Chao Chen   

Assistant Professor
Department of Biomedical Informatics
Also affiliated with Computer Science
and Applied Mathematics & Statistics
Stony Brook University
Stony Brook, NY 11794-8322
Office:     Computer Science Building, 2313C
Tel:         +1-631-632-2593

I have stopped maintaining this website. Please visit my new homepage.

Research Interests

I explore geometric and topological properties of data. These global and robust information can provide insight for modern data analytics. My research draws from the following different domains.

  • Machine learning: robustness of deep neural networks, label noise, graph neural networks.
  • Topological data analysis: persistent homology, computation of topological features.
  • Biomedical image analysis: segmentation, digital pathology.
Past Experience

Service

  • Area Chair, CVPR 2022

  • Area Chair, NeurIPS 2021

  • Area Chair, MICCAI 2021

  • Senior PC, AAAI 2021

  • Area Chair, MICCAI 2020

News

  • New!! One paper accepted by NeurIPS 2021!

    We use the tool of persistent homology to investigate the behavior of neural networks under backdoor attacks.

  • New!! One paper accepted by ICCV 2021!

    We model spatial context for cell detection and classification in histopathology images. We use the k-function in spatial statistics and incorporate into the feature representation on our deep neural network.

  • New!! One paper accepted by ICML 2021!

    We use topological features for link prediction with graph neural networks! Another contribution of the paper is a quadratic algorithm for the computation of extended persistent homology feature with graphs. It can be applied to any graph learning methods.

  • New!! One paper accepted by IPMI 2021!

    We learn topological biomarkers for MRI images of breast cancer patients.

  • New!! Two papers accepted by ICLR 2021 as spotlight presentations!

    We use discrete Morse theory to improve the topology-preserving segmentation problem.

    We also introduce a novel noise model and a theoretically-guaranteed algorithm to train robust model against such noise.

  • New!! One paper accepted by AAAI 2021!

    We use topological information for crowd counting.

  • New!! Two papers accepted by NeurIPS 2020!

    We train robust models by filtering out label noise using topological information. We also proposed a new variational formulation for the instance segmentation task.

