Home

Publication

Seminars

Group

Service

Teaching

Honor

Funding

Yu Guang Wang
Associate Professor Institute of Natural Sciences School of Mathematical Sciences Shanghai Jiao Tong University Adjunct Associate Professor Shanghai AI Lab Adjunct Associate Professor UNSW Sydney	Email: Mail:	yuguang.wang@sjtu.edu.cn Institute of Natural Sciences Shanghai Jiao Tong University 361, Build. No.6, Science Buildings No. 800 Dongchuan Road, Minhang District Shanghai 200240, China

Introduction

I am an Associate Professor in Institute of Natural Sciences, School of Mathematical Sciences, Department of Computer Science and Engineering, and Key Lab of Scientific and Engineering Computing of Minister of Education (MOE-LSC), at Shanghai Jiao Tong University. I am Adjunct Associate Professor at Shanghai AI Laboratory and UNSW Sydney.

My research interests lie in artificial intelligence, computational mathematics, statistics and data science. In particular, I am working on geometric deep learning, graph neural networks, applied harmonic analysis, Bayesian inference, information geometry, numerical analysis, and applications to biomedicine and protein design.

Previously, I was a research scientist at Max Planck Institute for Mathematics in Sciences, in Prof Guido Montufar's Deep Learning Theory Group. I obtained my PhD in applied mathematics from University of New South Wales under supervision of Prof Ian Sloan and Rob Womersley. I am a recipient of ICERM Semester Postdoctoral Fellowship of Brown University (2018), a long-term IPAM visitor of UCLA (2019), and long-term visitor of AI Group of Prof Pietro Lio at Univeristy of Cambridge (2022).

News

[Paper] "Harnessing TME depicted by histological images to improve the cancer prognosis through a deep learning system" is accepted by Cell Reports Medicine. Congrats, Ruitian!

[Benchmark] ProteinLMBench is released in 8 April 2024. The first evaluation system for LLM for Protein Engineering in the world!

[Platform] TourSynbio Protein LLM is released in 8 April 2024. The first ChatGPT for Protein Design in China!

[Paper] GraDe-IF paper joint with Kai, Zhou, Shen and Lio has been accepted in NeurIPS 2023. It provides a GNN-based diffusion model for inverse protein folding. Congrats!

[Paper] ACMP paper joint with Yuelin, Kai, Xinliang and Shi has been accepted in ICLR 2023 as a Spotlight Paper. Also Oral Presentation in NeurIPS 2022 Workshop on New Frontiers in Graph Learning. Congrats!

[Member] Jialin has been awarded Outstanding Graduate of Shanghai! She is going to pursue PhD in CS in Yale Univeristy in her next career stage. Big Congrats!

[Member] Xuebin's PhD thesis on graph neural networks with wavelet analysis has been approved by the University of Sydney! Congrats, Dr Zheng!

Current Research Interests

Artificial Intelligence: Graph Neural Networks, Geometric Deep Learning, Large Language Model, Information Geometry, Optimization Algorithms, Distributed Learning, Generative Models, Topological Data Analysis, Expressivity and Generalization of Deep Neural Networks, Kernel Methods, Reinforcement Learning Applied Math and Statistics: Applied Harmonic Analysis, Signal Processing, Bayesian Statistics, Computational Geometry, SDEs Interdisciplinary: AI for Sciences, AI for Mathematics, AI for Health/Medicine, AI for Synbio and Protein Design, Cosmic Microwave Background (CMB)

Publications

		List of publications can be found at my Google Scholar.

Book Chapter

1. Analysis of Framelet Transforms on Simplex.
   Y. G. Wang, H. Zhu.
   Contemporary Computational Mathematics: a Celebration for the 80th Birthday of Ian Sloan. Editors: Josef Dick, Frances Y. Kuo, Henryk Wozniakowski, Publisher: Springer, 2018.

Technical Report

1. White Paper: Geometry and Learning from Data in 3D and Beyond.
   P. Kr. Banerjee, Y. G. Wang et al.
   Technical Report, UCLA IPAM Long Program, Spring 2019.

Selected Papers

1. Harnessing TME depicted by histological images to improve cancer prognosis through a deep learning system.
   R. Gao, X. Yuan, Y. Ma, T. Wei, L. Johnston, Y. Shao, W. Lv, T. Zhu, Y. Zhang, J. Zheng, G. Chen, J. Sun, Y. G. Wang, Z. Yu. Cell Reports Medicine 2024.


