Yaqing Wang

Research Scientist
Google Deepmind
Company Email: yaqingwang # google "." com
Personal Email: yaqingwang90 # gmail "." com
       

Short Biography: I am a Research Scientist at Google Deepmind. Prior to that, I received my Ph.D. degree in Electrical and Computer Engineering from Purdue University under the supervision of Prof. Jing Gao. I received my Master of Science degree in Statistics from University of California, San Diego and my Bachelor of Science degree in Mathematics from Shandong University.

My research interests lie at the data-centric AI, natural language processing, and multimodal content understanding. The primary goal of my research is to develop universal, efficient, reliable and elastic models. In particular, my research projects are:

  • Efficient Learning: The ever-growing resource consumption of neural networks generates large carbonfootprint, brings difficulty for academics to engage in research and stops emerging economies from enjoying growing AI benefits. To address those issues, we devote our efforts to develop efficient algorithms to achieve the better resource productivity regarding data annotation, model training and deployment costs.
  • Elastic Learning: One of most important challenges when applying trained models into real-world applications is domain shift, which refers to changes in the data distribution between training dataset, and a dataset models encounter when deployed. To address the domain shift challenge, we develop a series of domain adaption algorithms for applications in various areas.
  • Knowledge Discovery: Lots of human knowledge is encoded in text. To make knowledge resources more findable, accessible, interoperable, and reusable (FAIR), we focus on extracting strcutured knowledge from massive collection of text.
  • News!

    • [2022-11] One paper on fairness is accepted by AAAI 2023.
    • [2022-10] One paper on model adaptation is accepted by EMNLP 2022.
    • [2022-7] Serve as SPC of AAAI 2023.
    • [2022-01] One co-authored paper on multilingual NLU in federated learning is accepted by WWW 2022. Congrats to Haoyu.
    • [2021-10] Invite to serve as PC/Reviewer for ICLR 2022, ACL Rolling Review 2022.
    • [2021-9] Two papers are accpted at EMNLP 21.
    • [2021-8] Presented our MetaST and MetaFEND papers at KDD 21.
    • [2021-8] Two co-authored papers (lightweight embedding and unstructured text retrieval) are accepted by CIKM 2021.
    • [2021-5] Two papers (few-shot learning and fake news detection) are accepted by KDD 2021.
    • [2021-5] Return to Microsoft Research for an internship.
    • [2021-4] Serve as PC of EMNLP 2021, NeurIPS 2021.
    • [2021-1] One co-authored paper on Health risk prediction is accepted by WWW 2021.

    • Outlier Weighted Layerwise Sparsity (OWL): A Missing Secret Sauce for LLMs to High Sparsity [Paper]
      Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Mykola Pechenizkiy, Yi Liang, Zhangyang Wang, Shiwei Liu.
    • Teach LLMs to Personalize--An Approach inspired by Writing Education [Paper]
      Cheng Li, Mingyang Zhang, Qiaozhu Mei, Yaqing Wang, Spurthi Amba Hombaiah, Yi Liang, Michael Bendersky.
    • DeeDiff: Dynamic Uncertainty-Aware Early Exiting for Accelerating Diffusion Model Generation [Paper]
      Shengkun Tang, Yaqing Wang, Caiwen Ding, Yi Liang, Yao Li, Dongkuan Xu.
    • Decomposed Adversarial Learned Inference [Paper]
      Hanbo Li*, Yaqing Wang*(* equal contribution), Changyou Chen, Jing Gao.
    • FedSemi: An Adaptive Federated Semi-Supervised Learning Framework [Paper]
      Zewei Long, Liwei Che, Yaqing Wang, Muchao Ye, Junyu Luo, Jinze Wu, Houping Xiao, Fenglong Ma.
    • MedLane: A Benchmark Dataset for Understandable Medical Language Translation [Paper]
      Junyu Luo, Zifei Zheng, Hanzhong Ye, Muchao Ye, Yaqing Wang, Quanzeng You, Cao Xiao, Fenglong Ma.

    2023

    • Hierarchical Pretraining on Multimodal Electronic Health Records [To Appear]
      Xiaochen Wang, Junyu Luo, Jiaqi Wang, Ziyi Yin, Suhan Cui, Yuan Zhong, Yaqing Wang and Fenglong Ma.
      2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, Dec. 2023.

    • HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference [To Appear]
      Haoyu Wang, Yaqing Wang, Tianci Liu, Tuo Zhao, Jing Gao.
      2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), Singapore, Dec. 2023.

    • Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding [To Appear]
      Haoyu Wang, Yaqing Wang, Huaxiu Yao, Jing Gao.
      2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), Singapore, Dec. 2023.

