Guy Wolf

Email: guy.wolf [at] umontreal.ca

Professeur agrégé / Associate Professor
Département de mathématiques et de statistique / Department of Mathematics and Statistics
Université de Montréal

Titulaire de chaire en IA Canada-CIFAR / Canada CIFAR AI Chair
CIFAR Pan-Canadian AI Strategy

Membre principal / Core Member
Mila - Institut québécois d’intelligence artificielle / Québec AI Institute

IVADO Professor
L'institut de valorisation des données / The institute for data valorization

Membre régulier/ Regular Member
CRM - Centre de recherches mathématiques / Center of Mathematical Research

Intérêts de recherche

Mes sujets de recherche se situent à l'intersection de l'apprentissage automatique, des sciences des données et des mathématiques appliquées. En particulier, je suis intéressé par les méthodes d'exploration des données qui utilisent l'apprentissage des variétés et l'apprentissage profond géométrique. Je m'intéresse aussi aux applications d'analyse exploratoire des données biomédicales, surtout ceux qui portent sur les données de cellules uniques (p.ex. scRNA-seq et CyTOF).

Major research interests

  1. Exploratory data analysis with manifold learning and deep learning
  2. Applied harmonic analysis, spectral graph theory, and diffusion geometry
  3. Graph signal processing and geometric deep learning
  4. Data-driven characterization of nonlinear structrures, patterns, and dynamics
  5. Biomedical big data applications (e.g., genomics and neuroscience)

Équipe de recherche: http://diffusion.space

Joining the team:


Enseignement / Teaching

Trimestre en cours / Current trimester:

Triemestres passés / Past trimesters:

For courses taught at Yale between 2015-2018 please use this link.


List of Publications

Preprints:

Journals:

  1. W.S. Chen, N. Zivanovic, D. van Dijk, G. Wolf, B. Bodenmiller, and S. Krishnaswamy. Uncovering axes of variation among single-cell cancer specimens. Naure Methods, 17:302-310, 2020.
  2. K.R. Moon, D. van Dijk, Z. Wang, S. Gigante, D.B. Burkhardt, W.S. Chen, K. Yim, A. van den Elzen, M.J. Hirn, R.R. Coifman, N.B. Ivanova, G. Wolf, and S. Krishnaswamy. Visualizing Structure and Transitions in High-Dimensional Biological Data. Nature Biotechnology, 37(12):1482-1492, 2019.
  3. M. Amodio, D. van Dijk, K. Srinivasan, W.S. Chen, H. Mohsen, K.R. Moon, A. Campbell, Y. Zhao, X. Wang, M. Venkataswamy, A. Desai, V. Ravi, P. Kumar, R. Montgomery, G. Wolf, and S. Krishnaswamy. Exploring Single-Cell Data with Deep Multitasking Neural Networks. Nature Methods, 16:1139–1145, 2019.
  4. D. van Dijk, R. Sharma, J. Nainys, K. Yim, P. Kathail, A.J. Carr, C. Burdziak, K.R. Moon, C.L. Chaffer, D. Pattabiraman, B. Bierie, L. Mazutis, G. Wolf, S. Krishnaswamy, and D. Pe’er. Recovering Gene Interactions from Single-Cell Data Using Data Diffusion. Cell, 174(3):716-729.e27, 2018.
  5. M. Salhov, A. Bermanis, G.Wolf, and A. Averbuch. Diffusion Representations. Applied and Computational Harmonic Analysis, 45(2):324-340, 2018.
  6. A. Bermanis, G. Wolf, and A. Averbuch. Diffusion-based kernel methods on Euclidean metric measure spaces. Applied and Computational Harmonic Analysis, 41(1):190-213, 2016.
  7. M. Salhov, A. Bermanis, G.Wolf, and A. Averbuch. Learning from patches by efficient spectral decomposition of a structured kernel. Machine Learning, 103(1):81-102, 2016.
  8. A. Bermanis, M. Salhov, G. Wolf, and A. Averbuch. Measure-based diffusion grid construction and high-dimensional data discretization. Applied and Computational Harmonic Analysis, 40(2):207-228, 2016.
  9. G. Wolf, S. Mallat, and S. Shamma. Rigid motion model for audio source separation. IEEE Transactions on Signal Processing, 64(7):1822-1831, 2016.
  10. M. Salhov, A. Bermanis, G. Wolf, and A. Averbuch. Approximately-isometric diffusion maps. Applied and Computational Harmonic Analysis, 38(3):399-419, 2015.
  11. A. Bermanis, G. Wolf, and A. Averbuch. Cover-based bounds on the numerical rank of Gaussian kernels. Applied and Computational Harmonic Analysis, 36(2):302-315, 2014.
  12. G. Wolf and A. Averbuch. Linear-projection diffusion on smooth Euclidean submanifolds. Applied and Computational Harmonic Analysis, 34(1):1-14, 2013.
  13. G. Wolf, A. Rotbart, G. David, and A. Averbuch. Coarse-grained localized diffusion. Applied and Computational Harmonic Analysis, 33(3):388-400, 2012.
  14. Y. Shmueli, G. Wolf, and A. Averbuch. Updating kernel methods in spectral decomposition by affinity perturbations. Linear Algebra and its Applications, 437(6):1356-1365, 2012.
  15. M. Salhov, G. Wolf, and A. Averbuch. Patch-to-tensor embedding. Applied and Computational Harmonic Analysis, 33(2):182-203, 2012.