2. Graph Denoising Diffusion for Inverse Protein Folding.
   Y. Kai, B. Zhou, Y. Shen, P. Lio, Y. G. Wang. NeurIPS 2023.


3. EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning.
   C. Xu, R. T. Tan, Y. Tan, S. Chen, Y. G. Wang, X. Wang, Y. Wang. CVPR 2023.


4. How powerful are shallow neural networks with bandlimited random weights?
   M. Li, S. Sho, F. Cao, Y. G. Wang, J. Liang. ICML 2023.


5. Robust Graph Representation Learning for Local Corruption Recovery.
   B. Zhou, Y. Jiang, Y. G. Wang, J. Liang, J. Gao, S. Pan, X. Zhang.
   WWW 2023 (Also in ICML 2022 Workshop on Topology, Algebra, and Geometry in Machine Learning).


6. ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks.
   Y. Wang, K. Yi, X. Liu, Y. G. Wang, S. Jin.
   ICLR 2023 (Spotlight) (Also in NeurIPS 2022 Workshop on New Frontiers in Graph Learning)


7. Lightweight Equivariant Graph Representation Learning for Protein Engineering.
   B. Zhou, O. Lv, K. Yi, X. Xiong, L. Hong, Y. G. Wang.
   NeurIPS 2022 Workshop on Machine Learning in Structral Biology


8. Cell Graph Neural Networks Enable Digital Staging of Tumour Microenvironment and Precisely Predict Patient Survival in Gastric Cancer.
   Y. Wang, Y. G. Wang, C. Hu, M. Li, Y. Fan, N. Otter, I. Sam, H. Gou, Y. Hu, T. Kwok, J. Zalcberg, A. Boussioutas, R. J. Daly, G. Montufar, P. Lio, D. Xu, G. I. Webb, J. Song.
   npj Precision Oncology 2022.


9. Weisfeiler and Lehman Go Cellular: CW Networks.
   C. Bodnar, F. Frasca, N. Otter, Y. G. Wang, P. Lio, G. Montufar, M. Bronstein.
   NeurIPS 2021.


10. Distributed Learning via Filtered Hyperinterpolation on Manifolds.
    G. Montufar, Y. G. Wang.
    Foundations of Computational Mathematics 2021.


11. How Framelets Enhance Graph Neural Networks.
    X. Zheng, B. Zhou, J. Gao, Y. G. Wang, P. Lio, M. Li, G. Montufar.
    ICML 2021 (Spotlight). Code


12. Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks.
    C. Bodnar, F. Frasca, Y. G. Wang, N. Otter, G. Montufar, P. Lio, M. Bronstein.
    ICML 2021 (Spotlight).
    (Also as a Spotlight in ICLR 2021 Workshop on GTRL).


13. Decimated Framelet System on Graphs and Fast G-Framelet Transforms.
    X. Zheng, B. Zhou, Y. G. Wang, X. Zhuang.
    Journal of Machine Learning Research 2022. Code


14. Algorithm 1018: FaVeST-Fast Vector Spherical Harmonic Transforms.
    M. Li, Q. T. Le Gia, Y. G. Wang.
    ACM Transactions on Mathematical Software 2021. Code also in CALGO (see file 1018.gz)
    


15. Improve Concentration of Frequency and Time by Novel Complex Spherical Designs.
    M. Sourisseau, Y. G. Wang, R. S. Womersley, H.-T. Wu, W.-H. Yu.
    Applied and Computational Harmonic Analysis 2021. Code


16. Distributed Filtered Hyperinterpolation For Noisy Data on the Sphere.
    S.-B. Lin, Y. G. Wang, D.-X. Zhou.
    SIAM Journal on Numerical Analysis 2021.


17. Path Integral Based Convolution and Pooling for Graph Neural Networks.
    Z. Ma, J. Xuan, Y. G. Wang, M. Li, P. Lio.
    NeurIPS 2020. Code


18. Haar Graph Pooling.
    Y. G. Wang, M. Li, Z. Ma, G. Montufar, X. Zhuang, Y. Fan.
    ICML 2020. Code


19. Tight Framelets and Fast Framelet Filter Bank Transforms on Manifolds.
    Y. G. Wang, X. Zhuang.
    Applied and Computational Harmonic Analysis, 48(1): 64–95, 2020.


