Shujian Yu (余书剑)
I am an assistant professor in the Department of Artificial Intelligence at the Vrije Universiteit Amsterdam. I also hold a guest position in the Machine Learning Group at the UiT  The Arctic University of Norway.
I graduated from the University of Florida in the Department of Electrical and Computer Engineering, working with Prof. Jose C. Principe, with a Ph.D. minor in theoretical statistics. Previously, I obtained my BEng degree from the School of Electronic Information and Communications at the Huazhong University of Science and Technology. I was a research scientist of machine learning at the NEC Laboratories Europe from 2019 to 2021.
My research interests lie primarily in the intersection of machine learning, information theory, and signal processing, which include topics like informationtheoretic learning and machine learning for signal processing. Particularly, I am interested in informationtheoretic quantities (such as entropy, mutual information, divergence, etc.) estimation, improving the explainability and generalization of deep neural networks by informationtheoretic principles (such as the information bottleneck and the principle of relevant information). I am also interested in brain data analysis (such as EEG and fMRI).
I am the recipient of the 2020 International Neural Networks Society Aharon Katzir Young Investigator Award. I am also selected for the 2023 AAAI New Faculty Highlights.
Email /
Google Scholar /
GitHub


News
 25092024: One paper on backdoor detection is accepted by NeurIPS24, link, code.
 20082024: One paper on Information Bottleneck for interpretable brain disorder diagnosis is accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS), link, code.
 02052024: One paper on neural networkbased Granger causality is accepted by International Conference on Machine Learning (ICML), link, code.
 26042024: One paper on CauchySchwarz divergence for domain adaptation is accepted by International Conference on Uncertainty in Artificial Intelligence (UAI), link, code.
 27032024: One paper on prototype learning for interpretable brain networkbased psychiatric diagnosis and subtyping is accepted by NeuroImage, link, code.
 23012024: One paper on Granger causality for interpretable brain networkbased psychiatric diagnosis is accepted by Neural Networks, link, code.
 16012024: Two papers on “Information Bottleneck”, “CauchySchwarz divergence”, and “generalization error bound” are accepted by International Conference on Learning Representations (ICLR), link1, link2.
 15092023: One paper on “Information Bottleneck meets Invariant Risk Minimization” for finegrained image classification is accepted by Computer Vision and Image Understanding, link.
 15072023: One paper on “minimum error entropy” for transfer learning is accepted by ECAI23, link.
 13062023: The slides of our "Information Theory meets Deep Learning" tutorial in ICASSP23 are available at link.
 17032023: One paper accepted by the IEEE Transactions on Information Theory.
 27012023: One paper accepted by the IEEE Transactions on Knowledge and Data Engineering.
 27122022: One paper accepted by the IEEE Transactions on Signal Processing.
 15122022: We will deliver a tutorial entitled “Information Theory meets Deep Learning” in ICASSP23. See you in Rhodes Island, Greece!
 22112022: I am honored to be selected for the 2023 AAAI New Faculty Highlights.
 19112022: Two papers accepted by AAAI23.

Research


**Matrixbased Entropy Functional**
Multivariate Extension of Matrixbased Renyi's αorder Entropy Functional
Shujian Yu, Luis Gonzalo Sanchez Giraldo, Robert Jenssen, Jose C. Principe
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020  code

Measuring Dependence with Matrixbased Entropy Functional
Shujian Yu, Francesco Alesiani, Xi Yu, Robert Jenssen, Jose C. Principe
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021  code

Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
Shujian Yu, Ammar Shaker, Francesco Alesiani, Jose C. Principe
Proceedings of the International Joint Conferences on Artificial Intelligence (IJCAI), 2020  code

Computationally Efficient Approximations for MatrixBased Rényi's Entropy
Tieliang Gong, Yuxin Dong, Shujian Yu, Bo Dong
IEEE Transactions on Signal Processing, 2022

Robust and Fast Measure of Information via Lowrank Representation
Yuxin Dong, Tieliang Gong, Shujian Yu, Hong Chen, Chen Li
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023  code

**CauchySchwarz Divergence**
The Conditional CauchySchwarz Divergence with Applications to TimeSeries Data and Sequential Decision Making
Shujian Yu, Hongming Li, Sigurd Løkse, Robert Jenssen, Jose C. Principe

CauchySchwarz Divergence Information Bottleneck for Regression
Shujian Yu, Xi Yu, Sigurd Løkse, Robert Jenssen, Jose C. Principe
Proceedings of the International Conference on Learning Representations (ICLR), 2024  code

Domain Adaptation with CauchySchwarz Divergence
Wenzhe Yin,Shujian Yu, Yicong Lin, Jie Liu, JanJakob Sonke, Stratis Gavves
Proceedings of the Uncertainty in Artificial Intelligence (UAI), 2024

**Principle of Relevant Information**
Principle of Relevant Information for Graph Sparsification
Shujian Yu, Francesco Alesiani, Wenzhe Yin, Robert Jenssen, Jose C. Principe
Proceedings of the Uncertainty in Artificial Intelligence (UAI), 2022  code

Multiscale Principle of Relevant Information for Hyperspectral Image Classification
Yantao Wei, Shujian Yu, Luis Gonzalo Sanchez Giraldo, Jose C. Principe
Machine Learning, 2021  code

**Deep Neural Networks Explainability (Opening the BlackBox of Deep Learning)**
Understanding Autoencoders with Information Theoretic Concepts
Shujian Yu, Jose C. Principe
Neural Networks, 2019  code

On Kernel Method–based Connectionist Models and Supervised Deep Learning without Backpropagation
Shiyu Duan, Shujian Yu, Yunmei Chen, Jose C. Principe
MIT Neural Computation, 2020  code

Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
Shujian Yu, Kristoffer Wickstrøm, Robert Jenssen, Jose C. Principe
IEEE Transactions on Neural Networks and Learning Systems, 2020  code1 (MATLAB)  code2 (Python)

**Deep Neural Networks Generalization**
Measuring Dependence with Matrixbased Entropy Functional
Shujian Yu, Francesco Alesiani, Xi Yu, Robert Jenssen, Jose C. Principe
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021  code

Deep Deterministic Information Bottleneck with Matrixbased Entropy Functional
Xi Yu, Shujian Yu, Jose C. Principe
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021  code

**Brain Data Analysis**
Causal Recurrent Variational Autoencoder for Medical Time Series Generation
Hongming Li, Shujian Yu, Jose C. Principe
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023  code

BrainIB: Interpretable Brain Networkbased Psychiatric Diagnosis with Graph Information Bottleneck
Kaizhong Zheng, Shujian Yu, Baojuan Li, Robert Jenssen, Badong Chen

CIGNN: A Granger CausalityInspired Graph Neural Network for Interpretable Brain NetworkBased Psychiatric Diagnosis
Kaizhong Zheng, Shujian Yu, Badong Chen