Conference Proceedings:

  1. Y. Min, F. Wenkel, and G. Wolf. Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Online, 2020
  2. B. Rieck, T. Yates, C. Bock, K. Borgwardt, G. Wolf, N. Turk-Browne, S. Krishnaswamy. Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence. In Neural Information Processing Systems (NeurIPS 2020), Online, 2020.
  3. A.F. Duque, S. Morin, G. Wolf, and K.R. Moon. Extendable and Invertible Manifold Learning with Geometry Regularized Autoencoders. In the 2020 IEEE International Conference on Big Data, Online, 2020. [Preprint: arXiv:2007.07142]
  4. E. Castro, A. Benz, A. Tong, G. Wolf, S. Krishnaswamy. Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings. In the 2020 IEEE International Conference on Big Data, Online, 2020. [Preprint: arXiv:2006.06885]
  5. A. Tong, G. Wolf, and S. Krishnaswamy. Fixing Bias in Reconstruction-based Anomaly Detection with Lipschitz Discriminators. In the 2020 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2020), Online, 2020.
  6. M. Amodio, D. van Dijk, G. Wolf, and S. Krishnaswamy. Learning General Transformations of Data for Out-of-Sample Extensions. In the 2020 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2020), Online, 2020.
  7. M. Perlmutter, F. Gao, G. Wolf, and M. Hirn. Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds. In Proceedings of the 1st Annual Conference on Mathematical and Scientific Machine Learning (MSML 2020), Princeton, NJ, USA; PMLR, 107:1-35, 2020.
  8. A. Tong, J. Huang, G. Wolf, D. van Dijk, and S. Krishnaswamy. TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria; PMLR, 119:9526-9536, 2020.
  9. S. Horoi, V. Geadah, G. Wolf and G. Lajoie. Low-dimensional dynamics of encoding and learning in recurrent neural networks. In Goutte C., Zhu X., editors, Advances in Artificial Intelligence (Canadian AI 2020), Ottawa, ON, Canada, volume 12109 of LNCS, pp. 276-282, 2020.
  10. J.S. Stanley III, S. Gigante, G. Wolf, and S. Krishnaswamy. Harmonic Alignment. In Proceedings of the 2020 SIAM International Conference on Data Mining (SDM20), Cincinnati, OH, USA, pp. 316-324, 2020.
  11. A. Tong, D. van Dijk, J.S. Stanley III, M. Amodio, K. Yim, R. Muhle, J. Noonan, G. Wolf and S. Krishnaswamy. Interpretable Neuron Structuring with Graph Spectral Regularization. In M. Berthold, A. Feelders, G. Krempl, editors, Advances in Intelligent Data Analysis XVIII (IDA 2020), Bodenseeforum, Lake Constance, Germany, volume 12080 of LNCS, pp. 509-521, 2020.
  12. D. van Dijk, D. Burkhardt, M. Amodio, A. Tong, G. Wolf, and S. Krishnaswamy. Finding Archetypal Spaces for Data Using Neural Networks. In Proceedings of the 2019 IEEE International Conference on Big Data, Los Angeles, CA, USA, pp. 2634-2643, 2019.
  13. N. Brugnone, A. Gonopolskiy, M.W. Moyle, M. Kuchroo, D. van Dijk, K.R. Moon, D. Colon-Ramos, G. Wolf, M.J. Hirn, and S. Krishnaswamy. Coarse Graining of Data via Inhomogeneous Diffusion Condensation. In Proceedings of the 2019 IEEE International Conference on Big Data, Los Angeles, CA, USA, pp. 2624-2633, 2019.
  14. A.F. Duque G. Wolf K.R. Moon, Visualizing High Dimensional Dynamical Processes. In Proceeding of the 2019 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2019), Pittsburgh, PA, USA, pp. 1-6, 2019.
  15. S. Gigante, D. van Dijk, K.R. Moon, A. Strzalkowski, G. Wolf, and S. Krishnaswamy. Modeling Global Dynamics from Local Snapshots with Deep Generative Neural Networks. In The 13th international conference on Sampling Theory and Applications (SampTA 2019), Bordeaux, France, 2019.
  16. S. Gigante, J.S. Stanley III, N. Vu, D. van Dijk, K.R. Moon, G. Wolf, and S. Krishnaswamy. Compressed Diffusion. In the 13th International Conference on Sampling Theory and Applications (SampTA 2019), Bordeaux, France, 2019.
  17. F. Gao, G. Wolf, and M. Hirn, Geometric Scattering for Graph Data Analysis. In Proceedings of the 36th International Conference on Machine Learning (ICML 2019), Long Beach, CA, USA; PMLR, 97:2122-2131, 2019.
  18. D.B. Burkhardt, J.S. Stanley III, G. Wolf, and S. Krishnaswamy. Vertex Frequency Clustering. In Proceedings of the 2019 IEEE Data Science Workshop (DSW 2019), Minneapolis, MN, USA, pp. 145-149, 2019.
  19. O. Lindenbaum, J.S. Stanley III, G. Wolf, and S. Krishnaswamy. Geometry-Based Data Generation. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), Montréal, QC, Canada, pp. 1405-1416, 2018.
  20. G. Wolf, S. Mallat, and S. Shamma. Audio source separation with time-frequency velocities. In Proceedings of the 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2014), Reims, France, pp. 1-6, 2014.
  21. A. Bermanis, G. Wolf, and A. Averbuch. Measure-based diffusion kernel methods. In Proceeding of the 10th international conference on Sampling Theory and Applications (SampTA 2013), Bremen, Germany, pp. 489-492, 2013.
  22. M. Salhov, G. Wolf, A. Bermanis, and A. Averbuch. Constructive sampling for patch-based embedding. In Proceeding of the 10th international conference on Sampling Theory and Applications (SampTA 2013), Bremen, Germany, pp. 424-427, 2013.
  23. M. Salhov, G. Wolf, A. Bermanis, A. Averbuch, and P. Neittaanmäki. Dictionary construction for patch-to-tensor embedding. In J. Hollmén, F. Klawonn, and A. Tucker, editors, Advances in Intelligent Data Analysis XI (IDA 2012), Helsinki, Finland, volume 7619 of LNCS, pp. 346-356, 2012.
  24. M. Salhov, G. Wolf, A. Averbuch, and P. Neittaanmäki. Patch-based data analysis using linear-projection diffusion. In J. Hollmén, F. Klawonn, and A. Tucker, editors, Advances in Intelligent Data Analysis XI (IDA 2012), Helsinki, Finland, volume 7619 of LNCS, pp. 334-345, 2012.
  25. G. Wolf, Y. Shmuelli, S. Harussi, and A. Averbuch. Polar clustering. In Proceedings of ECCOMAS Thematic Conference on Computational Analysis and Optimization (CAO2011), Jyväskylä, Finland, pp. 174-177, 2011.