20. Isotropic Sparse Regularization for Spherical Harmonic Representations of Random Fields on the Sphere.
    Q. T. Le Gia, I. H. Sloan, R. S. Womersley, Y. G. Wang.
    Applied and Computational Harmonic Analysis, 49(1): 257–278, 2020.


21. Fully Discrete Needlet Approximation on the Sphere.
    Y. G. Wang, Quoc T. Le Gia, I. H. Sloan, R. S. Womersley.
    Applied and Computational Harmonic Analysis, 43: 292–316, 2017. Code

Group Members

I am hiring PhD/Masters students in Graph Neural Networks, Geometric Deep Learning, NLP and AI for Science (in particular on AI for Protein Design and AI for Synbio): model, algorithm, theory and applications, from mathematics and computer science. Postgraduate candidates can jointly affiliate with Institute of Natural Sciences (INS) with School of Mathematical Sciences or Department of Computer Science and Engineering, Shanghai Jiao Tong University.

PhD

Hanwen Liu, 2022-, Shanghai Jiao Tong University, INS & Math, research on computational mathematics, deep learning, GNNs 

Hao Chen, 2022-, Shanghai Jiao Tong University, INS & Stats, research on causality, deep learning theory  (joint with Prof Lin Liu)

Chutian Zhang, 2021-, Shanghai Jiao Tong University, INS & Math, research on GNNs, geometric deep learning 

Yahao Ding, 2023-, Shanghai Jiao Tong University, CS, research on LLM, transformer, GNNss 

Yuelin Wang, 2020-, Shanghai Jiao Tong University, research on theory and algorithms for geometric deep learning (joint with Prof Shi Jin)

Kai Yi, 2020-, UNSW Statistics and Data Science, research on deep Bayesian learning, graph neural networks, (joint with A/Prof Yanan Fan, Dr Jan Hamann)

Master

Chutian Zhang, Shanghai Jiao Tong University, INS & Math, research on theory of GNNs, 2021

Alumni

Xinye Xiong  (Master, Shanghai Jiao Tong University) 

Xinliang Liu (Postdoc, now at KAUST) 

Yuehua Liu (Postdoc, now at Philips Research) 

Xuebin Zheng (PhD, University of Sydney, now at EcoPlants) 

Jialin Chen (Honors, Shanghai Jiao Tong University, now at Yale University in CS) 

Yiqing Shen (Honors, Shanghai Jiao Tong University, now at Johns Hopkins University in CS) 

Recent and Upcoming Events

Regular Seminars

	•	AI Group Seminar, University of Cambridge, 2023.
	•	Distinguished Lectures and INS Colloquia, INS, SJTU, Online, 2022.
	•	AI + Math Colloquia, INS, SJTU, Online, 2022.
	•	Deep Learning Theory & Math Machine Learning Seminar, MPI MIS + UCLA, Online, 2022.
	•	Machine Learning + X Seminars, Brown University, Online, 2022.
	•	M2D2: Molecular Modeling And Drug Discovery, Mila & Valence, Online, 2022.

