Dongkuan (DK) Xu / 胥栋宽

Hello! I am an Assistant Professor at NC State CS, leading the NCSU Reliable & Efficient Computing Lab (web under construction) and working on deep learning, machine learning, and natural language processing. I received my Ph.D. at Penn State, where I was advised by Xiang Zhang. I received my M.S. in Optimization and B.E. at the University of Chinese Academy of Sciences and Renmin University of China, respectively.

I has been collaborating with Microsoft Research exploring neural architecture search (NAS) and hyperparameter optimization (HPO) for Foundation Models, and with Google Research to enable scalable and adaptive learning for Vision-Language Models. I was a research scientist at Moffett AI, investigating low-resource model compression. I also spent some wonderful time at NEC Labs America on contrastive learning and multi-task learning.

Other than my work, I am a big fan of American football. I love Nittany Lions, New York Giants, and Dallas Cowboys. I also like workout and soccer ball.

Email  /  CV (Oct 2022)  /  Twitter  /  Google Scholar  /  LinkedIn   

I'm actively looking for multiple PhDs / interns to work in Reliable & Efficient AI (一亩三分地 I, 一亩三分地 II). Feel free to send me your CV. Once we have a commitment to each other, trust me I will do my best to help you!   

(I've received an amazingly large number of applications. Super thanks for everyone's interest! Interviews are in progress. Good luck~)   

I'm interested in reliable, efficient, and landable deep learning for AI at scale, investigating how to achieve Pareto optimality between decision reliability (uncertainty, robustness, adaptability), computational resources (data, parameters, computation), and model performance (inference, training) of deep learning systems. My long-term research goal is to free AI from the data-parameter-computation hungry beast and democratize AI to serve a broader range of populations and real-world domains.

• Reliable & Scalable Deep Learning with Theoretical Guarantees

• Efficient Large-scale Training & Inference Algorithms

• Algorithm-hardware Co-design for AI Acceleration

• Applications: Natural Language Processing, Computer Vision, Sciences

The First Workshop on DeepLearning-Hardware Co-Design for AI Acceleration (link) to be held at AAAI’23 (Workshop Chair)

• Welcomed topics include: model compression, deep learning acceleration, hard-soft co-design, applications, etc

• Workshop is non-archival and permits under-review or concurrent submissions. Best Paper Awards will be selected

• Submission Deadline: November 30th, 2022 (link)

2023

We propose two model augmentation techniques, i.e. using early-stage models and weight perturbation to learn an informative synthetic set with significantly reduced training cost. Extensive experiments demonstrate that our method achieves up to 20× speedup.

We propose a novel early exiting strategy based on cascading input similarity with valid assumptions on saturation states in visual-language models, a pioneering exploration of extending early exiting selection to encoders and decoders of sequence-to-sequence architectures.

We for the first time identify and study the reliability problem of sparse training and find that sparse training exacerbates the over-confidence problem of DNNs. We then develop a new sparse training method, CigL, to produce more reliable sparse models, which can simultaneously maintain or even improve accuracy with only a slight increase in computational and storage burden.

To assist explainable sparse training, we propose important weights exploitation and weights coverage exploration to characterize sparse training. Our method does not need to train dense models, achieving up to 95% sparsity ratio and even higher accuracy than dense training, with same amount of iterations.

We propose an energy efficient spiking neural network training workflow, and design a new drop-andgrow strategy with decreasing number of non-zero weights in the process of dynamically updating sparse mask. We demonstrate extremely high sparsity (i.e., 99%) model performance in SNN based vision tasks.

We develop a gradient-like proposal for any discrete distribution without this strong requirement. Built upon a locally-balanced proposal, our method efficiently approximates the discrete likelihood ratio via a Newton’s series expansion to enable a large and efficient exploration in discrete spaces.

We develop an adaptive gradient correction method to accelerate and stabilize the convergence of sparse training. Theoretically, we prove that our method can accelerate the convergence rate of sparse training.

We propose a class-based covariance transfer method from the perspective of disentangling to transfer covariance information in long-tailed classification task.

We propose an autonomous image composition and masking method for cloud masking, a fundamental task in Earth observation problems across social sectors such as agriculture, energy, and water.

We propose an adaptive data augmentation method to avoid ad-hoc choices or painstakingly trial-and-error tuning for time series representation learning.