Workshops & Symposia:

  1. A. Tong, M. Kuchroo, G. Huguet, R.R. Coifman, G. Wolf, and S. Krishnaswamy. Fast diffusion optimal transport for manifold-of-manifold embeddings. In NeurIPS 2020 Workshop on Learning Meaningful Representations of Life (LMRL), 2020.
  2. M. Kuchroo, J. Huang, P. Wong, A. Iwasaki, G. Wolf, and S. Krishnaswamy. Multiscale PHATE exploration of SARS-CoV-2 data reveals signature of disease. In NeurIPS 2020 Workshop on Learning Meaningful Representations of Life (LMRL), 2020.
  3. M. ElAraby, G. Wolf, and M. Carvalho. Identifying efficient sub-networks using mixed integer programming. In NeurIPS 2020 Workshop on Optimization for Machine Learning (OPT2020),2020.
  4. Y. Wang, J. Tang, Y. Sun, and G. Wolf. Decoupled greedy learning of graph neural networks. In NeurIPS 2020 Workshop on Optimization for Machine Learning (OPT2020), 2020.
  5. A.F. Duque, S. Morin, G. Wolf, and K.R. Moon. Extendable and invertible manifold learning withgeometry regularized autoencoders. In NeurIPS 2020 Workshop on Differential Geometry Meets Deep Learning (DiffGeo4DL), 2020.
  6. A. Tong, F. Wenkel, K. Macdonald, S. Krishnaswamy, and G. Wolf. Data-driven learning ofgeometric scattering networks. In NeurIPS 2020 Workshop on Machine Learning for Molecules (ML4Molecules), 2020.
  7. S. Horoi, J. Huang, G. Wolf, and S. Krishnaswamy. Visualizing high-dimensional trajectories onthe loss-landscape of ANNs. In NeurIPS 2020 Workshop on Deep Learning Through Information Geometry (DL-IG), 2020.
  8. A. Tong, F. Wenkel, K. Macdonald, G. Wolf, and S. Krishnaswamy. Scattering priors for graphneural networks. In the DeepMath 2020 Conference on the Mathematical Theory of Deep Neural Networks, 2020.
  9. A.F. Duque, S. Morin, G. Wolf, and K.R. Moon. Extendable and invertible manifold learning withgeometry regularized autoencoders. In the DeepMath 2020 Conference on the Mathematical Theory of Deep Neural Networks, 2020.
  10. V. Geadah, G. Kerg, S. Horoi, G. Wolf, and G. Lajoie. Advantages of biologically-inspired adaptive neural activation in RNNs during learning. In Bernstein Conference, 2020.
  11. Y. Min, F. Wenkel, and G. Wolf. Scattering GCN: Overcoming Oversmoothness in Graph Conv. Networks. In Montreal AI Symposium (MAIS 2020), Montréal, QC, 2020.
  12. S. Morin, A.F. Duque, G. Wolf, and K.R. Moon. Extendable and invertible manifold learning with geometry regularized autoencoders. In Montreal AI Symposium (MAIS), Montréal, QC, 2020.
  13. M. ElAraby, G. Wolf, and M. Carvalho. Optimizing ANN Architectures using Mixed Integer Programming. In Montreal AI Symposium (MAIS), Montréal, QC, 2020.
  14. Y. Min, F. Wenkel, and G. Wolf. Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks. In ICML 2020 Graph Representation Learning and Beyond (GRL+) Workshop, Vienna, Austria, 2020.
  15. E. Castro, A. Benz, A. Tong, G. Wolf, and S. Krishnaswamy. Uncovering the Folding Landscape of RNA Secondary Structure with Deep Graph Embeddings. In ICML 2020 Graph Representation Learning and Beyond (GRL+) Workshop, Vienna, Austria, 2020.
  16. B. Rieck, T. Yates, G. Wolf, N. Turk-Browne and S. Krishnaswamy. Topological Methods for fMRI Data. In ICML 2020 Workshop on Computational Biology, Vienna, Austria, 2020.
  17. S. Horoi, G. Lajoie, and G. Wolf. Internal representation dynamics and geometry in recurrent neural networks. In Montreal AI Symposium (MAIS), Montréal, QC, 2019.
