Research Interests

• Machine Learning/Reasoning: Deep Learning, Statistical Learning, and Graphical Models
• Biomedical Informatics: Text Understanding, Video Analysis, and Omics for Precision Medicine

Papers

(*Equal contribution, #Corresponding author)

Tianxiao Li*, Hongyu Guo, Filippo Grazioli, Mark Gerstein#, and Martin Renqiang Min*#. Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering. NeurIPS 2023.

Haifeng Xia, Kai Li, Martin Renqiang Min, Zhengming Ding. Few-Shot Video Classification via Representation Fusion and Promotion Learning. ICCV 2023.

Haomiao Ni, Changhao Shi, Kai Li, Sharon X. Huang, and Martin Renqiang Min#. Conditional Image-to-Video Generation with Latent Flow Diffusion Models. CVPR 2023.

Kai Li, Deep Patel, Erik Kruus, and Martin Renqiang Min. Learning Spatio-Temporal Manifolds for Source-Free Video Domain Adaptation. CVPR 2023.

Changhao Shi, Haomiao Ni, Kai Li, Shaobo Han, Mingfu Liang, and Martin Renqiang Min#. Exploring Compositional Visual Generation with Latent Classifier Guidance. CVPR Workshop 2023.

Ziqi Chen, Martin Renqiang Min#, Hongyu Guo, Chao Cheng, Trevor Clancy, and Xia Ning#. T-Cell Receptor Optimization with Reinforcement Learning and Mutation Polices for Precision Immunotherapy. RECOMB 2023.

Ziqi Chen*, Baoyi Zhang*, Hongyu Guo, Prashant Emani, Trevor Clancy, Chongming Jiang, Mark Gerstein, Xia Ning#, Chao Cheng#, and Martin Renqiang Min#. Binding Peptide Generation for MHC Class I Proteins with Deep Reinforcement Learning. Bioinformatics 2023.

Filippo Grazioli#, Pierre Machart, Anja Mosch, Kai Li, Leonardo Castorina, Nico Pfeifer, Martin Renqiang Min#. Attentive Variational Information Bottleneck for TCR-peptide Interaction Prediction. Bioinformatics 2023.

Filippo Grazioli#, Anja Mosch, Pierre Machart, Kai Li, Israa Alqassem, Timothy J. O'Donnell and Martin Renqiang Min#. On TCR Binding Predictors Failing to Generalize to Unseen Peptides. Frontiers in Immunology, section T Cell Biology, 2022.

Yiren Jian, Erik Kruus, and Martin Renqiang Min#. T-Cell Receptor-Peptide Interaction Prediction with Physical Model Augmented Pseudo-Labeling. KDD 2022 (Oral). [Slides] Physical Modeling prioritizes unlabeled data for pseudo labeling.

Zhiheng Li, Martin Renqiang Min#, Kai Li, and Chenliang Xu. StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis. CVPR 2022. Benchmark datasets for studying compositional reasoning.

Tingfeng Li, Shaobo Han, Martin Renqiang Min, and Dimitris Metaxas. Learning Transferable Reward for Query Object Localization with Policy Adaptation. ICLR 2022. Test-time policy adaptation to new environments.

Ligong Han, Sri Harsha Musunuri, Martin Renqiang Min, Ruijiang Gao, Yu Tian, and Dimitris Metaxas. AE-StyleGAN: Improved Training of Style-Based Auto-Encoders. WACV 2022.

Ziqi Chen, Martin Renqiang Min, Srinivasan Parthasarathy, and Xia Ning. A Deep Generative Model for Molecule Optimization via One Fragment Modification. Nature Machine Intelligence. 2021. Interpretable conditional variational encoder-decoder for molecule optimization.

Ligong Han, Martin Renqiang Min, Anastasis Stathopoulos, Yu Tian, Ruijiang Gao, Asim Kadav, and Dimitris Metaxas. Dual Projection Generative Adversarial Networks for Conditional Image Generation. ICCV 2021.

Yao Li, Martin Renqiang Min#, Thomas Lee, Wenchao Yu, Erik Kruus, Wei Wang, and Cho-Jui Hsieh. Towards Robustness of Deep Neural Networks via Regularization. ICCV 2021.

