Hello! I am an Assistant Professor at NC State CS , leading the NCSU Generative Intelligent Computing Lab (web under construction) and working on artificial intelligence, 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 &nbsp/&nbsp CV (July 2023) &nbsp/&nbsp Twitter &nbsp/&nbsp Google Scholar &nbsp/&nbsp LinkedIn &nbsp&nbsp I'm looking for multiple PhDs / interns to work in Autonomous, Reliable & Efficient Generative AI (一亩三分地 1, 2, 3) . 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! &nbsp&nbsp (I've received an amazingly large number of applications. Super thanks for everyone's interest! Interviews are in progress. Good luck~) &nbsp&nbsp Research My research is fundamentally grounded in exploring and advancing Landed Generative AI (LaGAI) , with particular emphasis on studying the autonomy of intelligent agents (tools, chains, tasks) , reasoning reliability (alignment, uncertainty, adaptability, robustness) , and resource efficiency (data utilization, computation, parameter optimization) in Generative AI (ChatGPT, GPT-X, Diffusion Models) Systems . My research group provides full-stack LaGAI solutions, ranging from theoretical optimization methods and data-centric strategies to the development of efficient deep learning techniques and the co-design of algorithms and hardware. My long-term research goal is to liberate AI productivity and democratize its application to serve a broader range of populations and real-world applications, equally, sustainably, and responsibly. Welcomed topics include: data-efficient learning, algorithm/model-efficient learning, system/hardward-efficient learning, etc Submission Deadline: June 07, 2023 (link)

07/2023: The First Open-Source ALM Platform for Collective Growth , Gentopia (link), is available! Join us!!

07/2023: One paper was accepted to ICCV'23 !

07/2023: One paper was accepted to CDC'23 !

07/2023: Our ChatGPT Education Workshop is available (co-organized with Dr. Tiffany Barnes )!

07/2022: Invited to give a talk at Microsoft Research Asia .

06/2023: Feel free to check out our ALM work, ReWOO (GitHub) (中文解读 1, 2, 3)

06/2023: Invited to serve as a Senior PC member of AAAI'24.

05/2023: One paper was accepted to KDD'23 !

05/2023: One paper was accepted to ACL'23 !

04/2023: Our work, E-App , was accepted to ICCCN'23 ! See u in Honolulu!

04/2023: One paper was accepted to ICAIBD'23 ! Congrats to our undergrad, Zihan!

03/2023: Our work, Acc.DD (paper) , was selected as a Highlight (2.5%) of CVPR'23 !

03/2023: Will co-chair RelKD'23: Resource-Efficient Learning for Knowledge Discovery Workshop @ KDD'23 .

02/2023: Two papers on accelerating data/model learning were accepted to CVPR'23 . Stay tuned ;-)

02/2023: Two papers on dynamic training were accepted to DAC'23 . See u in San Francisco!

01/2023: Our work, Calibrated Rigged Lottery , was accepted to ICLR'23 .

01/2023: Our work, Efficient Informed Proposals for Discrete Distributions, was accepted to AISTATS'23 .

01/2023: Invited to give a talk at Rutgers EFficient AI (REFAI) Seminar on Feb 16, 2023.

01/2023: Invited to give a talk at 2022 Annual Summit for High Tech High Growth Companies on March 11, 2023.

12/2022: Invited to serve as a journal reviewer for TPAMI and Communications of the ACM .

11/2022: Invited to serve as the PC Chair for MLNLP 2022. Super welcome to attend (online & free)!

11/2022: Two papers were accepted to AAAI'23 . See you in DC in February!

10/2022: Invited to serve as a TPC member for ISQED'23 .

09/2022: Will chair The First Workshop on DeepLearning-Hardware Co-Design for AI Acceleration with AAAI'23 !

09/2022: Our work, AutoDistil (paper) , was accepted to NeurIPS'22 . See u in New Orleans!

09/2022: Invited to give a talk at the CIS Department of the University of Macau .

07/2022: Will chair a Research session ( Deep Learning: New Architectures and Models ) and an Applied Data Science session ( Scalable, Distributed Systems & Trustable AI ) of KDD'22. Super welcome!