  18. J.S. Stanley III, S. Gigante, G. Wolf, and S. Krishnaswamy. Manifold Alignment by Feature Correspondence. In Signal Processing with Adaptive Sparse Structured Representations (SPARS), Toulouse, France, 2019.
  19. S. Gigante, J.S. Stanley III, N. Vu, D. van Dijk, K.R. Moon, G. Wolf, and S. Krishnaswamy. Compressed Diffusion. In Signal Processing with Adaptive Sparse Structured Representations (SPARS), Toulouse, France, 2019.
  20. F. Gao, G. Wolf, and M. Hirn. Geometric Scattering for Graph Data Analysis. In ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds, New Orleans, LA, 2019.
  21. A. Tong, D. van Dijk, J.S. Stanley III, M. Amodio, G. Wolf, and S. Krishnaswamy. Graph Spectral Regularization for Neural Network Interpretability, In ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds, New Orleans, LA, 2019.
  22. D.B. Burkhardt, J.S. Stanley III, A.L. Pertigoto, S.A. Gigante, K.C. Herold, G. Wolf, A.J. Giraldez, D. van Dijk, and S. Krishnaswamy. Enhancing experimental signals in single-cell RNA-sequencing data using graph signal processing. In ICLR 2019 Learning from Limited Labeled Data (LLD) Workshop, New Orleans, LA, 2019.
  23. F. Gao, G. Wolf, and M. Hirn. Geometric Scattering for Graph Data Analysis. In SDM 2019 Workshop on Deep Learning on Graphs, Calgary, AB, 2019.
  24. M. Perlmutter, G. Wolf, M. Hirn. Geometric Scattering on Manifolds. In NeurIPS 2018 Workshop on Integration of Deep Learning Theories, Montréal, QC, 2018.
  25. M. Aksen, S.I. Kronemer, J.S. Prince, Z. Ding, A. Agarwal, G. Wolf, B. Pearlmutter, R.R. Coifman, M. Pitts, H. Blumenfeld. Pupil dynamics as a covert measure of conscious perception in a visual no report paradigm. Program No. 789.12, 2018 Neuroscience Meeting, Society for Neuroscience, San Diego, CA, 2018.
  26. D. van Dijk, S. Gigante, K.R. Moon, A. Strzalkowski, K. Ferguson, J. Cardin, G. Wolf, and S. Krishnaswamy. Modeling Dynamics with Deep Transition-Learning Networks, In Joint ICML and IJCAI 2018 Workshop on Computational Biology (WCB 2018), Stockholm, Sweden, 2018.
  27. O. Lindenbaum, J.S. Stanley III, G. Wolf, and S. Krishnaswamy. Geometry based datageneration. In Joint ICML and IJCAI 2018 Workshop on Computational Biology(WCB2018), Stockholm, Sweden, 2018.
  28. M. Amodio, K. Srinivasan, D. van Dijk, H. Mohsen, K. Yim, R. Muhle, K.R. Moon, R.R.Montgomery, J. Noonan, G. Wolf, S. Krishnaswamy. SAUCIE: Sparse autoencoderfor unsupervised clustering, imputation, and embedding. In Proceedings of the American Association for Cancer Research Annual Meeting 2018, Chicago, IL; Cancer Research, 78(13 Supplement):5306, 2018.
  29. H. Mohsen, K. Srinivasan, K.R. Moon, G. Wolf, D. van Dijk, S. Krishnaswamy, Deep Neural Networks for Imputation, Clustering, and Embedding of Single-Cell Data. In ISMB 2017: 25th conference on Intelligent Systems for Molecular Biology, Prague, Czech Republic, 2017.
  30. K.R. Moon, D. van Dijk, Z. Wang, T. Welp, G. Wolf, R.R. Coifman, N. Ivanova, S. Krishnaswamy, PHATE: Potential Heat-diffusion Affinity-based Trajectory Embedding for Visualization of Progression Structure. In 11th Annual Machine Learning Symposium, New York, NY, USA, 2017.
  31. T. Welp, G. Wolf, M. Hirn, S. Krishnaswamy. A Diffusion-based Condensation Process for Multiscale Analysis of Single Cell Data. In ICML 2016 Workshop on Computational Biology (WCB), New York, NY, USA, 2016.

