Grégoire Montavon

Grégoire Montavon is a Research Associate in the Machine Learning Group at the Technische Universität Berlin, and Junior Research Group Lead in the Berlin Institute for the Foundations of Learning and Data (BIFOLD). He received a Masters degree in Communication Systems from École Polytechnique Fédérale de Lausanne in 2009, and a Ph.D. degree in Machine Learning from the Technische Universität Berlin in 2013. His research interests include explainable AI, deep neural networks, and unsupervised learning.

Grégoire Montavon's current research is on advancing the foundations and algorithms of explainable AI (XAI) in the context of deep neural networks. One particular focus is on closing the gap between existing XAI methods and practical desiderata. Examples include using XAI to build more trustworthy and autonomous machine learning models and using XAI to model the behavior of complex real-world systems so that the latter become meaningfully actionable.

See also: https://bifold.berlin/research/#dnn

• The Layer-Wise Relevance Propagation (LRP) [3] method. LRP robustly and efficiently explains deep neural network predictions in terms of input features.
• The Deep Taylor Decomposition [4] framework, which connects mathematically the LRP procedure to Taylor expansions and leads to a systematic way of designing LRP propagation rules.
• The "Neuralization-Propagation" framework for explaining non-neural network models, which consists of rewriting non neural network models (e.g. one-class SVMs [5], K-means [6]) as strictly equivalent neural networks, and using the neural network representation and LRP to produce explanations.
• Higher-order extensions of LRP (BiLRP [7] and GNN-LRP [8]). They enable to identify joint feature contributions in models such as graph neural networks or deep similarity models.
• Method to systematically verify that trained neural networks predict as expected and are not subject to a Clever Hans [9] effect.

These contributions are described in more details in our recent review paper on Explainable AI [10].

See also: www.heatmapping.org [11]

Winter semester 2021/2022:

• Machine Learning 1 [12]

Summer semester 2022:

• Machine Learning 2 [13]

Preprints

• J Kauffmann, M Esders, G Montavon, W Samek, KR Müller
  From Clustering to Cluster Explanations via Neural Networks [14]
  CoRR abs/1906.07633, v2 (2021)
• L Andéol, Y Kawakami, Y Wada, T Kanamori, KR Müller, G Montavon
  Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization [15]
  CoRR abs/2106.04923, v1 (2021)
• J Kauffmann, L Ruff, G Montavon, KR Müller
  The Clever Hans Effect in Anomaly Detection [16]
  CoRR abs/2006.10609, v1 (2020)

 Edited books

• W Samek, G Montavon, A Vedaldi, LK Hansen, KR Müller (Eds.)
  Explainable AI: Interpreting, Explaining and Visualizing Deep Learning [17]
  Springer LNCS 11700 (2019)
• G Montavon, G Orr, KR Müller (Eds.)
  Neural Networks: Tricks of the Trade, 2nd Edn [18]
  Springer LNCS 7700 (2012)

 Book chapters

• G Montavon, J Kauffmann, W Samek, KR Müller
  Explaining the Predictions of Unsupervised Learning Models [19]
  in xxAI - Beyond Explainable Artificial Intelligence, Springer LNAI 13200 (2022)
• W Samek, L Arras, A Osman, G Montavon, KR Müller
  Explaining the Decisions of Convolutional and Recurrent Neural Networks [20]
  in: Mathematical Aspects of Deep Learning (2022), to appear
• G Montavon
  Introduction to Neural Networks [21]
  in Machine Learning Meets Quantum Physics, 37-62 (2020)
• G Montavon, A Binder, S Lapuschkin, W Samek, KR Müller
  Layer-Wise Relevance Propagation: An Overview [22]
  in Explainable AI, Springer LNCS 11700 (2019)
• L Arras, J Arjona, M Widrich, G Montavon, M Gillhofer, KR Müller, S Hochreiter, W Samek
  Explaining and Interpreting LSTMs [23]
  in Explainable AI, Springer LNCS 11700 (2019)
• G Montavon
  Gradient-Based Vs. Propagation-Based Explanations: An Axiomatic Comparison [24]
  in Explainable AI, Springer LNCS 11700 (2019)
• C Anders, G Montavon, W Samek, KR Müller
  Understanding Patch-Based Learning of Video Data by Explaining Predictions [25]
  in Explainable AI, Springer LNCS 11700 (2019)
• L Rieger, P Chormai, G Montavon, LK Hansen, KR Müller
  Structuring Neural Networks for More Explainable Predictions [26]
  in Explainable and Interpretable Models in Computer Vision and Machine Learning, pp 115-131, Springer SSCML (2018)
• G Montavon, KR Müller
  Deep Boltzmann Machines and the Centering Trick [27]
  in Neural Networks: Tricks of the Trade, 2nd Edn, pp 621-637, Springer LNCS, vol. 7700 (2012)

