SelectedWorks - Kun Zhang

Selected Works of Kun Zhang

Acting Department Chair and Visiting Professor, Department of Machine Learning, & Director of Center for Integrative Artificial Intelligence (CIAI), MBZUAI

Dr. Kun Zhang is the  Acting Department Chair and Visiting Professor in the Machine Learning Department and Director of the Center for Integrative Artificial Intelligence (CIAI) at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI).

Biography

Dr. Kun Zhang joined MBZUAI as a Visiting Associate Professor in the Machine Learning Department (he is currently on leave from Carnegie Mellon University, where he is an associate professor).  His research interests lie in machine learning and artificial intelligence, especially in causal discovery and causality-based learning. He develops methods for automated causal discovery or causal representation learning from various kinds of data, investigates learning problems including transfer learning, representation learning, and deep learning from a causal view, and studies philosophical foundations of causation and various machine learning tasks. On the application side, he is interested in neuroscience, computer vision, computational finance, and climate analysis.

Works
About

×

About Kun Zhang

Dr. Kun Zhang is the  Acting Department Chair and Visiting Professor in the Machine Learning Department and Director of the Center for Integrative Artificial Intelligence (CIAI) at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI).

Biography

Dr. Kun Zhang joined MBZUAI as a Visiting Associate Professor in the Machine Learning Department (he is currently on leave from Carnegie Mellon University, where he is an associate professor).  His research interests lie in machine learning and artificial intelligence, especially in causal discovery and causality-based learning. He develops methods for automated causal discovery or causal representation learning from various kinds of data, investigates learning problems including transfer learning, representation learning, and deep learning from a causal view, and studies philosophical foundations of causation and various machine learning tasks. On the application side, he is interested in neuroscience, computer vision, computational finance, and climate analysis.

Present	Associate Professor, Mohamed bin Zayed University of Artificial Intelligence ‐ Department of Machine Learning
Institution Organization Position Type Position Title Time Period to Options Current Position Affiliate my profile with this Institution

Computer Sciences, Artificial Intelligence and Robotics, Statistics and Probability, and Data Science

causal discovery and inference, machine learning, and representation learning

Co-authored a best paper finalist paper at CVPR 2019.
Co-authored best student paper at UAI 2010.
Best benchmark award of the causality challenge 2008.
Test of Time Award Honorable Mention at ICML 2022
Best Paper Award of the workshop on New Frontiers in Adversarial Machine Learning (AdvML 2022) at ICML 2022
General and program chair of the 1st Conference on Causal Learning and Reasoning (CleaR 2022)
Program chair of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022)

Knee Injury Diagnosis with Data and Feature Fusion-Enhanced Multi-Label Classification Network (Hanin Al Ghothani and Kun Zhang) Proceedings - International Symposium on Biomedical Imaging (2023)

Knee injuries are among the most common human afflictions despite age, gender, or lifestyle. They are often detected using a non-invasive diagnostic tool such as Magnetic Resonance Imaging (MRI) of the knee. With the rising ...

Improving the Expressiveness of K-hop Message-Passing GNNs by Injecting Contextualized Substructure Information (Tianjun Yao, Yingxu Wang, Kun Zhang, et al.) Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2023)

Graph neural networks (GNNs) have become the de facto standard for representational learning in graphs, and have achieved state-of-the-art performance in many graph-related tasks; however, it has been shown that the expressive power of standard ...

Factored Adaptation for Non-stationary Reinforcement Learning (Fan Feng, Biwei Huang, Kun Zhang, et al.) Advances in Neural Information Processing Systems (2022)

Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most current approaches ...

Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models (Haoyue Dai, Peter Spirtes and Kun Zhang) Advances in Neural Information Processing Systems (2022)

Causal discovery aims to recover causal structures generating the observational data. Despite its success in certain problems, in many real-world scenarios the observed variables are not the target variables of interest, but the imperfect measures ...

Latent Hierarchical Causal Structure Discovery with Rank Constraints (Biwei Huang, Charles Low, Feng Xie, et al.) Advances in Neural Information Processing Systems (2022)

Most causal discovery procedures assume that there are no latent confounders in the system, which is often violated in real-world problems. In this paper, we consider a challenging scenario for causal structure identification, where some ...

MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models (Erdun Gao, Ignavier Ng, Mingming Gong, et al.) Advances in Neural Information Processing Systems (2022)

State-of-the-art causal discovery methods usually assume that the observational data is complete. However, the missing data problem is pervasive in many practical scenarios such as clinical trials, economics, and biology. One straightforward way to address ...

ADARL: WHAT, WHERE, AND HOW TO ADAPT IN TRANSFER REINFORCEMENT LEARNING (Biwei Huang, Fan Feng, Chaochao Lu, et al.) ICLR 2022 - 10th International Conference on Learning Representations (2022)

One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called AdaRL, that adapts reliably and ...

Conditional Contrastive Learning with Kernel (Yao Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, et al.) ICLR 2022 - 10th International Conference on Learning Representations (2022)

Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables. Fair contrastive learning constructs negative pairs, for example, from the same gender (conditioning on sensitive ...