Jun Han*, Martin Renqiang Min*#, Ligong Han*, Li Erran Li, and Xuan Zhang. Disentangled Recurrent Wasserstein Autoencoder. ICLR 2021 (Spotlight, scored among top 4%).

Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, and Hans Peter Graf. Hopper: Multi-hop Transformer for Spatiotemporal Reasoning. ICLR 2021.

Ziqi Chen, Martin Renqiang Min#, and Xia Ning. Ranking-based Convolutional Neural Network Models for Peptide-MHC Binding Prediction. Frontiers in Molecular Biosciences. 2021.

Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, and Xiaodan Zhu. Retrieval, Analogy and Composition: A framework for Compositional Generalization in Image Captioning. EMNLP 2021.

Tian Tian, Martin Renqiang Min, and Zhi Wei. Model-Based Autoencoders for Imputing Discrete single-cell RNA-seq Data. Methods. 2020.

Pengyu Cheng, Martin Renqiang Min#, Dinghan Shen, Chris Malon, Yizhe Zhang, Yitong Li, and Lawrence Carin. Improving Disentangled Text Representation Learning with Information Theoretical Guidance. ACL 2020.

Yizhe Zhu, Martin Renqiang Min#, Asim Kadav, and Hans Peter Graf. S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation. CVPR 2020.

Lu Wang, Wenchao Yu, Wei Cheng, Martin Renqiang Min, Bo Zong, Xiaofeng He, Hongyuan Zha, Wei Wang, Haifeng Chen. Adversarial Cooperative Imitation Learning for Dynamic Treatment Regimes. Proceedings of the International Conference on World Wide Web (WWW'20), 2020.

Yogesh Balaji, Martin Renqiang Min#, Bing Bai, Rama Chellappa, and Hans Peter Graf. Conditional GAN with Discriminative Filter Generation for Text-to-Video Synthesis. IJCAI 2019. [Code]

Xiaoyuan Liang, Martin Renqiang Min#, Hongyu Guo, and Guiling Wang. Learning K-way D-dimensional Discrete Embedding for Hierarchical Data Visualization and Retrieval. IJCAI 2019. [Scripts]

Kai Li, Martin Renqiang Min#, and Yun Fu. Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective. ICCV 2019.

Kai Li, Martin Renqiang Min#, Bing Bai, Yun Fu, and Hans Peter Graf. On Novel Object Recognition: A Unified Framework for Discriminability and Adaptability. CIKM 2019.

Xiaoyuan Liang, Guiling Wang, Martin Renqiang Min, Qi Yi, and Zhu Han. A Deep Spatio-Temporal Fuzzy Neural Network for Passenger Demand Prediction. 2019 SIAM International Conference on Data Mining (SDM19).

Dinghan Shen, Martin Renqiang Min#, Yitong Li, and Lawrence Carin. Learning Context-Aware Convolutional Filters for Text Processing. EMNLP 2018.

Ting Chen, Martin Renqiang Min, and Yizhou Sun. Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations. ICML 2018.

Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen. Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection. International Conference on Learning Rrepresentations (ICLR 2018).

Yitong Li, Martin Renqiang Min#, Dinghan Shen, David Carlson, and Lawrence Carin. Video Generation from Text. AAAI 2018. This research project was reported by many national and international news media including Communications of the ACM [1], Science [2], and MIT Technology Review [3].

Yunchen Pu, Martin Renqiang Min#, Zhe Gan, and Lawrence Carin. Adaptive Feature Abstraction for Translating Video to Text. AAAI 2018. [Demo]

Yang Gao, Jeff M. Phillips, Yan Zheng, Martin Renqiang Min, P. Thomas Fletcher, and Guido Gerig. Fully Convolutional Structured LSTM Networks for Joint 4D Medical Image Segmentation. IEEE International Symposium on Biomedical Imaging (ISBI). 2018.

Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao and Lawrence Carin. Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms. ACL 2018. [Supp Material]

Martin Renqiang Min, Hongyu Guo, and Dinghan Shen. Parametric t-Distributed Stochastic Exemplar-centered Embedding. ECML 2018.