    • LightToken: a Task and Model-agnostic Lightweight Token Embedding Framework for Pre-trained Language Models [To Appear]
      Haoyu Wang, Ruirui Li, Haoming Jiang, Zhengyang Wang, Xianfeng Tang, Bin Bi, Monica Cheng, Bing Yin, Yaqing Wang, Tuo Zhao, Jing Gao.
      29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Long Beach, California, United States, Aug. 2023.

    • Macular: a Multi-Task Adversarial Framework for Cross-Lingual Natural Language Understanding [[To Appear]
      Haoyu Wang, Yaqing Wang, Feijie Wu, Hongfei Xue, Jing Gao.
      29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Long Beach, California, United States, Aug. 2023.

    • You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model [Arxiv]
      Shengkun Tang, Yaqing Wang, Zhenglun Kong, Tianchi Zhang, Yao Li, Caiwen Ding, Yanzhi Wang, Yi Liang, Dongkuan Xu.
      The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Vancouver, Canada, Jun. 2023.

    • SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification [Arxiv]
      Tianci Liu, Haoyu Wang Yaqing Wang, Xiaoqian Wang, Lu Su, Jing Gao.
      Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI). Washington D.C., Feb 2023

      Distinguished Paper Award

    2022

    • AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning [Arxiv] [Code]
      Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao.
      The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP). Abu Dhabi, Dec 2022

    • LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners [Arxiv] [Code]
      Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao.
      Findings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Findings). Seattle, July 2022

    • FedKC: Federated Knowledge Composition for Multilingual Natural Language Understanding [Paper]
      Haoyu Wang, Handong Zhao, Yaqing Wang, Tong Yu, Jiuxiang Gu, and Jing Gao.
      The Web Conference (WWW), online, April 2022

    2021

    • Meta Self-training for Few-shot Neural Seuqence Labeling [Paper] [Code]
      Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao and Ahmed Hassan Awadallah.
      Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), August 14-18, 2021, Singapore
    • Multimodal Emergent Fake News Detection via Meta Neural Process Networks [Paper]
      Yaqing Wang, Fenglong Ma, Haoyu Wang, Kishlay Jha and Jing Gao.
      Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), August 14-18, 2021, Singapore
    • Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework [Paper]
      Yaqing Wang, Haoda Chu, Chao Zhang and Jing Gao.
      Findings of the 2021 Conference on Empirical Methods in Natural Language Processing, (EMNLP Findings), 7th-11th November 2021, Online and in the Barceló Bávaro Convention Centre, Punta Cana, Dominican Republic
    • Knowledge-Guided Paraphrase Identification [Paper]
      Haoyu Wang, Fenglong Ma, Yaqing Wang and Jing Gao.
      Findings of the 2021 Conference on Empirical Methods in Natural Language Processing, (EMNLP Findings), 7th-11th November 2021, Online and in the Barceló Bávaro Convention Centre, Punta Cana, Dominican Republic
    • A Lightweight Knowledge Graph Embedding Framework for Efficient Inference and Storage [Paper]
      Haoyu Wang, Yaqing Wang, Defu Lian and Jing Gao.
      Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM), 1-5 November 2021, Online, Hosted in Gold Coast, Queensland, Australia.
    • MedRetriever: Target-Driven Interpretable Health Risk Prediction via Retrieving Unstructured Medical Text [Paper]
      Muchao Ye, Suhan Cui, Yaqing Wang, Junyu Luo, Cao Xiao and Fenglong Ma.
      Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM), 1-5 November 2021, Online, Hosted in Gold Coast, Queensland, Australia.
    • MedPath: Augmenting Health Risk Prediction via Medical Knowledge Paths [Paper]
      Muchao Ye, Suhan Cui, Yaqing Wang, Junyu Luo, Cao Xiao and Fenglong Ma.
      Proceedings of the 30th The Web Conference (WWW), Ljubljana, Slovenia, April 19-23, 2021.
    • FedTriNet: A Pseudo Labeling Method with Three Players for Federated Semi-supervised Learning [Paper]
      Liwei Che, Zewei Long, Jiaqi Wang, Yaqing Wang, Houping Xiao, Fenglong Ma.
      Proceedings of the 2021 IEEE International Conference on Big Data (BigData),December 15-18 2021, Online.
    • Fair Classification Under Strict Unawareness [Paper]
      Haoyu Wang, Hengtong Zhang, Yaqing Wang and Jing Gao.
      SIAM International Conference on Data Mining (SDM), Alexandria, Virginia, US. March 25 - 27, 2021.
    • Towards Learning Outcome Prediction via Modeling Question Explanations and Student Responses [Paper]
      Tianqi Wang, Fenglong Ma, Yaqing Wang, Tang Tang, Longfei Zhang, and Jing Gao.
      SIAM International Conference on Data Mining (SDM), Alexandria, Virginia, US. March 25 - 27, 2021.