07/2022: Will be teachinng CSC 791 Advanced Topics in Efficient Deep Learning at NC State this fall. Feel free to attend!

07/2022: One paper, S4: a High-sparsity, High-performance AI Accelerator (paper) , was accepted to SNN'22 !

07/2022: Invited to serve as a (Senior) PC member for AAAI'23. and ICLR'23.

06/2022: Invited to serve as a Column Editor for ACM SIGAI Newsletter.

06/2022: Invited to give a talk at Pinterest (Pinterest Machine Learning Lunch) on August 18, 2022.

06/2022: Invited to give a talk at 中科院深圳先进技术研究院 on June 27, 2022.

06/2022: Invited to serve as a PC member for WSDM'23 , LoG'22 , and AACL-IJCNLP'22 .

05/2022: Invited to serve as a PC member for COLING'22 and a reviewer for the journal TNNLS .

05/2022: Invited to give a talk at Amazon Search (A9) on May 20, 2022. ("5.20" >.< "我爱你")

04/2022: Invited to give a talk at 将门创投 on May 24, 2022. Welcome!

04/2022: Invited to give a talk at Vanderbilt University 's Machine Learning Lunch Seminar on May 09, 2022.

04/2022: Invited to give a talk at Renmin University of China in May 2022.

04/2022: Invited to give a talk at Shenzhen University in May 2022.

04/2022: A new US patent application: Bank-balanced-sparse Activation for Deep NN Models.

04/2022: Invited to give a talk at University of Connecticut on April 27, 2022.

04/2022: Invited to give a talk at UCAS (中国科学院大学) on April 25, 2022.

04/2022: Invited to give a talk at New York Institute of Technology 's Research Seminar Series.

04/2022: Organizing MLNLP Community's 6th Academic Seminar.

04/2022: Third place winner (Eng.) in the 37rd annual PSU Graduate Exhibition ( News ).

03/2022: Invited to serve as a PC member for NeurIPS'22 .

02/2022: One paper, Sparse Progressive Distillation (code, paper) , was accepted to ACL'22 !

02/2022: Invited to serve as a PC member for CIKM'22 .

12/2021: Thanks to MLNLP (机器学习与自然语言处理) for reporting our work SparseBERT.

12/2021: Code released for SparseBERT (NAACL'21) (code , paper) ! Feel free to use it!

12/2021: Invited to serve as a PC member for ICML'22 .

12/2021: Invited to give a talk "Parameter Efficiency: Democratizing AI at Scale" at Brandeis University (slides) .

11/2021: Invited to serve as a PC member for KDD'22 (both Research and Applied Science Tracks).

10/2021: Our ML&NLP academic community is officially launched (>500k followers) .

10/2021: Received IST Fall 2021 Travel Award.

09/2021: Our work, InfoGCL , was accepted to NeurIPS'21 !

08/2021: Invited to serve as PC member for AAAI'22 , ACL Rolling Review'22. , SDM'22 .

07/2021: Received complimentary ACM student membership. Thanks you ACM!.

06/2021: Invited to serve as a PC member for ICLR'22 , WSDM'22 , IJCAI-ECAI'22 .

05/2021: Received NAACL 2021 Scholarship.

05/2021: One paper was accepted to ACL'21 !

05/2021: Excited to join Microsoft Research as a research intern working on neural architecture search!

04/2021: Gave a talk titled "BERT Pruning: Structural vs. Sparse" at Brandeis University (slides) .

04/2021: Gave a talk titled "BERT, Compression and Applications" at Xpeng Motors (小鹏汽车) (slides) .

03/2021: My application to SDM'21 Doctoral Forum has been accepted. See you in May!

03/2021: Received a SIAM Student Travel Award to attend SDM'21 .

03/2021: Our work, SparseBERT , was accepted to NAACL'21 ! Along with three U.S. patent applications !

03/2021: Invited to serve as a PC member for NeurIPS'21 , EMNLP'21 , CIKM'21 .

03/2021: Received IST Spring 2021 Travel Award.

12/2020: One paper was accepted to SDM'21 . See you virtually in April!

12/2020: Invited to serve as a Senior PC member for IJCAI'21 .

12/2020: Four papers were accepted to AAAI'21 . See you virtually in February!