Journal publications

• H El-Hajj, M Zamani, J Büttner, J Martinetz, O Eberle, N Shlomi, A Siebold, G Montavon, KR Müller, H Kantz, M Valleriani
  An Ever-Expanding Humanities Knowledge Graph: The Sphaera Corpus at the Intersection of Humanities, Data Management, and Machine Learning [28]
  Datenbank-Spektrum (2022)
• S Letzgus, P Wagner, J Lederer, W Samek, KR Müller, G Montavon
  Toward Explainable AI for Regression Models [29]
  Signal Processing Magazine, accepted (2022)
• O Eberle, J Büttner, F Kräutli, KR Müller, M Valleriani, G Montavon
  Building and Interpreting Deep Similarity Models [30]
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(3):1149-1161 (2022)
• T Schnake, O Eberle, J Lederer, S Nakajima, K T. Schütt, KR Müller, G Montavon
  Higher-Order Explanations of Graph Neural Networks via Relevant Walks [31]
  IEEE Transactions on Pattern Analysis and Machine Intelligence, early access (2021)
• S Agarwal, N Tosi, P Kessel, D Breuer, G Montavon
  Deep learning for surrogate modeling of two-dimensional mantle convection [32]
  Physical Review Fluids 6 (11), 113801 (2021)
• S Agarwal, N Tosi, P Kessel, S Padovan, D Breuer, G Montavon
  Toward constraining Mars' thermal evolution using machine learning [33]
  Earth and Space Science 8 (4), e2020EA001484 (2021)
• W Samek, G Montavon, S Lapuschkin, C Anders, KR Müller
  Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications [34]
  Proceedings of the IEEE 109(3):247-278 (2021)
• L Ruff, J Kauffmann, R Vandermeulen, G Montavon, W Samek, M Kloft, T Dietterich, KR Müller
  A Unifying Review of Deep and Shallow Anomaly Detection [35]
  Proceedings of the IEEE 109(5):756-795 (2021)
• K Melnyk, S Klus, G Montavon, T Conrad
  GraphKKE: Graph Kernel Koopman Embedding for Human Microbiome Analysis [36]
  Applied Network Science 5(1):96 (2020)
• S Agarwal, N Tosi, D Breuer, S Padovan, P Kessel, G Montavon
  A machine-learning-based surrogate model of Mars’ thermal evolution [37]
  Geophysical Journal International, ggaa234 (2020)
• P Baumeister, S Padovan, N Tosi, G Montavon, N Nettelmann, J MacKenzie, M Godolt
  Machine learning inference of the interior structure of low-mass exoplanets [38]
  The Astrophysical Journal, 118(1):42 (2020)
• J Kauffmann, KR Müller, G Montavon
  Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models [39]
  Pattern Recognition, 107198 (2020)
• P Jurmeister, M Bockmayr, P Seegerer, T Bockmayr,D Treue, G Montavon, C Vollbrecht, A Arnold, D Teichmann, K Bressem, U Schüller, Mv Laffert, KR Müller, D Capper, F Klauschen
  Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases [40]
  Science Translational Medicine 11(509):eaaw8513 (2019)
• S Lapuschkin, S Wäldchen, A Binder, G Montavon, W Samek, KR Müller
  Unmasking Clever Hans Predictors and Assessing What Machines Really Learn [41]
  Nature Communications 10:1096 (2019)
• D Heim, G Montavon, P Hufnagl, KR Müller, F Klauschen
  Computational analysis reveals histotype-dependent molecular profile and actionable mutation effects across cancers [42]
  Genome Medicine, 10:83 (2018)
• G Montavon, W Samek, KR Müller
  Methods for Interpreting and Understanding Deep Neural Networks [43]
  Digital Signal Processing, 73:1-15 (2018)
• L Arras, F Horn, G Montavon, KR Müller, W Samek
  "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach [44]
  PLOS ONE, 12(8):e0181142 (2017)
• G Montavon, S Lapuschkin, A Binder, W Samek, KR Müller
  Explaining NonLinear Classification Decisions with Deep Taylor Decomposition [45]
  Pattern Recognition, 65:211–222 (2017)
• W Samek, A Binder, G Montavon, S Lapuschkin, KR Müller
  Evaluating the Visualization of What a Deep Neural Network has Learned [46]
  IEEE Transactions on Neural Networks and Learning Systems, 28(11):2660-2673 (2016)
• S Bach, A Binder, G Montavon, F Klauschen, KR Müller, W Samek
  On Pixel-wise Explanations for Non-Linear Classifier Decisions by Layer-wise Relevance Propagation [47]
  PLOS ONE, 10(7):e0130140 (2015)
• G Montavon, M Rupp, V Gobre, A Vazquez-Mayagoitia, K Hansen, A Tkatchenko, KR Müller, OAv Lilienfeld
  Machine Learning of Molecular Electronic Properties in Chemical Compound Space [48]
  New Journal of Physics, 15 095003 (2013)
• K Hansen, G Montavon, F Biegler, S Fazli, M Rupp, M Scheffler, OAv Lilienfeld, A Tkatchenko, KR Müller
  Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies [49]
  Journal of Chemical Theory and Computation, 9(8):3404-3419 (2013)
• G Montavon, M Braun, T Krueger, KR Müller
  Analyzing Local Structure in Kernel-based Learning: Explanation, Complexity and Reliability Assessment [50]
  IEEE Signal Processing Magazine, 30(4):62-74 (2013)
• G Montavon, M Braun, KR Müller
  Kernel Analysis of Deep Networks [51]
  Journal of Machine Learning Research, 12:2563-2581 (2011)