Publications

Conferences
  • Songzhu Zheng, Yikai Zhang, Hubert Wagner, Mayank Goswami, Chao Chen: "Topological Detection of Trojaned Neural Networks", in the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021, (acceptance rate 26%)
  • Shahira Abousamra, David Belinsky, John Van Arnam, Felicia Allard, Eric Yee,Rajarsi Gupta, Tahsin Kurc, Dimitris Samaras, Joel Saltz, Chao Chen: "Multi-Class Cell Detection Using Spatial Context Representation", in International Conference on Computer Vision (ICCV), 2021 (Oral, acceptance rate 3%)
  • Jiaqi Yang, Xiaoling Hu, Chao Chen, Chialing Tsai: "A Topological-Attention ConvLSTM Network and Its Application to EM Images", in the 24th International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2021 (acceptance rate 32.7%)
  • Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang and Chao Chen: "Persistence Homology for Link Prediction: An Interactive View", in International Conference on Machine Learning (ICML), 2021 (acceptance rate 21.5%, paper)
  • Fan Wang, Saarthak Kapse, Steven Liu, Prateek Prasanna, and Chao Chen: "TopoTxR: A Topological Biomarker for Predicting Treatment Response in Breast Cancer", in international conference on Information Processing in Medical Imaging (IPMI), 2021
  • Aishik Konwer, Joseph Bae, Gagandeep Singh, Rishabh Gattu, Syed Ali, Jeremy Green, Tej Phatak, Amit Gupta, Chao Chen, Joel Saltz, Prateek Prasanna: "Predicting COVID-19 Lung Infiltrate Progression on Chest Radiographs Using Spatio-temporal LSTM based Encoder-Decoder Network", in Medical Imaging with Deep Learning(MIDL), 2021
  • Xiaoling Hu, Yusu Wang, Li Fuxin, Dimitris Samaras, Chao Chen: "Topology-Aware Segmentation Using Discrete Morse Theory", in the Nineth International Conference on Learning Representations(ICLR), 2021, (Spotlight, acceptance rate for spotlight+oral = 5.6%)
  • Yikai Zhang, Songzhu Zheng, Pengxiang Wu, Mayank Goswami, Chao Chen: "Learning with feature dependent label noise: a progressive approach", in the Nineth International Conference on Learning Representations(ICLR), 2021, (Spotlight, acceptance rate for spotlight+oral = 5.6%)
  • Jiaqi Yang, Xiaoling Hu, Chao Chen , Chia-Ling Tsai: "3D Topology-Preserving Segmentation with Compound Multi-Slice Representation", in IEEE International Symposium on Biomedical Imaging (ISBI), 2021
  • Shahira Abousamra, Minh Hoai Nguyen, Dimitris Samaras, Chao Chen: "Localization in the Crowd with Topological Constraints", in The 35th AAAI Conference in Artificial Intelligence (AAAI), 2021, (acceptance rate 21%)
  • Pengxiang Wu, Songzhu Zheng, Mayank Goswami, Dimitris Metaxas, Chao Chen: "A Topological Filter for Learning with Label Noise", in the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020, (acceptance rate 20.1%)
  • Jialin Yuan, Chao Chen, Li Fuxin: "Deep Variational Instance Segmentation", in the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020, (acceptance rate 20.1%)
  • Cong Chen, Jiaqi Yang, Chao Chen and Changhe Yuan: "Solving Multiple Inference by Minimizing Expected Loss", in the 10th international conference on probabilistic graphical models (pgm), 2020.
  • Cong Chen, Changhe Yuan, Chao Chen: "efficient heuristic search for m-modes inference", in the 10th international conference on probabilistic graphical models (pgm), 2020.
  • Fan Wang, Huidong Liu, Dimitris Samaras, Chao Chen: "TopoGAN: A Topology-Aware Generative Adversarial Network", in European Conference on Computer Vision(ECCV), 2020, (paper, supplemental material, Oral, acceptance rate 2.1%).
  • Hui Qu, Yikai Zhang, Qi Chang, Zhennan Yan, Chao Chen, Dimitris Metaxas: "Learn distributed GAN with Temporary Discriminators", in European Conference on Computer Vision(ECCV), 2020, (acceptance rate 27.1%).
  • Songzhu Zheng, Pengxiang Wu, Aman Goswami, Mayank Goswami, Dimitris Metaxas, Chao Chen: "Error-Bounded Correction of Noisy Labels", in International Conference on Machine Learning (ICML), 2020, (acceptance rate 21.8%).
