Banner Banner

Probabilistic Modeling and Inference

Icon

Lead
Dr. Shinichi Nakajima

Icon

Technische Universität Berlin
Marchstraße 23, 10587 Berlin

Multimodal data modeling, Efficient inference methods, Deep uncertainty estimation

Dr. Shinichi Nakajima leads the Independent Research Group Probabilistic Modeling and Inference. His aim is to develop novel probabilistic models and inference methods for multimodal, heterogeneous, and complex structured data analysis. In particular he wants to provide machine learning tools that can incorporate multiple aspects of data samples observed under different circumstances, in efficient and theoretically grounded ways. This includes:

  • developing novel probabilistic models with efficient inference methods
  • exploring novel applications of probabilistic models, and
  • establishing uncertainty estimation methods for deep probabilistic models.

Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Gregoire Montavon

Higher-Order Explanations of Graph Neural Networks via Relevant Walks

November 01 , 2022
https://ieeexplore.ieee.org/abstract/document/9547794

Lorenz Vaitl, Kim Andrea Nicoli, Shinichi Nakajima, Pan Kessel

Path-Gradient Estimators for Continuous Normalizing Flows

June 17 , 2022
https://arxiv.org/abs/2206.09016

Kirill Bykov, Anna Hedström, Shinichi Nakajima, Marina M.-C. Höhne

NoiseGrad: enhancing explanations by introducing stochasticity to model weights

May 30 , 2022
https://doi.org/10.48550/arXiv.2106.10185

Ping Xiong, Thomas Schnake, Gregoire Montavon, Klaus-Robert Müller, Shinichi Nakajima

Efficient Computation of Higher-Order Subgraph Attribution via Message Passing

January 01 , 2022
https://proceedings.mlr.press/v162/xiong22a.html

Dr. Shinichi Nakajima

Research Group Lead

Marco Morik Bifold Researcher

Marco Morik

Doctoral Researcher