Conference Publications

• P Xiong, T Schnake, G Montavon, KR Müller, S Nakaijma
  Efficient Computation of Higher-Order Subgraph Attribution via Message Passing
  ICML 2022, accepted
• A Ali, T Schnake, O Eberle, G Montavon, KR Müller, L Wolf. XAI for Transformers: Better Explanations through Conservative Propagation [52]
  ICML 2022, accepted
  
• G Montavon, KR Müller, M Cuturi
  Wasserstein Training of Restricted Boltzmann Machines [53]
  NIPS 2016
• F Arbabzadah, G Montavon, KR Müller, W Samek
  Identifying Individual Facial Expressions by Deconstructing a Neural Network [54]
  GCPR 2016
• A Binder, G Montavon, S Bach, KR Müller, W Samek
  Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers [55]
  ICANN 2016
• S Lapuschkin, A Binder, G Montavon, KR Müller, W Samek
  Analyzing Classifiers: Fisher Vectors and Deep Neural Networks [56]
  CVPR 2016
• A Binder, S Bach, G Montavon, KR Müller, W Samek
  Layer-wise Relevance Propagation for Deep Neural Network Architectures [57]
  ICISA 2016
• G Montavon, K Hansen, S Fazli, M Rupp, F Biegler, A Ziehe, A Tkatchenko, OAv Lilienfeld, KR Müller
  Learning Invariant Representations of Molecules for Atomization Energy Prediction [58]
  NIPS 2012
• G Montavon, M Braun, KR Müller
  Deep Boltzmann Machines as Feed-Forward Hierarchies [59]
  AISTATS 2012
• G Montavon, M Braun, KR Müller
  Layer-Wise Analysis of Deep Networks with Gaussian Kernels [60]
  NIPS 2010

Software Publications

• M Alber, S Lapuschkin, P Seegerer, M Hägele, KT Schütt, G Montavon, W Samek, KR Müller, S Dähne, PJ Kindermans
  iNNvestigate neural networks! [61]
  Journal of Machine Learning Research, Software Track (2019)
• S Lapuschkin, A Binder, G Montavon, KR Müller, W Samek
  The Layer-wise Relevance Propagation Toolbox for Artificial Neural Networks [62]
  Journal of Machine Learning Research, Software Track (2016)

Workshop Publications

• L Arras, G Montavon, KR Müller, W Samek
  Explaining Recurrent Neural Network Predictions in Sentiment Analysis [63]
  EMNLP Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (2017)
• W Samek, G Montavon, A Binder, S Lapuschkin, KR Müller
  Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation [64]
  NIPS Workshop on Interpretable ML for Complex Systems (2016)
• L Arras, F Horn, G Montavon, KR Müller, W Samek
  Explaining Predictions of Non-Linear Classifiers in NLP [65]
  ACL Workshop on Representation Learning for NLP (2016)
• G Montavon, S Bach, A Binder, W Samek, KR Müller
  Deep Taylor Decomposition of Neural Networks [66]
  ICML Workshop on Visualization for Deep Learning (2016)
• A Binder, W Samek, G Montavon, S Bach, KR Müller
  Analyzing and Validating Neural Networks Predictions [67]
  ICML Workshop on Visualization for Deep Learning (2016)
• G Montavon, KR Müller
  Neural Networks for Computational Chemistry: Pitfalls and Recommendations [68]
  MRS Online Proceedings Library (2013)
• G Montavon
  Deep Learning for Spoken Language Identification [69]
  NIPS Workshop on Deep Learning for Speech Recognition and Related Applications (2009)

Theses

• G Montavon
  On Layer-Wise Representations in Deep Neural Networks [70]
  PhD Thesis, Technische Universität Berlin, Germany (2013)
• G Montavon
  A Machine Learning Approach to Classification of Low Resolution Histological Samples [71]
  Master Thesis, École Polytechnique Fédérale de Lausanne, Switzerland (2009)

Unpublished

• J Kauffmann, G Montavon, LA Lima, S Nakajima, KR Müller, N Görnitz
  Unsupervised Detection and Explanation of Latent-class Contextual Anomalies [72] (2018)
• F Horn, L Arras, G Montavon, KR Müller, W Samek
  Exploring text datasets by visualizing relevant words [73] (2017)