  • Andrew Aukerman, Mathieu Carrière, Chao Chen, Kevin Gardner, Raúl Rabadán, Rami Vanguri: "Persistent Homology Based Characterization ofthe Breast Cancer Immune Microenvironment: A Feasibility Study", in International Symposium on Computational Geometry (SoCG), 2020.
  • Qi Chang, Hui Qu, Yikai Zhang, Mert Sabuncu, Chao Chen, Tong Zhang, Dimitris Metaxas: "Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Data", in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, (acceptance rate 22.1%).
  • Shahira Abousamra, Danielle Fassler, Le Hou, Yuwei Zhang, Rajarsi Gupta, Tahsin Kurc, Luisa F. Escobar-Hoyos, Dimitris Samaras, Beatrice Knudson, Kenneth Shroyer, Joel Saltz, Chao Chen: "Weakly-Supervised Deep Stain Decomposition for Multiplex IHC Images", in IEEE International Symposium on Biomedical Imaging (ISBI), 2020
  • Qi Zhao, Ze Ye, Yusu Wang, Chao Chen: "Persistence Enhanced Graph Neural Network", in International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
  • Ze Ye, Kin Sum Liu, Tengfei Ma, Jie Gao, Chao Chen: "Curvature Graph Network", in the Eighth International Conference on Learning Representations(ICLR), 2020, (pdf, code, acceptance rate 26.5%).
  • Yikai Zhang, Hui Qu, Dimitris Metaxas, Chao Chen: "Local Regularizer Improves Generalization", in The 34th AAAI Conference in Artificial Intelligence (AAAI), 2020, (acceptance rate 20.6%)
  • Xiaoling Hu, Fuxin Li, Dimitris Samaras, Chao Chen: "Topology-Preserving Deep Image Segmentation", in the Thirty-third Conference on Neural Information Processing Systems (NeurIPS), 2019, (acceptance rate 21.2%)
  • Xiuyan Ni, Yang Yu, Peng Wu, Youlin Li, Shaoliang Nie, Qichao Que, Chao Chen: "Feature Selection for Facebook Feed Ranking System via a Group-Sparsity-Regularized Training Algorithm", in The 28th ACM International Conference on Information and Knowledge Management (CIKM), 2019
  • Ze Ye, Cong Chen, Changhe Yuan, Chao Chen: "Diverse Multiple Prediction on Neural Image Reconstruction", in the 22st International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2019, (Early Acceptance)
  • Yikai Zhang, Hui Qu, Chao Chen, Dimitris Metaxas:"Taming the Noisy Gradient: Train Deep Neural Networks with Small Batch Sizes", in the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019, (acceptance rate 17.9%)
  • Xudong Zhang, Pengxiang Wu, Changhe Yuan, Yusu Wang, Dimitris Metaxas, Chao Chen: "Heuristic Search for Homology Localization Problem and Its Application in Cardiac Trabeculae Reconstruction", in the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019, (acceptance rate 17.9%)
  • Chao Chen, Xiuyan Ni, Qinxun Bai, Yusu Wang: "A Topological Regularizer for Classifiers via Persistent Homology", in International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
  • Pengxiang Wu, Hui Qu, Jingru Yi, Qiaoying Huang, Chao Chen, Dimitris Metaxas: "Deep Attentive Feature Learning for Histopathology Image Classification", in IEEE International Symposium on Biomedical Imaging (ISBI), 2019
  • Pengxiang Wu, Chao Chen, Jingru Yi, Dimitris Metaxas: "Point Cloud Processing via Recurrent Set Encoding", in The 33rd AAAI Conference in Artificial Intelligence (AAAI), 2019, (acceptance rate 16.2%)
  • Cong Chen, Changhe Yuan, Ze Ye, Chao Chen: "Solving M-Modes in Loopy Graphs Using Tree Decompositions", in The 9th International Conference on Probabilistic Graphical Models (PGM), 2018.
  • Xiuyan Ni, Zhennan Yan, Tingting Wu, Jin Fan, Chao Chen: "A Region-of-Interest-Reweight 3D Convolutional Neural Network for the Analytics of Brain Information Processing", in the 21st International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI), 2018, (Oral Presentation, Acceptance Rate 4%).
