Publications

Publications:

  • J. Kim, A. Lamb, S. Woodhead, S. Peyton Jones, C. Zhang, M. Allamanis
    CoRGi: Content-Rich Graph Neural Networks with Attention
    SIGKDD Conference on Knowledge Discovery and Data Mining (KDD, 2022)
  • R. Tu, H. Kjellstrom, K. Zhang, C.Zhang
    Optimal Transport for Causal Discovery
    The International Conference on Learning Representations (ICLR, 2022)
  • P. Versteeg, C.Zhang, J. Mooij
    Local Constraint-Based Causal Discovery under Selection Bias
    The Conference on Causal Learning and Reasoning (CLeaR, 2022)
  • C. Ma  ,  C. Zhang
    Identifiable Generative models for Missing Not at Random Data Imputation
    Conference on Neural Information Processing Systems  (NeurIPS 2021) 
  • H. Ritter, M. Kukla, C. Zhang, Y. Li
    Sparse Uncertainty Representation in Deep Learning with Inducing Weights
    Conference on Neural Information Processing Systems  (NeurIPS 2021) 
  • J. Grosse,  C. Zhang, P. Hennig
    Probabilistic DAG Search 
    Conference on Uncertainty in Artificial Intelligence (UAI 2021)
  • R. Tu, K. Zhang, H. Kjellstrom, C. Zhang
    Optimal transport for causal discovery
    ICML 2021 workshop on the Neglected Assumptions in Causal Inference
  • P. Morales-Alvarez, A. Lamb, S. Woodhead,  S. Peyton Jones, M. Allamanis,  C. Zhang
    VICAUSE: Simultaneous missing value imputation and causal discovery
    ICML 2021 workshop on the Neglected Assumptions in Causal Inference
  • A. Sharma, V. Syrgkanis,  C. Zhang, E. Kiciman
    DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions
    ICML 2021 workshop on the Neglected Assumptions in Causal Inference
  • M. Klasson, H. Kjellstrom,  C. Zhang
    Learn the Time to Learn: Replay Scheduling for Continual Learning
    ICML 2021 workshop on Theory and Foundation of Continual Learning
  • R. Zhang, Y. Li, C. De Sa, S. Devlin, C. Zhang
    Meta-Learning for Variational Inference
    International Conference on Artificial Intelligence and Statistics (AISTATS 2021)
  • V.  Chandrasekaran, D. Edge, S. Jha, A. Sharma, C. Zhang, S. Tople
    Causally Constrained Data Synthesis for Private Data Release
    ICLR 2021 workshop on distributed & private ML
  • T. Rashid, C. Zhang, K. Ciosek
    Estimating α-Rank by Maximizing Information Gain
    AAAI Conference on Artificial Intelligence (AAAI 2021)
  • Z. Wang, S. Tschiatschek, S. Woodhead, J.M. Hernández-Lobato, S. Peyton Jones, R.G. Baraniuk and C. Zhang
    Educational Question Mining At Scale: Prediction, Analysis and Personalization,
    In Symposium on Educational Advances in Artificial Intelligence (AAAI-EAAI), 2021.
  • M. Klasson,  C. Zhang, and H. Kjellström.
    Using Variational Multi-view Learning for Classification of Grocery Items.
    Patterns 1.8 (2020): 100143.
  • C. Ma, S. Tschiatschek, R. Turner, J.M.H. Lobato, C. Zhang,
    VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
    Conference on Neural Information Processing Systems  (NeurIPS 2020) 
  • X. Zhang*(first author),  R.Tu*(first author), L.Yang, M. Liu, K. Zhang, C.Zhang
    How do fair decisions fare in long-term qualification?