2022

We develop a few-shot task-agnostic NAS framework, AutoDistil, for distilling large language models into compressed students with variable computational cost. AutoDistil outperforms leading baselines with upto 3x additional reduction in computational cost and negligible loss in task performance.

We introduce the first commercial hardware platform supporting high-degree sparsity acceleration up to 32 times — S4. S4 provides a (sparse) equivalent computation power of 944 TOPS in INT8 and 472 TFLOPS in BF16, and has 20GB LPDDR4 memory with up to 72 GB memory bandwidth in a low 70 Watt power envelope. We demonstrate several-times practical inference speedup on S4 over mainstream inference platforms such as Nvidia T4.

We propose AE-BERT, an automatic and efficient pruning framework. AE-BERT achieves the inference time of a single BERT-BASE encoder on Xilinx Alveo U200 FPGA board that is 1.83x faster compared to Intel(R) Xeon(R) Gold 5218 (2.30GHz) CPU.

We study network pruning of Transformer-based language models under the pre-training and fine-tuning paradigm and propose a counter-traditional hypothesis that pruning increases the risk of overfitting when performed during the fine-tuning phase.

2021

We propose an information-aware contrastive learning framework for graph-structure data, and show for the first time that all recent graph contrastive learning methods can be unified by our framework.

We study how knowledge is transferred and lost during the pre-train, fine-tune, and pruning process, and propose a knowledge-aware sparse pruning process that achieves significantly superior results than existing literature.

We study data augmentation for cross-lingual natural language inference and propose two methods of training a generative model to induce synthesized examples to reflect more diversity in a semantically faithful way.

We utilize multi-instance learning to model the uncertainty of precursor period, and design a contrastive loss to address the issue that annotated anomalies are few.

We propose MT-RMN to dynamically learn task relationships and accordingly learn to assemble composable modules into complex layouts to jointly solve multiple sequence processing tasks.

We propose TRRN to model temporal networks by employing transformer-style self-attention to reason over a set of memories.

We propose MoveSD to model state transition in human movement from a novel perspective, by learning the decision model and integrating the system dynamics.

We introduce Longitudinal deep kernel Gaussian process regression to fully automate the discovery of complex multi level correlation structure from longitudinal data.

2020

We propose to adopt deep neural networks to parameterize the generation process of explanations, which enables a natural approach to multi-instance explanations.

We propose a semi-supervised adversarial perturbation framework that encourages the model to be more robust towards such divergence and better adapt to the target language.

We propose a deep architecture for learning trends in multivariate time series, which jointly learns both local and global contextual features for predicting the trend of time series.

We propose longitudinal kulti-level factorization machine, to the best of our knowledge, the first model to address these challenges in learning predictive models from longitudinal data.

2019

We propose an adaptive neural network for node classification in dynamic networks, which is able to consider the evolution of both node attributes and network topology.

We propose a spatio-temporal attentive RNN model, which aims to learn node representations for classification by jointly considering both the temporal and spatial patterns of the node.

DeepCC utilizes the deep autoencoder for dimension reduction, and employs a variant of Gaussian mixture model to infer the cluster assignments. A mutual information loss is proposed to bridge the training of instances and features.

2018

DMNE coordinates multiple neural networks (one for each input network data) with a co-regularized loss function to manipulate cross-network relationships, which can be many-to-many, weighted and incomplete.

Most multi-instance learning (MIL) methods that study true positive instances ignore 1) the global similarity among positive instances and 2) that negative instances are non-i.i.d.. We propose a MTL method based on positive instance graph updating to address this issue.

This paper reviews the research progress of multi-instance learning (MTL), introduces different assumptions, and categories MTL methods into instance-level, bag-level, and embedded-space. Extensions and major applications in various areas are discussed at last.

2017

We propose a self-adaptive locality-sensitive hashing encoding method for multi-instance learning (MIL), which efficiently deals with large MIL problems.

We propose a metric learning method for multi-instance classification, aiming to find an instance-dependent metric by maximizing the relative distance on neighborhood level.

2016

We propose a positive instance detection method based on multiple instance learning, of which the core idea is that true positive instances should not only be similar to themselves globally but also different from negative instances robustly.