12/2020: Invited to serve as a PC member for ICML'21 , KDD'21 , NAACL'21 , IJCNN'21 .

09/2020: Our work, PGExplainer , was accepted to NeurIPS'20 .

08/2020: Invited to serve as a PC member for AAAI'21 , EACL'21 , a journal reviewer for Information Fusion .

08/2020: Received KDD 2020 Student Registration Award.

06/2020: Invited to serve as a reviewer for NeurIPS'20 .

05/2020: Happy to join Moffett AI as an intern research scientist.

04/2020: One paper was accepted to SIGIR'20 .

03/2020: Invited to serve as a PC member for EMNLP'20 , KDD'20 , CIKM'20 , AACL-IJCNLP'20 .

02/2020: Received IST Spring 2020 Travel Award.

12/2019: Invited to serve as a PC member for IJCAI'20 , IJCNN'20 .

12/2019: Received AAAI 2020 Student Scholarship.

11/2019: Two papers were accepted to AAAI'20 . See you in the Big Apple!

08/2019: Invited to serve as a PC member for AAAI'20 .

08/2019: One paper was accepted to ICDM'19 .

05/2019: One paper was accepted to IJCAI'19 .

05/2019: Happy to join NEC Labs America as a research intern.

03/2019: Received IST Spring 2019 Travel Award.

01/2019: Grateful to receive The Award for Excellence in Teaching, IST ( News ).

01/2019: Invited to serve as a PC member for IJCNN'19 .

12/2018: One paper was accepted to SDM'19 . See you in Calgary!

05/2018: Started working at NEC Labs America as a research intern.

11/2017: Invited to serve as a PC member for IJCNN'18 .

D. Zhu , B. Lei, J. Zhang, Y. Fang, Y. Xie, R. Zhang, D. Xu [ICCV 2023] International Conference on Computer Vision PDF (to appear)

We show that distilled data lead to not-calibratable networks due to the loss of information that is semantically meaningful but unrelated to classification tasks. We propose Masked Temperature Scaling & Distillation Training to mitigate these limitations while maintaining the efficiency.

S. Li , H. Mei, J. Li, H. Wei, D. Xu [CDC 2023] The 62nd IEEE Conference on Decision and Control PDF (to appear)

We introduce EfficientLight, an RL-based traffic signal control method that balances model size and performance. In multi-intersection scenarios, our method outperforms all baseline methods with the lowest #paras and the smallest computational cost compared to other RL-based methods.

L. Zhang* , J. Zhang*, B. Lei, S. Mukherjee, X.Pan, B.Zhao, C. Ding, Y. Li, D. Xu [CVPR 2023] The IEEE/CVF Conference on Computer Vision and Pattern Recognition Highlight Paper (2.5%)

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.

You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model S. Tang , Y. Wang, Z. Kong, T. Zhang, Y. Li, C. Ding, Y. Wang, Y. Liang, D. Xu [CVPR 2023] The IEEE/CVF Conference on Computer Vision and Pattern Recognition

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.

Labels Are Not Necessary: Assessing Peer-Review Helpfulness Using Domain Adaptation Based on Self-Training C. Liu , D. Doshi, M. Bhargava, R. Shang, J. Cui, D. Xu , E. Gehringer [BEA 2023] The 18th Workshop on Innovative Use of NLP for Building Educational Applications

This study first highlights the pedagogical significance of predicting useful comments in mutual assessment to promote student learning, and then considers the challenges of collecting labeled data to build reliable predictive models. We explore a solution that reduces the need to collect labeled data via domain adaptation.

L. Wu, B. Lei, D. Xu , D. Zhou [KDD 2023] The 29th SIGKDD Conference on Knowledge Discovery and Data Mining

How can we quantify the uncertainty in the learning process and enable reliable rare category analysis? We propose an end-to-end method that jointly learns the characterizations of rare categories and calibrates the confidence.

Q. Zhang, S. Chen, D. Xu , Q. Cao, X, Chen, T. Cohn, M. Fang [ACL 2023] The 61th Annual Meeting of the Association for Computational Linguistics

We provide a survey of recent advances in the efficiency of ODQA models . We walk through the ODQA models and conclude the core techniques on efficiency. Quantitative analysis on memory cost, processing speed, accuracy and overall comparison are given.

