Me
Maosheng Yang
Ph.D. candidate
Intelligent Systems dept.,
TU Delft
email: m.yang-2@tudelft.nl

About

Hi! I am a Ph.D. student at TU Delft, advised by Prof. Elvin Isufi and Prof. Geert Leus in the Department of Intelligent Systems. I am also affiliated with Aidro Lab (TU Delft AI Lab Programme). My research interests currently include: signal processing and learning on topological domains (graphs, simplicial complexes); discrete differential and spectral geometry; optimal transport; and machine learning for real-world problems.

Prior to my Ph.D., I obtained my master in Electrical Engineering (cum laude) in the group of Signal Processing Systems at TU Delft. I appreciate the Faculty scholarship of Microelectronics department. For my master thesis, I worked on graph signal processing topics with Dr. Mario Couriño, and my PhD advisors. Even before that, I did my bachelor in telecommunication engineering in Beijing Jiaotong University in China.

Outside of work, I love watching movies, bouldering, biking and hiking!

Research Interests

  • Topological Machine Learning
  • Topological Signal Processing
  • Optimal Transport, Schrödinger Bridges
  • Applications involved with data over networks

Education

TU Delft, Sep, 2020 - Aug, 2025
  • Ph.D. student (ongoing)
TU Delft, Sep, 2018 - Aug, 2020
  • M.Sc in Electrical Engineering (cum laude, 9.3/10.0)
Beijing Jiaotong University, Sep, 2014 - Jul, 2018
  • B.Sc in Telecommunication Engineering (93+/100)

News

  • My paper Topological Schrödinger Bridge Matching is accepted to ICLR Spotlight, 2025. [Paper]
  • I gave an invited talk on my PhD work at Applied Math Seminar in Utrecht University. [Slides]
  • I have been awarded a travel fund from G-research to attend the LOGML summer school in July. Appreciate the opportunity very much!
  • I gave an invited talk on my PhD work to Computational neuroEngineering Lab at the University of Florida. [Slides]
  • I gave an oral presentation at the DEEPK workshop in KU Leuven. [Slides]
  • I gave a talk on my work on Simplicial Convolution at AMLab, Amsterdam. [Slides]
  • Our paper on "Hodge-compositional Edge Gaussian Processes" was accepted by AISTATS 2024.
  • I gave a talk about my work on Simplicial Convolution at the Delft AI Energy Lab.
  • I gave a talk about my work on Simplicial Convolution at BNAIC 2023 and logAMS 2023.
  • A preprint Hodge-compositional Edge Gaussian Processes was out, where we, together with Viacheslav Borovitskiy, built principled Gaussian processes on simplicial complexes based on combinatorial Hodge theory, and applied them in Foreign Currency Exchange, Ocean Currents, and Water Supply Networks.

Selected Publications

See a full list on my google scholar.

Machine Learning:
Topological Schrödinger Bridge Matching
Maosheng Yang (single-author)
ICLR Spotlight, 2025
  • We investigate the problem of matching signal distributions over topological domains like graphs and simplicial complexes. This extends the classical Schrödinger bridge (SB) problem, i.e., the dynamical optimal transport.
  • We consider the reference process to be Topological Stochastic Dynamics and focused on the cases of topological heat diffusion mixed with Brownian motion, VE and VP processes. For some of them, we looked for the optimal topological Schrödinger bridge between two Gaussian processes.
  • Inspired by the likelihood SB based generative models, we propose topological SB based models for topological generative modeling and distribution matching. This generalizes other possible generative models for topological signals based on score matching or flow matching.
  • We consider the generative applications in biological data such as brain signals and single-cell data, as well as seismic signals and ocean currents.
    •
    [paper] [code] [slides]
    Hodge-compositional Edge Gaussian Processes
    Maosheng Yang, Viacheslav Borovitskiy, Elvin Isufi
    AISTATS, 2024
  • We built principled Gaussian processes on simplicial complexes based on combinatorial Hodge theory, and applied them in foreign currency exchange, ocean currents and water supply networks.
  • This allows for statistical modeling of edge flows with various properties like being divergence-free or curl-free.
  • Consider checking out the Geometric Kernels library where our work will be integrated soon.
    •
    [paper] [code] [slides]
    Hodge-Aware Learning on Simplicial Complexes
    Maosheng Yang, Elvin Isufi
    arXiv, 2023
  • Proposed a general convolutional learning framework for data in simplicial complexes, including node data, edge flows, triangle data, and more.
  • The framework incorporates theoretical analysis of locality, symmetry, spectral properties based on Hodge decomposition, and stability analysis.
  • Applications include foreign currency exchange, triangle and tetrahedron (higher-order link) predictions, and trajectory prediction for ocean buoys.
  • Consider checking out the open-source module TopoModelX for topological deep learning where our model is implemented.
    •
    [paper] [code]
    Simplicial Convolutional Neural Networks
    Maosheng Yang, Elvin Isufi
    ICASSP, 2022
  • Designed a neural network based on simplicial convolutional filters for learning from data on simplices of one certain order, e.g., edge flows, which returns to graph convolutional neural networks for node data.
  • Implemented the proposed model in the open-source module TopoModelX.
    • [paper] [code]
    Signal Processing:
    Simplicial Convolutional Filters
    Maosheng Yang, Elvin Isufi, Michael T. Schaub, and Geert Leus
    IEEE Transactions on Signal Processing, 2022
  • Proposed spectral methods for signals defined on simplicial complexes, based on discrete calculus.
  • Built the convolutional filters for simplicial complexes based on the Hodge decomposition.
  • Large-scale filter implementation based on Chebyshev polynomials on simplicial complexes.
  • Generalized Graph signal processing framework to simplicial complexes.
    • [paper] [code]

    Talks

    This is a recently updated material on my PhD work Understanding and Learning Simplicial Signals (slides for personal use) that I used for some talks. I appreciate the opportunity to present my work in the other research groups, workshops and conferences.

    Teaching

    Teaching Assistant
    BSc & MSc Project Supervision
    • Three projects involving 15 computer science bachelor students on topics: recommender systems, deep neural networks and graph neural networks Apr - Jul 2022, 2023, 2024
    • Two master projects on topics: topological unrolling networks and building a Python library for topological signal processing Sep 2022 - Apr 2023, Jan - Aug 2024
      •

    Open Source Projects

    • Participation in the Python module TopoModelX for topological deep learning (check the related overview paper 1 and paper 2), where I implemented two models (SCNN, SCCNN) that we proposed for convolutional learning on simplicial complexes.
    • Participation in the Python module GeometricKernels. It implements kernels including the heat and Matérn classes on non-Euclidean spaces such as Riemannian manifolds, graphs and meshes, where I implemented kernels on the edge space of graphs or simplicial complexes.

    Service

    Conference Reviewer: ICASSP, EUSIPCO, ICML, NeurIPS, ICLR
    Journal Reviewer: IEEE TSP, IEEE TSIPN, IEEE SPL, IEEE TNNLS