Conference Independent Component Analysis and Blind Signal Separation (ICA 2004), Granada, Spain.
Vol. 3195 of Lecture Notes in Computer Science, pp. 790 - 797, Springer-Verlag (2004).
Publisher electronic edition

A. Honkela.
Approximating Nonlinear Transformations of Probability Distributions for Nonlinear Independent Component Analysis.
In Proceedings of the 2004 IEEE International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, pp. 2169 - 2174 (2004).

V. Siivola and A. Honkela.
A State-Space Method for Language Modeling.
In Proceedings of the IEEE Workshop on Automatice Speech Recognition and Understanding (ASRU 2003), St. Thomas, U.S. Virgin Islands, pp. 548 - 553 (2003).

A. Honkela and H. Valpola.
On-line Variational Bayesian Learning.
In Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, pp. 803 - 808 (2003).

A. Honkela.
Speeding Up Cyclic Update Schemes by Pattern Searches.
In Proceedings of the 9th International Conference on Neural Information Processing (ICONIP'02), Singapore, pp. 512 - 516 (2002).

H. Valpola, A. Honkela, and J. Karhunen.
An Ensemble Learning Approach to Nonlinear Dynamic Blind Source Separation Using State-Space Models.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN'02), Honolulu, Hawaii, USA, pp. 460 - 465 (2002).

H. Valpola, A. Honkela, and J. Karhunen.
Nonlinear Static and Dynamic Blind Source Separation Using Ensemble Learning.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN'01), Washington D.C., USA, pp. 2750 - 2755 (2001).

A. Honkela and J. Karhunen.
An Ensemble Learning Approach to Nonlinear Independent Component Analysis.
In Proceedings of the European Conference on Circuit Theory and Design (ECCTD'01), Espoo, Finland, pp. I-41 - 44 (2001).

H. Valpola, X. Giannakopoulos, A. Honkela, and J. Karhunen.
Nonlinear Independent Component Analysis Using Ensemble Learning: Experiments and Discussion.
In Proceedings of the Second International Workshop on Independent Component Analysis and Blind Signal Separation, ICA 2000, Helsinki, Finland, pp. 351 - 356 (2000).

H. Lappalainen, A. Honkela, X. Giannakopoulos, and J. Karhunen.
Nonlinear Source Separation Using Ensemble Learning and MLP Networks.
In Proceedings of the Symposium 2000 on Adaptive Systems for Signal Processing, Communications, and Control (AS-SPCC), Lake Louise, Alberta, Canada, pp. 187 - 192 (2000).

Conference abstracts and presentations

A. Honkela, M. Tornio, and T. Raiko.
Variational Bayes for Continuous-Time Nonlinear State-Space Models.
In NIPS*2006 Workshop on Dynamical Systems, Stochastic Processes and Bayesian Inference, Whistler, B.C., Canada (2006).

A. Honkela, M. Harva, T. Raiko, H. Valpola, and J. Karhunen.
Bayes Blocks: A Python Toolbox for Variational Bayesian Learning.
In NIPS*2006 Workshop on Machine Learning Open Source Software, Whistler, B.C., Canada (2006).

A. Honkela.
Distributed Bayes Blocks for Variational Bayesian Learning.
In Conference on High Performance Computing for Statistical Inference, Dublin, Ireland (2006).

Theses

A. Honkela.
Advances in Variational Bayesian Nonlinear Blind Source Separation.
Doctoral thesis, Helsinki University of Technology, Espoo, Finland (2005).

A. Honkela.
Nonlinear Switching State-Space Models.
Master's thesis, Helsinki University of Technology, Espoo, Finland (2001).
(Browsable HTML version also available.)

Technical reports

H. Valpola and A. Honkela.
Hyperparameter Adaptation in Variational Bayes for the Gamma Distribution.
Publications in Computer and Information Science E6, Helsinki University of Technology, Espoo, Finland, 2006.

^* Equal contribution.

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Links

My personal home page (in Finnish)