Learning Temporally Causal Latent Processes from General Temporal Data (Weiran Yao, Yuewen Sun, Alex Ho, et al.) ICLR 2022 - 10th International Conference on Learning Representations (2022)

Our goal is to recover time-delayed latent causal variables and identify their relations from measured temporal data. Estimating causally-related latent variables from observations is particularly challenging as the latent variables are not uniquely recoverable in ...

Partial Identifiability for Domain Adaptation (Lingjing Kong, Shaoan Xie, Weiran Yao, et al.) Proceedings of Machine Learning Research (2022)

Unsupervised domain adaptation is critical to many real-world applications where label information is unavailable in the target domain. In general, without further assumptions, the joint distribution of the features and the label is not identifiable ...

Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint (Jiaxian Guo, Jiachen Li, Huan Fu, et al.) Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2022)

Unsupervised image-to-image (I21) translation aims to learn a domain mapping function that can preserve the semantics of the input images without paired data. However, because the underlying semantics distributions in the source and target domains ...

Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation (Yanwu Xu, Shaoan Xie, Wenhao Wu, et al.) Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2022)

Unpaired image-to-image translation (I2I) is an ill-posed problem, as an infinite number of translation functions can map the source domain distribution to the target distribution. Therefore, much effort has been put into designing suitable constraints, ...

Residual Similarity Based Conditional Independence Test and Its Application in Causal Discovery (Hao Zhang, Shuigeng Zhou, Kun Zhang, et al.) Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022 (2022)

Recently, many regression based conditional independence (CI) test methods have been proposed to solve the problem of causal discovery. These methods provide alternatives to test CI by first removing the information of the controlling set ...

Journal article (6)

Ada-FFL: Adaptive computing fairness federated learning (Yue Cong, Jing Qiu, Kun Zhang, et al.) CAAI Transactions on Intelligence Technology (2023)

As the scale of federated learning expands, solving the Non-IID data problem of federated learning has become a key challenge of interest. Most existing solutions generally aim to solve the overall performance improvement of all ...

A New Minimality Condition for Boolean Accounts of Causal Regularities (Jiji Zhang and Kun Zhang) Erkenntnis (2023)

The account of causal regularities in the influential INUS theory of causation has been refined in the recent developments of the regularity approach to causation and of the Boolean methods for inference of deterministic causal ...

Causal discovery of 1-factor measurement models in linear latent variable models with arbitrary noise distributions (Feng Xie, Yan Zeng, Zhengming Chen, et al.) Neurocomputing (2023)

The problem of causal discovery is especially challenging when the variables of interest cannot be directly measured. In measurement models, the measured variables were generated by latent causal variables that are causally related to each ...

Action-Sufficient State Representation Learning for Control with Structural Constraints (Biwei Huang, Chaochao Lu, Liu Leqi, et al.) Proceedings of Machine Learning Research (2022)

Perceived signals in real-world scenarios are usually high-dimensional and noisy, and finding and using their representation that contains essential and sufficient information required by downstream decision-making tasks will help improve computational efficiency and generalization ability ...

Testability of Instrumental Variables in Linear non-Gaussian Acyclic Causal Models (Feng Xie, Yangbo He, Zhi Geng, et al.) Entropy (2022)

This paper investigates the problem of selecting instrumental variables relative to a target causal influence X → Y from observational data generated by linear non-Gaussian acyclic causal models in the presence of unmeasured confounders. We ...

Relevance Attack on Detectors (Sizhe Chen, Fan He, Xiaolin Huang, et al.) Pattern Recognition (2022)

This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures. To pursue a high attack transferability, one ...

Truncated Matrix Power Iteration for Differentiable DAG Learning (Zhen Zhang, Ignavier Ng, Dong Gong, et al.) arXiv (2022)

Recovering underlying Directed Acyclic Graph structures (DAG) from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem. Recently, DAG learning has been cast as a continuous optimization problem by ...

On the Identifiability of Nonlinear ICA: Sparsity and Beyond (Yujia Zheng, Ignavier Ng and Kun Zhang) arXiv (2022)

Nonlinear independent component analysis (ICA) aims to recover the underlying independent latent sources from their observable nonlinear mixtures. How to make the nonlinear ICA model identifiable up to certain trivial indeterminacies is a longstanding problem ...

Casual Balancing for Domain Generalization (Xinyi Wang, Michael Saxon, Jiachen Li, et al.) arXiv (2022)

While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy ...

What-Is and How-To for Fairness in Machine Learning: A Survey, Reflection, and Perspective (Zeyu Tang, Jiji Zhang and Kun Zhang) arXiv (2022)

Algorithmic fairness has attracted increasing attention in the machine learning community. Various definitions are proposed in the literature, but the differences and connections among them are not clearly addressed. In this paper, we review and ...

Offline Reinforcement Learning with Causal Structured World Models (Zheng-Mao Zhu, Xiong-Hui Chen, Hong-Long Tian, et al.) arXiv (2022)

Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully connected nets as world-models ...

Attainability and Optimality: The Equalized Odds Fairness Revisited (Zeyu Tang and Kun Zhang) arXiv (2022)

Fairness of machine learning algorithms has been of increasing interest. In order to suppress or eliminate discrimination in prediction, various notions as well as approaches have been proposed to impose fairness. Given a notion of ...