B. Lei , R. Zhang, D. Xu , B. K. Mallick [ICLR 2023] The 11th International Conference on Learning Representations

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.

E-App: Adaptive mmWave Access Point Planning with Environmental Awareness in Wireless LANs Y. Liu, M. Chen, D. Xu , Z. Yang, S. Zhao [ICCCN 2023] The 32nd International Conference on Computer Communications and Networks

To enable ultra-high throughputs while addressing the potential blockage problem, maintaining an adaptive access point (AP) planning is critical to mmWave networking. We develop an adaptive AP planning (E-app) approach that can accurately sense the environment dynamics, reconstruct the obstacle map, and then predict the placements of mmWave APs adaptively.

Exploring the Augmented Large Language Model with Mathematical tools in Personalized and Efficient Education Zihan Dong ( Undergrad at NC State ), D. Xu [ICAIBD 2023] The 6th International Conference on Artificial Intelligence and Big Data

We propose to augment ChatGPT with math performance assessments , which facilitate the creation of customized learning experiences based on the needs of each student. This study explores how ChatGPT personalizes the learning experience, how it can be augmented with math and physical performance, and how educators can ensure that the LLM algorithm is unbiased.

S. Huang , B. Lei, D. Xu , H. Peng, Y. Sun, M. Xie, C. Ding [DAC 2023] The 60th Design Automation Conference

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.

S. Huang , H. Fang, K. Mahmood, B. Lei, N. Xu, B. Lei, Y. Sun, D. Xu , W. Wen, C. Ding [DAC 2023] The 60th Design Automation Conference

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.

Efficient Informed Proposals for Discrete Distributions via Newton’s Series Approximation Y. Xiang* , D. Zhu* , B. Lei, D. Xu , R. Zhang [AISTATS 2023] The 26th International Conference on Artificial Intelligence and Statistics

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.

Auto-CAM: Label-Free Earth Observation Imagery Composition and Masking Using Spatio-Temporal Dynamics Y. Xie, Z. Li, H. Bao, X. Jia, D. Xu , X. Zhou, S. Skakun [AAAI 2023] The 37th AAAI International Conference on Artificial Intelligence

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 .

D. Luo, W. Cheng, Y. Wang, D. Xu , J. Ni, W. Yu, X. Zhang, Y. Liu, Y. Chen, H. Chen, X. Zhang [AAAI 2023] The 37th AAAI International Conference on Artificial Intelligence

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

AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models D. Xu , S. Mukherjee, X. Liu, D. Dey, W. Wang, X. Zhang, A. H. Awadallah, J. Gao [NeurIPS 2022] The 36th Conference on Neural Information Processing Systems PDF / Code / Supp / Slides

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.

PDF / Code / Supp / Slides

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 .

S. Huang, N. Liu, Y. Liang, H. Peng, H. Li, D. Xu , M. Xie, C. Ding [ISQED 2022] The 23rd IEEE International Society for Quality Electronic Design Video / PDF / Code / Supp / Slides

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.

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm S. Huang*, D. Xu* , I. E. Yen, S. Chang, B. Li, C. Ding, et al. [ACL 2022] The 60th Annual Meeting of the Association for Computational Linguistics PDF / Code / Supp / Slides

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.

D. Xu , W. Cheng, D. Luo, H. Chen, X. Zhang [NeurIPS 2021] The 35th Conference on Neural Information Processing Systems PDF / Code / Supp / Slides

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.

Dongkuan Xu , Ian En-Hsu Yen, Jinxi Zhao, Zhibin Xiao [NAACL-HLT 2021] 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics PDF / Code / Supp / Slides

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.

Xin Dong, Yaxin Zhu, Zuohui Fu, Dongkuan Xu , Gerard de Melo [ACL 2021] The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing PDF / Code / Supp / Slides

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.

Deep Multi-Instance Contrastive Learning with Dual Attention for Anomaly Precursor Detection Dongkuan Xu , Wei Cheng, Jingchao Ni, Dongsheng Luo, Masanao Natsumeda, Dongjin Song, Bo Zong, Haifeng Chen, Xiang Zhang [SDM 2021] The 21th SIAM International Conference on Data Mining PDF / Code / Supp / Slides

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.