  • Xiuyan Ni, Novi Quadrianto, Yusu Wang, Chao Chen: "Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data", in the 34rd International Conference on Machine Learning (ICML), 2017, (acceptance rate 25.46%) (pdf)
  • Pengxiang Wu, Chao Chen, Yusu Wang, Shaoting Zhang, Changhe Yuan, Zhen Qian, Dimitris Metaxas, Leon Axel: "Optimal Topological Cycles and Their Application in Cardiac Trabeculae Restoration", in the 25th biennial international conference on Information Processing in Medical Imaging (IPMI), 2017, (Oral presentation, acceptance rate 14.32%, pdf, code)
  • Chao Chen, Dimitris Metaxas, Yusu Wang, Pengxiang Wu: "Cardiac Trabeculae Segmentation, an Application of Computational Topology", in the 33rd International Symposium on Computational Geometry (SoCG): Multimedia Session, 2017, (pdf, video)
  • Chao Chen, Novi Quadrianto: "Clustering High Dimensional Categorical Data via Topographical Features", in the 33rd International Conference on Machine Learning (ICML), 2016, (acceptance rate 24.26%) (pdf)
  • Cong Chen, Changhe Yuan, Chao Chen: "Solving M-Modes Using Heuristic Search", in the 25th International Joint Conference on Artificial Intelligence (IJCAI), 2016 (pdf)
  • Scott Kulp, Chao Chen, Dimitris Metaxas, Leon Axel: "Ventricular blood flow analysis using topological methods", in International Symposium on Biomedical Imaging (ISBI), 2015 (pdf)
  • Chao Chen, Han Liu, Dimitris Metaxas, Tianqi Zhao: "Mode Estimation for High Dimensional Discrete Tree Graphical Models", in Advances in Neural Information Processing Systems (NIPS), 2014 (Spotlight oral, acceptance rate ~5%, pdf, technical report available soon)
  • Mustafa Uzunbas, Chao Chen, Dimitris Metaxas: "Optree: a Learning-Based Adaptive Watershed Algorithm for Neuron Segmentation", in the 17th Annual International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2014. (Early acceptance rate ~10%, pdf)
  • Mingchen Gao, Chao Chen, Shaoting Zhang, Zhen Qian, Mani Vannan, Sarah Rinehart, Dimitris Metaxas, Leon Axel: "Morphological analysis of the papillary muscles and the trabaculae", in International Symposium on Biomedical Imaging (ISBI), 2014 (pdf)
  • Mustafa Uzunbas, Chao Chen, Shaoting Zhang, Kilian Pohl, Kang Li, Dimitris Metaxas: "Collaborative multi organ segmentation by integrating deformable and graphical models", in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2013 (pdf)
  • Mingchen Gao *, Chao Chen *, Shaoting Zhang, Zhen Qian, Dimitris Metaxas, Leon Axel: "Segmenting the papillary muscles and the trabeculae from high resolution cardiac CT through restoration of topological handles", in International Conference on Information Processing in Medical Imaging (IPMI), 2013 (pdf) (* contributed equally)
  • Chao Chen, Vladimir Kolmogorov, Yan Zhu, Dimitris Metaxas, Christoph Lampert: "Computing the M most probable modes of a graphical model", in International Conference on Artificial Intelligence and Statistics (AISTATS), 2013 (Oral presentation, acceptance rate ~11% pdf, supplemental material)
  • Novi Quadrianto, Chao Chen, Christoph Lampert: "The most persistent soft-clique in a set of sampled graphs", in International Conference on Machine Learning (ICML), 2012 (pdf)
  • Oleksiy Busaryev, Sergio Cabello, Chao Chen, Tamal K. Dey, Yusu Wang: "Annotating simplices with a homology basis and its applications", in Scandinavian Symposium and Workshops on Algorithm Theory (SWAT), 2012 (pdf)
  • Chao Chen, Herbert Edelsbrunner: "Diffusion runs low on persistence fast", in IEEE International Conference on Computer Vision (ICCV), 2011 (Acceptance rate 23.7%, pdf, poster, code)
  • Chao Chen, Daniel Freedman, Christoph H. Lampert: "Enforcing topological constraints in random field image segmentation", in IEEE Computer Vision and Pattern Recognition (CVPR), 2011 (pdf, technical report, poster, code)
  • Chao Chen, Michael Kerber: "An output-sensitive algorithm for persistent homology", in Annual Symposium on Computational Geometry (SoCG), 2011 (pdf)