We propose a metric learning approach called multi-metrics classification machine. We establish an optimization problem for each class (each metric) to learn multiple metrics independently.

2015

We introduce the definition of clustering, the basic elements involved in clustering process, and categorize the clustering algorithms into the traditional ones and the modern ones. All the algorithms are discussed comprehensively.

Undergraduate

This paper proposes a support vector machine-based ensemble model to forecast crude oil price based on VECM and stochastic time effective pattern modelling and recognition system (STEPMRS).

This paper presents an integrated model to forecast crude oil prices, where pattern modelling & recognition system is used to model the price trend and error correction model is offered to forecast errors. A neural network layer is employed to integrate the results.

• Column Editor:
  • ACM SIGAI Newsletter

• Academic Committee Member:
  • MLNLP

• Conference/Workshop Chair:
  • The First Workshop on DL-Hardware Co-Design for AI Acceleration @ AAAI2023
  • International Workshop on Resource-Efficient Learning for Knowledge Discovery (RelKD'23) @ KDD2023
  • The First Conference on Machine Learning Algorithms & Natural Language Processing (MLNLP'22)

• Session Chair:
  • Research Track of KDD'22
  • ADS Track of KDD'22

• Senior Program Committee Member:
  • IJCAI'21, AAAI'23

• Program Committee Member:
  • ICLR'21, 22, 23
  • ICML'21, 22
  • NeurIPS'20, 21, 22
  • AAAI'20, 21, 22
  • ISQED'23
  • KDD'20, 21, 22
  • ACL Rolling Review'22
  • LoG'22
  • IJCAI'20, 22
  • NAACL'21
  • EMNLP'20, 21
  • COLING'22
  • WSDM'22, 23
  • SDM'22
  • EACL'21
  • ACM CIKM'20, 21, 22
  • AACL-IJCNLP'20, 22
  • IJCNN'18, 19, 20, 21

• Journal Reviewer:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • Communications of the ACM
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Knowledge and Data Engineering (TKDE)
  • IEEE Transactions on Cybernetics
  • Information Fusion
  • ACM Transactions on Knowledge Discovery from Data (TKDD)
  • Pattern Recognition
  • Neural Networks
  • Neurocomputing
  • ACM Transactions on Asian and Low-Resource Language Information Processing
  • IEEE Access
  • Neural Computation
  • Complexity
  • Soft Computing
  • Complex & Intelligent Systems
  • Multimedia Tools and Applications
  • Big Data

• External Conference Reviewer:
  • AAAI'18, 19, 20, KDD'18, 19, 20, 21, TheWebConf (WWW)'20, 21, 22, WSDM'20, 21, ICDM'18, 19, 21, SDM'18, 19, 20, 21, 22, ACM CIKM'18, 19, Big Data'18, IJCNN'16, 17, ITQM'16, 17

• Conference Volunteer:
  • The Annual Conference of NAACL-HLT, 2021
  • Backuping SDM Session Chairs, 2021
  • The 35th AAAI Conference on Artificial Intelligence, 2021
  • The 26th SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

• Instructor at NC State

  • CSC 791&591: Advanced Topics in Efficient Deep Learning
    Course Materials: Dive into Deep Learning

• Teaching Assistant at Penn State

  • SRA268 - Visual Analytics, Fall 2021
    Instructor: Prof. Mahir Akgun    Course Materials: Visual Analytics with Tableau
    (Responsible for teaching lab classes of 46 students)

  • SRA450 - Cybercrime and Cyberwar, Fall 2021
    Instructor: Prof. John Hodgson    Course Materials: Cybersecurity: What Everyone Needs to Know

  • DS/CMPSC 410 - Programming Models for Big Data, Spring 2021
    Instructor: Prof. John Yen    Course Materials: Learning Spark

  • SRA365 - Statistics for Security and Risk Analysis, Fall 2020
    Instructor: Dr. James Farrugia    Course Materials: Discovering Statistics Using R

  • DS402 - Introduction to Social Media Mining, Spring 2020
    Instructor: Prof. Suhang Wang    Course Materials: Social Media Mining: An Introduction

  • SRA365 - Statistics for Security and Risk Analysis, Spring 2019
    Instructor: Dr. Katherine Hamilton    Course Materials: Theoretical Foundations of Intermediate Statistics