Dongkuan Xu , Wei Cheng, Xin Dong, Bo Zong, Wenchao Yu, Jingchao Ni, Dongjin Song, Xuchao Zhang, Haifeng Chen, Xiang Zhang [AAAI 2021] The 35th AAAI International Conference on Artificial Intelligence PDF / Code / Supp / Slides

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.

Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling Dongkuan Xu , Junjie Liang, Wei Cheng, Hua Wei, Haifeng Chen, Xiang Zhang [AAAI 2021] The 35th AAAI International Conference on Artificial Intelligence PDF / Code / Supp / Slides

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

Hua Wei, Dongkuan Xu , Junjie Liang, Zhenhui Li [AAAI 2021] The 35th AAAI International Conference on Artificial Intelligence PDF / Code / Supp / Slides

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

Junjie Liang, Yanting Wu, Dongkuan Xu , Vasant Honavar [AAAI 2021] The 35th AAAI International Conference on Artificial Intelligence PDF / Code / Supp / Slides

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

Dongsheng Luo, Wei Cheng, Dongkuan Xu , Wenchao Yu, Bo Zong, Haifeng Chen, Xiang Zhang [NeurIPS 2020] The 34th Conference on Neural Information Processing Systems PDF / Code / Supp / Slides

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

Xin Dong, Yaxin Zhu, Yupeng Zhang, Zuohui Fu, Dongkuan Xu , Sen Yang, Gerard de Melo [SIGIR 2020] The 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval PDF / Code / Supp / Slides

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.

Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series Dongkuan Xu , Wei Cheng, Bo Zong, Dongjin Song, Jingchao Ni, Wenchao Yu, Yanchi Liu, Haifeng Chen, Xiang Zhang [AAAI 2020] The 34th AAAI International Conference on Artificial Intelligence PDF / Code / Poster / Slides

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.

Junjie Liang, Dongkuan Xu , Yiwei Sun, Vasant Honavar [AAAI 2020] The 34th AAAI International Conference on Artificial Intelligence PDF / Code / Supp

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.

Dongkuan Xu , Wei Cheng, Dongsheng Luo, Yameng Gu, Xiao Liu, Jingchao Ni, Bo Zong, Haifeng Chen, Xiang Zhang [ICDM 2019] The 19th IEEE International Conference on Data Mining PDF / Slides

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.

Dongkuan Xu , Wei Cheng, Dongsheng Luo, Xiao Liu, Xiang Zhang [IJCAI 2019] The 29th International Joint Conference on Artificial Intelligence PDF / Code / Poster / Slides

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.

Dongkuan Xu , Wei Cheng, Dongsheng Luo, Xiao Liu, Xiang Zhang [SDM 2019] The 19th SIAM International Conference on Data Mining PDF / Code / Supp / Poster / Slides

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.

Jingchao Ni, Shiyu Chang, Xiao Liu, Wei Cheng, Haifeng Chen, Dongkuan Xu and Xiang Zhang [WWW 2018] The 27th International Conference on World Wide Web PDF / Code

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.

Dongkuan Xu , Jia Wu, Dewei Li, Yingjie Tian, Xingquan Zhu, Xindong Wu Pattern Recognition , 2017

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

Dewei Li, Dongkuan Xu , Jingjing Tang, Yingjie Tian [IJCNN 2017] The 30th IEEE International Joint Conference on Neural Networks

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.

Dewei Li, Wei Zhang, Dongkuan Xu , Yingjie Tian [ITQM 2016] The 4th International Conference on Information Technology and Quantitative Management (Best Paper Award)

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.

A Support Vector Machine-based Ensemble Prediction for Crude Oil Price with VECM and STEPMRS Dongkuan Xu , Tianjia Chen, Wei Xu International Journal of Global Energy Issues , 2015

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).

Dongkuan Xu , Yi Zhang, Cheng Cheng, Wei Xu, Likuan Zhang [HICSS 2014] The 47th Hawaii International Conference on System Science

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.