    Conference on Neural Information Processing Systems  (NeurIPS 2020) 
  • C. Zhang, K.Zhang, Y. Li
    A Causal View on Robustness of Neural Networks
    Conference on Neural Information Processing Systems  (NeurIPS 2020)
  • A. Lamb, E. Saveliev, Y. Li, S. Tschiatschek, C. Longden, S. Woodhead, J. M. Hernandez-Lobato, R. E. Turner, P. Cameron, C. Zhang
    Contextual HyperNetworks for Novel Feature Adaptation
    NeurIPS 2020 Workshop: Meta-Learning
  • P. J. Ball, Y. Li, A.Lamb, C. Zhang
    A Study on Efficiency in Continual Learning Inspired by Human Learning
    NeurIPS 2020 Workshop: BabyMind
  • H. Yin, Y. Li, S. Pan, C. Zhang, S. Tschiatschek
    Reinforcement Learning with Efficient Active Feature Acquisition
    NeurIPS 2020 Workshop: Learning Meets Combinatorial Algorithms
  • A.L. Popkes, H. Overweg, A. Ercole, Y. Li, J.M. Hernández-Lobato, Y. Zaykov, C. Zhang
    Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care
    ICML 2020  Workshop on Healthcare Systems, Population Health, and the Role of Health-tech
    [ArXiv]
  • T. Rashid, C. Zhang, K. Ciosek
    Estimating α-Rank by Maximizing Information Gain
    ICML 2020  Workshop on Real World Experiment Design and Active Learning
    [pdf]
  • J. Beck, K. Ciosek, S. Devlin, S. Tschiatschek, C. Zhang, K. Hofmann,
    AMRL: Aggregated Memory For Reinforcement Learning
    International Conference on Learning Representations (ICLR 2020)
  • C. Zhang, J. Butepage, H. Kjellstrom, and S. Mandt,
    Advances in Variational Inference,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019
    [ArXiv pdf]
  • R. Bamler*, C.Zhang*, M. Opper, S. Mandt* (Equal contribution)
    Tightening Bounds for Variational Inference by Revisiting Perturbation Theory
    Machine Learning Special Issue on Journal of Statistical Mechanics: Theory and Experiment (JSTATS), 2019
  • W. Gong , S. Tschiatschek, S. Nowozin, R.E. Turner, J.M. Hernández-Lobato, C.Zhang
    Icebreaker: Efficient Information Acquisition with Active Learning
    Conference on Neural Information Processing Systems  (NeurIPS 2019) 
    [ArXiv]
  • R. Tu, K. Zhang,  B, Bertilson, H. Kjellstrom, C. Zhang
    Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation
    Conference on Neural Information Processing Systems  (NeurIPS 2019) 
    [ArXiv]
  • M. Igl,  K. Ciosek,  Y. Li, S. Tschiatschek , C.  Zhang,  S. Devlin,  K. Hofmann
    Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
    Conference on Neural Information Processing Systems  (NeurIPS 2019) 
  • C. Zhang, Y. Li
    A Causal View on Robustness of Neural Networks,
    ICML Workshop on Understanding and Improving Generalization in Deep Learning, 2019
    [PDF]
  • C. Ma, S. Tschiatschek, K. Palla, J.M.H. Lobato, S. Nowozin, C. Zhang,
    EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE,
    International Conference on Machine Learning (ICML), 2019
    [PDF]
  • C.  Hamesse,  R. Tu, P.  Ackermann, H. Kjellstrom, and C. Zhang,
    Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation,
    Conference on Machine Learning for Healthcare (MLHC), 2019
    [ArXiv]
  • R.  Tu*,  C. Zhang*,  P. Ackermann, K. Mohan, H. Kjellström, K. Zhang*,
    Causal discovery in the presence of missing data,
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
    ( * equal contribution)
    [arXiv]
  • C. Zhang, C. Öztireli, S. Mandt, G. Salvi,
    Active Mini-Batch Sampling using Repulsive Point Processes,
    The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019 (acceptance rate 16.2%; Oral)
    [arXiv]
  • M. Klasson, C. Zhang, and H. Kjellström,
    A hierarchical grocery store image dataset with visual and semantic labels.
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2019.