Book Chapters:

  1. G. Wolf, A. Averbuch, and P. Neittaanmäki. Parameter Rating by Diffusion Gradient. In W. Fitzgibbon, Y.A. Kuznetsov, P. Neittaanmäki, O. Pironneau, editors, Modeling, Simulation and Optimization for Science and Technology, volume 34 of Computational Methods in Applied Sciences, pages 225-248. Springer Netherlands, 2014.
  2. G. Wolf, Y. Shmuelli, S. Harussi, and A. Averbuch. Polar classification of nominal data. In S. Repin, T. Tiihonen, and T. Tuovinen, editors, Numerical methods for differential equations, optimization, and technological problems, volume 27 of Computational Methods in Applied Sciences, pages 253-271, Springer Netherlands, 2013.

Reviews:

  1. K.R. Moon, J.S. Stanley III, D. Burkhardt, D. van Dijk, G. Wolf, and S. Krishnaswamy. Manifold learning-based methods for analyzing single-cell RNA-sequencing data. Current Opinion in Systems Biology, 7:36-46, 2018.

Invited Papers:

  1. F. Gao and M. Hirn and M. Perlmutter and G. Wolf. Geometric wavelet scattering on graphs and manifolds. In SPIE Optical Engineering + Applications, San Diego, CA; Wavelets and Sparsity XVIII, 11138:228-235, 2019.

Office address:
Pavillon André-Aisenstadt (AA-6165)
2920 chemin de la Tour
Montréal (Québec) H3T 1J4
Canada