Huayu Li, Martin Renqiang Min#, Yong Ge, and Asim Kadav. A Context-aware Attention Network for Interactive Question Answering. KDD 2017.

Martin Renqiang Min, Hongyu Guo, and Dongjin Song. Exemplar-centered Supervised Shallow Parametric Data Embedding. IJCAI 2017.

Linnan Wang, Yi Yang, Martin Renqiang Min, and Srimat Chakradhar. Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent. Neural Networks. 2017.

Ke Zhang, Jianwu Xu, Martin Renqiang Min, Guofei Jiang, Konstantinos Pelechrinis, Hui Zhang. Automated IT System Failure Prediction: A Deep Learning Approach. IEEE BigData 2016, Washington D.C., USA, Dec 2016 (acceptance rate: 18.7%).

Martin Renqiang Min*#, Pavel Kuksa*, Rishabh Dugar*, and Mark Gerstein#. High-Order Neural Networks and Kernel Methods for Peptide-MHC Binding Prediction. Bioinformatics. 2015. [Supplementary Material][Prediction Scores]

Martin Renqiang Min*#, Sanjay Purushotham*, C.-C. Jay Kuo, and Rachel Ostroff. Factorized Sparse Learning Models with Interpretable High Order Feature Interactions. KDD 2014 (Acceptance rate: 14.6%). [Supplementary Material][Slides][Code]

Martin Renqiang Min, Xia Ning, Chao Cheng, and Mark Gerstein. Interpretable Sparse High-Order Boltzmann Machines. The Seventeenth International Conference on Artificial Intelligence and Statistics (AISTATS 2014), Reykjavik, Iceland, 2014. Supplementary Material. (A method called sparse high order logistic regression is proposed in this paper)

Martin Renqiang Min*#, Salim Chowdhury*, Yanjun Qi, Alex Stewart, and Rachel Ostroff. An integrated approach to blood-based cancer diagnosis and biomarker discovery. Pacific Symposium on Biocomputing (PSB 2014), Big Island, Hawaii, 2014.

The ENCODE Project Consortium. An integrated encyclopedia of DNA elements in the human genome. Nature. 2012.

M. Gerstein*, ..., R. Min* et al. (*Co-first authors) Architecture of the human regulatory network derived from ENCODE data. Nature. 2012.

C. Cheng, R. Alexander, R. Min, ..., E. Birney, Z. Weng, M. Gerstein. Understanding transcriptional regulation by integrative analysis of transcription factor binding data. Genome Research. 2012.

C. Cheng, R. Min, and M. Gerstein. TIP: A probabilistic method for identifying transcription factor target genes from ChIP-Seq binding profiles. Bioinformatics. 2011.

K. Jin, J. Li, F. Vizeacoumar, Z. Li, R. Min, L. Zamparo, F. Vizeacoumar, A. Datti, B. Andrews, C. Boone, and Z. Zhang. PhenoM: a database of morphological phenotypes caused by mutation of essential genes in Saccharomyces cerevisiae. Nucleic Acids Research. 2011.

Z. Li, F. Vizeacoumar, S. Bahr, J. Li, J. Waringer,F. Vizeacoumar, R. Min, ..., Z. Zhang, A. Blomberg, K. Bloom, B. Andrews, C. Boone (31 co-authors). Systematic exploration of essential yeast gene function with temperature-sensitive mutants. Nature Biotechnology. 2011.

R. Min. Machine learning approaches to biological sequence and phenotype data analysis. PhD Thesis. Department of Computer Science, University of Toronto. September 2010.

R. Min, L. van der Maaten, Z. Yuan, A. Bonner, and Z. Zhang. Deep supervised t-distributed embedding. The 27th International Conference on Machine Learning (ICML 2010), Haifa, Israel, 2010. [Slides][Code]

J. Li, Y. Liu, T. Kim, R. Min, and Z. Zhang. Gene expression variability within and between human populations and implications toward disease susceptibility. PLoS Computational Biology. 2010.

J. Li, R. Min, FJ Vizeacoumar, K. Jin, X. Xin, and Z. Zhang. Exploiting the determinants of stochastic gene expression in S. cerevisiae for genome-wide prediction of expression noise. Proc Natl Acad Sci U S A (PNAS). Vol. 107 No. 23, 10472-10477. 2010.