Workshop and Conference

	•	Applied Geometry for Data Sciences, Institute for Mathematical Sciences, National University of Singapore, 30 September - 12 October 2024.
	•	Biomolecular Topology: Modelling and Data Analysis, Institute for Mathematical Sciences, National University of Singapore, 24-28 June 2024.
	•	Artificial Intelligence and Computational Mathematics Conference, Institute of Natural Sciences, Shanghai Jiao Tong University, 16-17 March 2024.
	•	NTU-NUS Joint Workshop on Applied Topology and Geometry for AI, National University of Singapore, 17-18 February 2024.
	•	LoG Shanghai Meetup, Shanghai Jiao Tong University, 29 Nov - 1 Dec 2023.
	•	ICIAM Minisymposium on Mathematics of Geometric Deep Learning, Waseda University, 20-25 August 2023.
	•	Foundations of Computational Mathematics (FoCM), Sorbonne University, 12-21 June 2023.
	•	14th International Conference on Monte Carlo Methods and Applications, Sorbonne University, 26-30 June 2023.
	•	International Conference on Applied Mathematics, City University of Hong Kong, 30 May - 3 June 2023.
	•	Cambridge AI Research Group Talks, University of Cambridge, 22 October 2022.
	•	Machine Learning + X Seminars, Online, Brown University, 7 January 2022.
	•	Workshop on Combinatorics and Information Transfer, Shanghai Jiao Tong University, 27-28 December 2021.
	•	ELLIS Machine Learning for Molecule Discovery Workshop, Online, ELLIS unit Cambridge & ELLIS unit Linz, 13 December 2021.
	•	NeurIPS MeetUp China, Shanghai, 11 December 2021.
	•	NeurIPS, Online, 6-14 December 2021.
	•	Deep learning and partial differential equations, Online, INI, Cambridge, 15-19 November 2021.
	•	Geometry & Learning from Data Workshop, Online, BIRS, 24-29 October 2021.
	•	International Conference on Computational Harmonic Analysis, Online, Cambridge & Online, 13-17 September 2021.
	•	Theory of Deep Learning, Isaac Newton Institute, Cambridge & Online, 9-13 August 2021.
	•	Conference on Mathematics of Machine Learning, Bielefeld University & Online , 4-7 August 2021.
	•	TopoNets 2021 - Networks beyond pairwise interactions, Online , 30 June 2021.
	•	AI Group Seminar, University of Cambridge, Online, 11 May 2021.
	•	ICLR Workshop on Geometric and Topological Representation Learning, Online, 7 May 2021.
	•	ICLR'21, Online, 3-7 May 2021.
	•	AIM: Artificial Intelligence and Mathematics, CNR IAC (National Research Council of Italy), Online, 4 May 2021.
	•	Topological Data Analysis, Online, 26-30 April 2021.
	•	Business Analytics Seminar, University of Sydney, Online, 30 Apr 2021.

Service

Guest Associate Editor for Special Issue Deep Neural Networks for Graphs: Theory, Models, Algorithms and Applications in IEEE Transactions on Neural Networks and Learning Systems (Top AI Journal). Call for Papers!

Review Editor for the journal Frontiers in Applied Mathematics and Statistics.

Reviewer for ICML'20 (Top Reviewer), ICML'20-23, NeurIPS'21-23, NeurIPS'21, ICLR'21-23, IJCAI'21-23.

Organiser for Collaborate@ICERM on Geometry of Data and Networks, 2019 joint with Joan Bruna (NYU), Zheng Ma (Princeton), Guido Montúfar (UCLA), Nina Otter (UCLA).

Organiser for Minisymposium on Harmonic Analysis for Graph Signal Processing and Deep Learning Applications in SIAM Conference on Mathematics of Data Science 2020 (MDS20, postponed to May 2021) joint with Xiaosheng Zhuang (CityU HK).

Teaching

I am lecturing the following courses in 2021-2022.

		2022-2024 Spring, Deep Learning (Applied Statistics Graduate)
		2024 Spring, Cutting-Edge Fields in AI (Senior-Level Undergraduate in Math)
		2023 Fall, Linear Algebra (Undergraduate)
		2021 Fall, Computational Mathematics (Graduate)
		2022-2023 Spring, Optimization (Graduate)

I was a class tutor in UNSW for following courses.

		Semester 3 2019, MATH3101/5305 Computational Mathematics (Numerical Methods for PDEs)
		Semester 2 2018, MATH2089 Numerical Methods and Statistics
		Semester 1 2015, MATH1131 Mathematics 1A
		Semester 2 2014, MATH1231 Mathematics 1B, MATH1241 Higher Mathematics 1B, MATH2019 Engineering Mathematics 2E

Masters

		Yi Guo, 2018-2019, UNSW, thesis title: Cosmo-Encoder: A Bayesian deep learning approach for cosmic microwave background inpainting
		Kai Yi, 2018-2019 UNSW, thesis title: Variational autoencoder for cosmic microwave background image inpainting (Current: PhD in UNSW)

Honors and Awards

		ICML Top Reviewer, 2020
		ICERM Postdoctoral Fellowship, Brown University, 2018
		University International Postgraduate Award, UNSW, 2011-2015

Funding

I am grateful for the financial support of the following institutions:

		Institute of Natural Sciences, Shanghai Jiao Tong University
		Huawei Central Research Institute
		Explore X, Shanghai Jiao Tong University
		Ministry of Education Key Lab in Scientific and Engineering Computing
		Shanghai National Center for Applied Mathematics
		National Natural Science Foundation of China
		European Research Council

Copyright @ 2023 Yu Guang Wang

Top