  • IST210 - Organization of Data, Fall 2018
    Instructor: Prof. Xiang Zhang    Course Materials: Database Systems Concepts
    (The Award for Excellence in Teaching Support)

• Guest Lecturer

  • COSI 133A: Graph Mining
    Brandeis University, 2021 Fall
    

  • COSI 165B: Deep Learning
    Brandeis University, 2021 Spring
    

• Shaoyi Huang, Ph.D. at University of Connecticut
  Topic I: Sparse Neural Architecture Search
  Topic II: Few-shot Foundation Model Distillation
  

• Bowen Lei, Ph.D. at Texas A&M University
  Topic: Theoretical Foundations of Sparse Training
  

• Xiangxiang Gao, Ph.D. at Shanghai Jiao Tong University
  Topic: Theoretical Foundations of Sparse Training
  

• Shuren He, Ph.D. at Texas A&M University
  Topic: Theoretical Foundations of Sparse Training
  

• Shengze Xu, Undergraduate at Zhejiang University
  Topic: Theoretical Foundations of Sparse Neural Networks
  

• Shijian Wu, Master at Georgia Institute of Technology
  Topic: Theoretical Foundations of Sparse Neural Networks
  

• Zhenglun Kong, Ph.D. at Northeastern University
  Topic: Efficient Transformer Architecture Search
  

• Xukun Liu, Undergraduate at South University of Science and Technology of China
  Topic: Efficient Transformer Architecture Search
  

• Haoze Lv, Undergraduate at South University of Science and Technology of China
  Topic: Efficient Transformer Architecture Search
  

• Wei Zhang, Undergraduate at Renmin University of China
  (Now Ph.D. at City University of Hong Kong)
  Topic: Cost-Sensitive Multi-Instance Learning
  

• Jie Zhang, Master at Zhejiang University
  Topic: Efficient Data-centric AI
  

• Lei Zhang, Master at Zhejiang University
  Topic: Efficient Data-centric AI
  

• Xiang Pan, Master at New York University
  Topic: Efficient Data-centric AI
  

• Dongyao Zhu, Undergraduate at University of California San Diego
  Topic: Efficient Data-centric AI
  

• Shitian Zhang, Master at University of Chinese Academy of Sciences
  Topic: Adaptive Code Generation
  

• Jiasheng Gu, Master at University of Southern California
  Topic: Adaptive Code Generation
  

• Ziqing Wang, Undergraduate at Sun Yat-sen University
  Topic: Efficient Co-design AI
  

• Shuya Li, Master at Tsinghua University
  Topic: Efficient Intelligent Traffic Learning
  

• Shengkun Tang, Undergraduate at Wuhan University
  Topic: Efficient Multi-modal Learning
  

• Tianchi Zhang, Master at University of Michigan - Ann Arbor
  Topic: Efficient Multi-modal Learning
  

• Xuelin Kong, Master at National University of Singapore
  Topic: Efficient Multi-modal Learning
  

• Hongye Fu, Undergraduate at Zhejiang University
  Topic: Efficient Multi-modal Learning
  

• Chengyuan Liu, Ph.D. at NC State University
  Topic: Robust Generalized Model Compression
  

• Weizhi Gao, Master at University of Chinese Academy of Sciences
  Topic: Robust Generalized Model Compression
  

• Jianwei Li, Master at San Jose State University
  Topic: Robust Generalized Model Compression
  

• Yanbo Fang, Master at Rutgers University
  Topic: Robust Generalized Model Compression
  

• System and Method for Knowledge-Preserving Neural Network Pruning.
  Enxu Yan, Dongkuan Xu, and Zhibin Xiao.
  U.S. Patent. 11,200,497. Dec. 2021

• Bank-balanced-sparse Activation Feature Maps for Neural Network Models.
  Enxu Yan and Dongkuan Xu.
  U.S. Patent App. 17/038,557. Apr. 2022.

• Neural Network Pruning Method and System via Layerwise Analysis.
  Enxu Yan and Dongkuan Xu.
  U.S. Patent App. 17/107,046. Nov. 2020.

• Unsupervised Multivariate Time Series Trend Detection for Group Behavior Analysis.
  Wei Cheng, Haifeng Chen, Jingchao Ni, Dongkuan Xu, and Wenchao Yu.
  U.S. Patent App. 16/987,734. Mar. 2021.

• Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series.
  Wei Cheng, Haifeng Chen, Jingchao Ni, Dongkuan Xu, and Wenchao Yu.
  U.S. Patent App. 16/987,789. Mar. 2021.

• Adaptive Neural Networks for Node Classification in Dynamic Networks.
  Wei Cheng, Haifeng Chen, Wenchao Yu, and Dongkuan Xu.
  U.S. Patent App. 16/872,546. Nov. 2020.

• Spatio Temporal Gated Recurrent Unit.
  Wei Cheng, Haifeng Chen, and Dongkuan Xu.
  U.S. Patent App. 16/787,820. Aug. 2020.

• Automated Anomaly Precursor Detection.
  Wei Cheng, Dongkuan Xu, Haifeng Chen, and Masanao Natsumeda.
  U.S. Patent App. 16/520,632. Feb. 2020.

• Parameter Efficiency: Democratizing AI at Scale (Slides)
  Waltham, MA, USA, Dec. 2021.
  Brandeis University.

• Chasing Efficiency of Pre-trained Language Models
  Redmond, Washington, USA, Jun. 2021.
  Microsoft Research Lab.

• BERT Pruning: Structural vs. Sparse (Slides)
  Waltham, MA, USA, Apr. 2021.
  Brandeis University.

• BERT, Compression and Applications (Slides)
  Mountain View, USA, Apr. 2021.
  Xpeng Motors.

• BERT Architecture and Computation Analysis (Slides)
  Los Altos, USA, May. 2020.
  Moffett.AI.

• Learning Trends in Multivariate Time Series (Slides)
  New York, USA, Feb. 2020.
  AAAI 2020.

• Node Classification in Dynamic Networks (Slides)
  Beijing, China, Nov. 2019.
  ICDM 2019.

• Anomaly Precursor Detection via Deep Multi-Instance RNN (Slides)
  Princeton, USA, May. 2019.
  NEC Laboratories America.

• Deep Co-Clustering (Slides)
  Calgary, Canada, May 2019.
  SDM 2019.

• Efficient Multiple Instance Learning (Slides)
  Princeton, USA, May. 2018.
  NEC Laboratories America.

• Doctor of Philosophy (Ph.D.)
  • College of IST Award for Excellence in Teaching Support (top 2), 2019
  • Third place winner (Eng.) in the 37rd annual PSU Graduate Exhibition (News), 2022
  • NAACL Scholarship, 2021
  • SIAM Student Travel Award, 2021
  • IST Travel Awards, Spring 2021, Fall 2021
  • College of IST Award for Excellence in Teaching Support, Finalist, 2021
  • KDD Student Registration Award, 2020
  • AAAI Student Scholarship, 2020
  • IST Travel Award, Spring 2020
  • IST Travel Award, Spring 2019

• Master of Science (M.S.)
  • ITQM Best Paper, 2016
  • President’s Fellowship of Chinese Academy of Sciences (the most prestigious award), 2016
  • National Graduate Scholarship, China (2% in university), 2016
  • Graduate Student Academic Scholarship, 2017
  • Graduate Student Academic Scholarship, 2016
  • Graduate Student Academic Scholarship, 2015

• Bachelor of Engineering (B.E.)
  • First-class Scholarship of Sashixuan Elite Fund, China (5% in university), 2014
  • Kwang-hua Scholarship of RUC, China, 2014
  • Second-class Scholarship of Excellent Student Cadre, 2014
  • Meritorious Winner in Mathematical Contest in Modeling, 2013
  • First-class Scholarship of Social Work and Volunteer Service of RUC, 2013

• ACM (Association for Computing Machinery) Student Membership, 2021-Present
  
• ACL (Association for Computational Linguistics) Membership, 2021-Present
  
• AAAI (Association for the Advancement of Artificial Intelligence) Student Membership, 2019-Present
  
• SIAM (Society of Industrial and Applied Mathematics) CAS Student Member, 2016-Present
  
• President of Youth Volunteers Association of School of Information of RUC, 2012-2013
  
• Volunteer of Beijing Volunteer Service Federation (BVF), 2012-Present
  
• Leader of National Undergraduate Training Programs for Innovation and Entrepreneurship, 2011-2012

*Last updated on 03/21/2023*
This guy makes a nice webpage