Home | Research | Groups | Vincent Fortuin

Research Group Vincent Fortuin

Link to Vincent Fortuin

Vincent Fortuin

Dr.

Associate

Bayesian Deep Learning

Vincent Fortuin

is a tenure-track research group leader at Helmholtz AI in Munich, leading the group for Efficient Learning and Probabilistic Inference for Science (ELPIS), and a faculty member at TU Munich.

His research focuses on reliable and data-efficient AI approaches leveraging Bayesian deep learning, deep generative modeling, meta-learning, and PAC-Bayesian theory.

Publications @MCML

2024


[6]
R. Dhahri, A. Immer, B. Charpentier, S. Günnemann and V. Fortuin.
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood.
NeurIPS 2024 - 38th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. To be published. Preprint available. arXiv
Abstract

Neural network sparsification is a promising avenue to save computational time and memory costs, especially in an age where many successful AI models are becoming too large to naïvely deploy on consumer hardware. While much work has focused on different weight pruning criteria, the overall sparsifiability of the network, i.e., its capacity to be pruned without quality loss, has often been overlooked. We present Sparsifiability via the Marginal likelihood (SpaM), a pruning framework that highlights the effectiveness of using the Bayesian marginal likelihood in conjunction with sparsity-inducing priors for making neural networks more sparsifiable. Our approach implements an automatic Occam’s razor that selects the most sparsifiable model that still explains the data well, both for structured and unstructured sparsification. In addition, we demonstrate that the pre-computed posterior Hessian approximation used in the Laplace approximation can be re-used to define a cheap pruning criterion, which outperforms many existing (more expensive) approaches. We demonstrate the effectiveness of our framework, especially at high sparsity levels, across a range of different neural network architectures and datasets.

MCML Authors
Link to Stephan Günnemann

Stephan Günnemann

Prof. Dr.

Data Analytics & Machine Learning

Link to Vincent Fortuin

Vincent Fortuin

Dr.

Bayesian Deep Learning


[5]
K. Flöge, M. A. Moeed and V. Fortuin.
Stein Variational Newton Neural Network Ensembles.
Preprint (Nov. 2024). arXiv
Abstract

Deep neural network ensembles are powerful tools for uncertainty quantification, which have recently been re-interpreted from a Bayesian perspective. However, current methods inadequately leverage second-order information of the loss landscape, despite the recent availability of efficient Hessian approximations. We propose a novel approximate Bayesian inference method that modifies deep ensembles to incorporate Stein Variational Newton updates. Our approach uniquely integrates scalable modern Hessian approximations, achieving faster convergence and more accurate posterior distribution approximations. We validate the effectiveness of our method on diverse regression and classification tasks, demonstrating superior performance with a significantly reduced number of training epochs compared to existing ensemble-based methods, while enhancing uncertainty quantification and robustness against overfitting.

MCML Authors
Link to Vincent Fortuin

Vincent Fortuin

Dr.

Bayesian Deep Learning


[4]
K. Flöge, S. Udayakumar, J. Sommer, M. Piraud, S. Kesselheim, V. Fortuin, S. Günneman, K. J. van der Weg, H. Gohlke, A. Bazarova and E. Merdivan.
OneProt: Towards Multi-Modal Protein Foundation Models.
Preprint (Nov. 2024). arXiv
Abstract

Recent AI advances have enabled multi-modal systems to model and translate diverse information spaces. Extending beyond text and vision, we introduce OneProt, a multi-modal AI for proteins that integrates structural, sequence, alignment, and binding site data. Using the ImageBind framework, OneProt aligns the latent spaces of modality encoders along protein sequences. It demonstrates strong performance in retrieval tasks and surpasses state-of-the-art methods in various downstream tasks, including metal ion binding classification, gene-ontology annotation, and enzyme function prediction. This work expands multi-modal capabilities in protein models, paving the way for applications in drug discovery, biocatalytic reaction planning, and protein engineering.

MCML Authors
Link to Vincent Fortuin

Vincent Fortuin

Dr.

Bayesian Deep Learning


[3]
K. Bouchiat, A. Immer, H. Yèche, G. Ratsch and V. Fortuin.
Improving Neural Additive Models with Bayesian Principles.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Abstract

Neural additive models (NAMs) enhance the transparency of deep neural networks by handling input features in separate additive sub-networks. However, they lack inherent mechanisms that provide calibrated uncertainties and enable selection of relevant features and interactions. Approaching NAMs from a Bayesian perspective, we augment them in three primary ways, namely by a) providing credible intervals for the individual additive sub-networks; b) estimating the marginal likelihood to perform an implicit selection of features via an empirical Bayes procedure; and c) facilitating the ranking of feature pairs as candidates for second-order interaction in fine-tuned models. In particular, we develop Laplace-approximated NAMs (LA-NAMs), which show improved empirical performance on tabular datasets and challenging real-world medical tasks.

MCML Authors
Link to Vincent Fortuin

Vincent Fortuin

Dr.

Bayesian Deep Learning


[2]
T. Papamarkou, M. Skoularidou, K. Palla, L. Aitchison, J. Arbel, D. Dunson, M. Filippone, V. Fortuin, P. Hennig, J. M. Hernández-Lobato, A. Hubin, A. Immer, T. Karaletsos, M. E. Khan, A. Kristiadi, Y. Li, S. Mandt, C. Nemeth, M. A. Osborne, T. G. J. Rudner, D. Rügamer, Y. W. Teh, M. Welling, A. G. Wilson and R. Zhang.
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Abstract

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

MCML Authors
Link to Vincent Fortuin

Vincent Fortuin

Dr.

Bayesian Deep Learning

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group


[1]
F. Sergeev, P. Malsot, G. Rätsch and V. Fortuin.
Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information.
Preprint (Jul. 2024). arXiv
Abstract

Knowing which features of a multivariate time series to measure and when is a key task in medicine, wearables, and robotics. Better acquisition policies can reduce costs while maintaining or even improving the performance of downstream predictors. Inspired by the maximization of conditional mutual information, we propose an approach to train acquirers end-to-end using only the downstream loss. We show that our method outperforms random acquisition policy, matches a model with an unrestrained budget, but does not yet overtake a static acquisition strategy. We highlight the assumptions and outline avenues for future work.

MCML Authors
Link to Vincent Fortuin

Vincent Fortuin

Dr.

Bayesian Deep Learning