  • Chao Chen, Daniel Freedman: "Hardness results for homology localization", in Proceedings of the Twenty-First Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2010 (pdf)
  • Chao Chen, Daniel Freedman: "Quantifying homology classes", in Annual Symposium on Theoretical Aspects of Computer Science (STACS), 2008 (pdf)
    Note: Proofs of the NP-hardness results in this paper are available in "Quantifying homology classes II: localization and stability".
Journals and Book Chapters
  • Suwichaya Suwanwimolkul, Lei Zhang, Dong Gong, Zhen Zhang, Chao Chen, Damith C. Ranasinghe, Qinfeng Shi: "An Adaptive Markov Random Field for Structured Compressive Sensing", in IEEE Transactions on Image Processing (TIP), to appear
  • Tingting Wu, Alexander J. Dufford, Laura J. Egan, Melissa-Ann Mackie, Cong Chen, Changhe Yuan, Chao Chen, Xiaobo Li, Xun Liu, Patrick R. Hof, Jin Fan: "Hick–Hyman Law is Mediated by the Cognitive Control Network in the Brain", in Cerebral Cortex pp. 1-16, May 2017 (pdf)
  • Jingjing Liu, Chao Chen, Yan Zhu, Wei Liu, Dimitris Metaxas: “Video Classification via Weakly Supervised Sequence Modeling”, in Computer Vision and Image Understanding (CVIU) 152 pp. 79-87, Nov. 2016 (pdf)
  • Mustafa Uzunbas, Chao Chen, Dimitris Metaxas: “ An efficient conditional random field approach for automatic and interactive neuron segmentation”, in Medical Image Analysis (MedIA) 27 pp. 31-44, Jan. 2016 (pdf)
  • Arjun Jain, Chao Chen, Thorsten Thormählen, Dimitris Metaxas, Hans-Peter Seidel: “Multi-layer stencil creation from images”, in Computer & Graphics (C&G) 48 pp. 11-22, 2015 (pdf, video, website)
  • Chao Chen, Michael Kerber: “An output-sensitive algorithm for persistent homology”, in Computational Geometry: Theory and Applications (CGTA) 46 (4) pp. 435-447 - Special Issue on the 27th Annual Symposium on Computational Geometry, 2013 (pdf)
  • Yu Sheng, Barbara Cutler, Chao Chen, Joshua Nasman: "Perceptual global illumination cancellation in complex projection environments", in Computer Graphics Forum (CGF), Volume 30, Issue 4, Eurographics Symposium on Rendering (EGSR), 2011 (pdf)
  • Daniel Freedman, Chao Chen: "Algebraic topology for computer vision", Chapter 5 of Computer Vision, 239-268, Ed. Sota R. Yoshida, Nova Science Pub. Inc., Hauppauge, New York, 2011 (pdf)
  • Chao Chen, Daniel Freedman: "Hardness results for homology localization", in Discrete & Computational Geometry (DCG) 45(3): 425-448, 2011 (pdf)
  • Chao Chen, Daniel Freedman: "Measuring and computing natural generators for homology groups", in Computational Geometry: Theory and Applications (CGTA) 43(2): 169-181, 2010 (pdf)
  • Chao Chen, Ho-Lun Cheng: "Superimposing voronoi complexes for shape deformation", in International Journal of Computational Geometry and Applications (IJCGA) 16(2-3): 159-174 2006
Workshops
  • Chao Chen, Dimitris Metaxas, Yusu Wang, Pengxiang Wu, Changhe Yuan: "Cardiac Trabeculae Segmentation: an Application of Computational Topology", in the 27th Annual Fall Workshop on Computational Geometry (FWCG), 2017
  • Chao Chen, Han Liu, Dimitris Metaxas, Tianqi Zhao: "Identifying Sub-Networks of Functional Connectivity Using Modes of Distributions", in the 4th NIPS Workshop on Machine Learning and Interpretation in Neuroimaging (MLINI), 2014
  • Hubert Wagner, Chao Chen, Erald Vuçini: "Efficient computation of persistent homology for cubical data", in Proceedings of the 4th Workshop on Topology-based Methods in Data Analysis and Visualization (TopoInVis), 2011 (Best paper runner-up, pdf)
  • Chao Chen, Michael Kerber: "Persistent homology computation with a twist", in European Workshop on Computational Geometry (EuroCG), 2011 (pdf)
  • Chao Chen, Daniel Freedman: "Topology noise removal for curve and surface evolution", in Proceedings of the Medical Computer Vision Workshop (MCV) (in conjunction with MICCAI), 2010

Teaching

 Last modified: Yesterday