  • C. Ma, W. Gong, J.M. Hernandez-Lobato, N. Koenigstein, S. Nowozin, C. Zhang,
    Partial VAE for Hybrid Recommender System
    NIPS Workshop on Bayesian Deep Learning, 2018
    [pdf]
  • J. Butepage, J. He, C. Zhang, L.Sigal, G. Mori, S. Mandt,
    Informed Priors for Deep Representation Learning,
    Symposium on Advances in Approximate Bayesian Inference, 2018
  • T.F. Fu, C. Zhang, S. Mandt,
    Continuous Word Embedding Fusion via Spectral Decomposition,
    The SIGNLL Conference on Computational Natural Language Learning  (CoNLL), 2018
    [Preprint] [Appendix]
  • T. Ding, C. Zhang, M. Bos,
    Causal Feature Selection for Individual Characteristics Prediction,
    International Conference on Tools with Artificial Intelligence (ICTAI), 2018
    [arXiv]
  • C. Zhang, C. Oztireli and S. Mandt,
    Diversified Mini-Batch Sampling using Repulsive Point Processes,
    NIPS Workshop on Advances in Approximate Bayesian Inference, 2017
    [PDF]
  • M. Klasson, K. Zhang, B. Bertilson, C. Zhang and H. Kjellström,
    Causality Refined Diagnostic Prediction,
    NIPS Workshop on Machine Learning for Health (ML4H), 2017
    [PDF]
  • R. Bamler*, C. Zhang*, M. Opper and S. Mandt,
    Perturbative Black Box Variational Inference,
    Conference on Neural Information Processing Systems  (NIPS 2017)(*Joint first authorship; order decided by coin flip.) [pdf]
  • C. Zhang, H. Kjellström, and S. Mandt,
    Determinantal Point Processes for Mini-batch Diversification,
    Uncertainty in Artificial Intelligence (UAI 2017). Plenary talk
    [pdf]
  • C. Zhang,
    Structured Representation Using Latent Variable Models,
    PhD Thesis, 2016
    [PDF]
  • C. Zhang, S. Mandt and H. Kjellström,
    Balanced Population Stochastic Variational Inference,
    NIPS Workshop on Advances in Approximate Bayesian Inference, 2016
    [pdf]
  • A. Qu, C. Zhang, P. Ackermann and H. Kjellström,
    Bridging Medical Data Inference to Achilles Tendon Rupture Rehabilitation,
    NIPS Workshop on Machine Learning for Health, 2016
    [pdf]
  • C. Zhang, H. Kjellström and B. C. Bertilson,
    Diagnostic Prediction Using Discomfort Drawings,
    NIPS Workshop on Machine Learning for Health, 2016 (This is an extension of the MLHC conference paper)
    [pdf]
  • C. Zhang, H. Kjellström and C.H. Ek,
    Inter-Battery Topic Representation Learning
    European Conference on Computer Vision (ECCV), 2016
    [pdf] [Supplement]
  • C. Zhang, H. Kjellström, C.H. Ek and B. C. Bertilson,
    Diagnostic Prediction Using Discomfort Drawing with IBTM,
    Machine Learning in Health Care Conference, 2016
    [pdf]
  • K. Zhang, J. Karlgren, C. Zhang, J. Lagergren.
    Viewpoint and Topic Modeling of Current Events,
    arXiv, 2016  [arXiv]
  • C. Zhang, M. Gartrell, T. P. Minka, Y. Zaykov and J. Guiver,
    GroupBox: A generative model for group recommendation,
    Microsoft Research technical report; MSR-TR-2015-61
    [PDF]
  • C. Zhang and H. Kjellström,
    How to Supervise Topic Models,
    ECCV workshop on Graphical Models in Computer Vision (ECCVws 2014, GMCV) (oral)
    [PDF][Supplement][Slides]
  • C. Zhang, C.H. Ek, X. Gratal, F. T. Pokorny and H. Kjellström,
    Supervised Hierarchical Dirichlet Processes with Variational Inference,
    IEEE ICCV workshop on Inference for probabilistic graphical models (ICCVws 2013, Infer PGM) (oral)
    [PDF] [Supplement][Slides][Poster][Code]
  • C. Zhang, D. Song and H. Kjellström,
    Contextual Modeling with Labeled Multi-LDA,
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013)
    [PDF][Bibtex] [Slides]
  • C. Zhang, C.H. Ek, A. Damianou, H. Kjellström,
    Factorized Topic Models.
    International Conference on Learning Representations 2013, (ICLR 2013)
    [PDF] [Bibtex][Poster]
  • C. Zhang and H. Kjellström,
    Multi-Class Detection and Segmentation of Objects in Depth
    [PDF] [Bibtex]