R. Min, D. A. Stanley, Z. Yuan, A. Bonner, and Z. Zhang. A deep non-linear feature mapping for large-margin kNN classification. IEEE International Conference on Data Mining (ICDM 2009). PP. 357-366. Regular paper and oral presentation. Acceptance rate: 8.9%.[Slides][Code]

R. Min, A. Bonner, J. Li, and Z. Zhang. Learned random-walk kernels and empirical-map kernels for protein sequence classification. Journal of Computational Biology. March 2009, 16(3): 457-474.

R. Min*, J. Li*, A. Bonner, and Z. Zhang. (*Co-first authors) A probabilistic framework to improve microRNA target prediction by incorporating proteomics data. Journal of Bioinformatics and Computational Biology. Volume: 7, Issue: 6(2009) pp. 955-972.

R. Min, R. Kuang, A. Bonner, and Z. Zhang. Learning random-walk kernels for protein remote homology identification and motif discovery. 2009 SIAM International Conference on Data Mining (SDM09). PP. 133-144. Full paper and oral presentation. Acceptance rate: 15.7%.

R. Min, A. Bonner, and Z. Zhang. Modifying kernels using label information improves SVM classification performance. IEEE Proceeding of the 2007 International Conference on Machine Learning and Applications, pp. 13-18. December 13-15, 2007.

R. Min. A non-linear dimensionality reduction method for improving nearest neighbour classification. Master Thesis. Department of Computer Science, University of Toronto. 2005.

Ting Chen, Martin Renqiang Min, and Yizhou Sun. Learning K-way D-dimensional Discrete Code for Compact Embedding Representations. NIPS Workshop on Discrete Structures in Machine Learning 2017.

Yunchen Pu, Martin Renqiang Min, Zhe Gan, and Lawrence Carin. Adaptive Feature Abstraction for Translating Video to Language. Workshop International Conference on Learning Rrepresentations (ICLR 2017).

Sanjay Purushotham, Martin Renqiang Min, C.-C. Jay Kuo, and Mark Gerstein. Knowledge Based Factorized High Order Sparse Learning Models. NIPS 2015 Workshop on Machine Learning in Computational Biology. [Long version]

Cun Mu, Asim Kadav, Erik Kruus, Donald Goldfarb, and Martin Renqiang Min. Random Walk Distributed Dual Averaging Method For Decentralized Consensus Optimization. NIPS 2015 Workshop on Optimization for Machine Learning (OPT2015).

Martin Renqiang Min*#, Pavel Kuksa*, Rishabh Dugar*, and Mark Gerstein#. High-Order Neural Networks and Kernel Methods for Peptide-MHC Binding Prediction. NIPS 2014 Workshop on Machine Learning in Computational Biology.

Martin Renqiang Min, Xia Ning, Yanjun Qi, Chao Cheng, Anthony Bonner, and Mark Gerstein. Ensemble Learning Based Sparse High-Order Boltzmann Machine for Unsupervised Feature Interaction Identification. NIPS 2014 Workshop on Machine Learning in Computational Biology (Oral presentation).

Hongyu Guo*, Xiaodan Zhu*, and Martin Renqiang Min*. A Deep Learning Model for Structured Outputs with High-order Interaction. NIPS 2014 Workshop on Representation and Learning Methods for Complex Outputs.

Dongjin Song, David Meyer, and Martin Renqiang Min. Fast Nonnegative Matrix Factorization with Rank-one ADMM. NIPS 2014 Workshop on Optimization for Machine Learning (OPT2014).

Hao Wu, Martin Renqiang Min, and Bing Bai. Deep Semantic Embedding. SIGIR 2014 Workshop on Semantic Matching for Information Retrieval. 2014.

Martin Renqiang Min, Xia Ning, Chao Cheng, and Mark Gerstein. Interpretable Sparse High-Order Boltzmann Machines for Transcription Factor Interaction Identification. NIPS 2013 Workshop on Machine Learning in Computational Biology. (The results are based on ENCODE ChIP-Seq TF binding data filtered by our published method TIP)

Technical Reports