International Workshop on Resource-Efficient Learning for Knowledge Discovery (RelKD'23) @ KDD2023 The First Conference on Machine Learning Algorithms & Natural Language Processing (MLNLP'22) SRA268 - Visual Analytics, Fall 2021
Instructor: Prof. Mahir Akgun &nbsp&nbsp Course Materials: Visual Analytics with Tableau
(Responsible for teaching lab classes of 46 students) SRA450 - Cybercrime and Cyberwar, Fall 2021
Instructor: Prof. John Hodgson &nbsp&nbsp Course Materials: Cybersecurity: What Everyone Needs to Know DS/CMPSC 410 - Programming Models for Big Data, Spring 2021
Instructor: Prof. John Yen &nbsp&nbsp Course Materials: Learning Spark SRA365 - Statistics for Security and Risk Analysis, Fall 2020
Instructor: Dr. James Farrugia &nbsp&nbsp Course Materials: Discovering Statistics Using R DS402 - Introduction to Social Media Mining, Spring 2020
Instructor: Prof. Suhang Wang &nbsp&nbsp Course Materials: Social Media Mining: An Introduction SRA365 - Statistics for Security and Risk Analysis, Spring 2019
Instructor: Dr. Katherine Hamilton &nbsp&nbsp Course Materials: Theoretical Foundations of Intermediate Statistics IST210 - Organization of Data, Fall 2018
Instructor: Prof. Xiang Zhang &nbsp&nbsp Course Materials: Database Systems Concepts
(The Award for Excellence in Teaching Support) Bowen Lei , Ph.D. at Texas A&M University
Topic i: Theoretical Foundations of Sparse Training
Topic ii: Reliable Large Generative Model
Dongyao Zhu , Undergraduate at University of California San Diego
Topic: Reliable Large Generative Model
Shaoyi Huang , Ph.D. at University of Connecticut
Topic i: Large-scale Language Model Compression
Topic ii: Algorithm-hardware Co-design Efficient Training
Zhiyuan Peng , Ph.D. at The Chinese University of Hong Kong
Topic: Augmented Large Language Model
Binfeng Xu , Master at New York University
Topic: Augmented Large Language Model
Jiasheng Gu , Master at University of Southern California
Topic: Augmented Large Language Model
Yuhan Li , Master at Tianjin University
Topic: Augmented Large Language Model
Boyan Li , Undergraduate at South University of Science and Technology of China
Topic: Augmented Large Language Model
Hanyang Lin , Master at University of Illinois Urbana-Champaign
Topic: Autonomous Tool Learning
Longxuan Yu , Master at University of California San Diego
Topic: Autonomous Tool Learning
Zihan Dong , Undergraduate at NC State University
Topic: Large Language Model in Education
Zifan Zhang, Master at Cornell University
Topic: Large Language Model in Education
Zhengdong Zhang, Master at Georgia Tech
Topic: Large Language Model in Education
Peiyan Dong , Ph.D. at Northeastern University
Topic: Algorithm-hardware Co-design Efficient Transformer
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 i: Hyperparameter & Architecture Aptimization
Topic ii: Augmented Large Language Model
Haoze Lv, Undergraduate at South University of Science and Technology of China
Topic: Hyperparameter & Architecture Aptimization
Zeyu Han, Undergraduate at Sichuan University
Topic: Efficient Data-centric AI
Xiang Pan , Master at New York University
Topic: Efficient Data-centric AI
Shuya Li, Master at Tsinghua University
Topic: Efficient Intelligent Traffic Learning
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. Testing Accuracy is Not All You Need: Less Training Cost & More Testing Reliability
Rutgers University, New Brunswick, USA, Feb 2023.
Rutgers Efficient AI (REFAI) Seminar ( link ). 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.

IEEE (Institute of Electrical and Electronics Engineers) Membership, 2023-Present

ACL (Association for Computational Linguistics) Membership, 2021-Present

AAAI (Association for the Advancement of Artificial Intelligence) Student Membership, 2019-2022

SIAM (Society of Industrial and Applied Mathematics) CAS Student Member, 2016-2022

President of Youth Volunteers Association of School of Information of RUC, 2012-2013

Volunteer of Beijing Volunteer Service Federation (BVF), 2012-2014

Leader of National Undergraduate Training Programs for Innovation and Entrepreneurship, 2011-2012