    2020

    • Automatic Validation of Textual Attribute Values in ECommerce Catalog by Learning with Limited Labeled Data [Paper]
      Yaqing Wang, Yifan Ethan Xu, Xian Li, Xin Luna Dong and Jing Gao.
      ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Diego, CA, August 2020
      Oral Paper Acceptance Rate 5.8%
    • Weak Supervision for Fake News Detection via Reinforcement Learning [Paper] [Full Paper] [Data]
      Yaqing Wang, Weifeng Yang, Fenglong Ma, Jin Xu, Bin Zhong, Qiang Deng, Jing Gao.
      Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020
    • Efficient Knowledge Graph Validation via Cross-Graph Representation Learning [Paper]
      Yaqing Wang, Fenglong Ma, Jing Gao.
      Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM), Virtual, October, 2020
    • Rare Disease Prediction by Generating Quality-Assured Electronic Health Records [Paper]
      Fenglong Ma*, Yaqing Wang*(* equal contribution), Jing Gao, Houping Xiao, and Jing Zhou.
      Proceedings of the SIAM International Conference on Data Mining(SDM), 2020.
    • AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types [Paper]
      Xin Luna Dong, Xiang He, Andrey Kan, Xian Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, Saurabh Deshpande, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum, Jiawei Han.
      ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Diego, CA, August 2020
    • LP-Explain: Local Pictorial Explanation for Outliers [Paper]
      Haoyu Liu, Fenglong Ma, Yaqing Wang, Shibo He, Jiming Chen, and Jing Gao.
      IEEE International Conference on Data Mining(ICDM), 2020.

    2019

    • Hypothesis Generation From Text Based On Co-Evolution Of Biomedical Concepts [Paper]
      Kishlay Jha, Guangxu Xun, Yaqing Wang, Aidong Zhang.
      ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019
    • MeSHProbeNet: A Self-attentive Probe Net for MeSH Indexing [Paper]
      Guangxu Xun, Kishlay Jha, Ye Yuan, Yaqing Wang, Aidong Zhang.
      Bioinformatics, Oxford University Press, 2019

    2018

    • EANN: Event Adversarial Neural Networks for Multi-Modal Fake News Detection [Paper] [Data&Code] [Video] [Poster]
      Yaqing Wang, Fenglong Ma, Zhiwei Jin, Ye Yuan, Guangxu Xun, Kishlay Jha, Lu Su and Jing Gao.
      ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2018

      Ranked as the 5th most influenctial paper at KDD 2018 by Paperdigest untill 5/21/2021
    • Interpretable Word Embeddings For Medical Domain [Paper]
      Kishlay Jha*, Yaqing Wang* (* equal contribution), Guangxu Xun and Aidong Zhang.
      IEEE International Conference on Data Mining (ICDM), 2018
    • A General Framework for Diagnosis Prediction via Incorporating Medical Code Descriptions [Paper]
      Fenglong Ma, Yaqing Wang, Houping Xiao, Ye Yuan, Radha Chitta, Jing Zhou and Jing Gao.
      IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018
    • Multivariate Sleep Stage Classification using Hybrid Self-Attentive Deep Learning Networks [Paper]
      Ye Yuan, Fenglong Ma, Guangxu Xun,Yaqing Wang, Kebin Jia, Lu Su and Aidong Zhang.
      IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018
    • MuVAN: A Multi-view Attention Network for Multivariate Temporal Data [Paper]
      Ye Yuan, Guangxu Xun, Fenglong Ma, Yaqing Wang, Nan Du, Kebin Jia, Lu Su and Aidong Zhang.
      IEEE International Conference on Data Mining (ICDM), 2018
    • Towards Environment Independent Device Free Human Activity Recognition [Paper]
      Wenjun Jiang, Chenglin Miao, Fenglong Ma, Shuochao Yao, Yaqing Wang, Xin Ma, Chen Song,
      Ye Yuan, Hongfei Xue, Dimitrios Koutsonikolas, Wenyao Xu and Lu Su.
      24th Annual International Conference on Mobile Computing and Networking (MobiCom), 2018
    • Concepts-Bridges: Uncovering Conceptual Bridges Based on Biomedical Concept Evolution [Paper]
      Kishlay Jha, Guangxu Xun, Yaqing Wang, Vishrawas Gopalakrishnan and Aidong Zhang.
      ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2018

    2017

    • Discovering Truths from Distributed Data [Paper] [Code]
      Yaqing Wang, Fenglong Ma, Lu Su, and Jing Gao
      IEEE International Conference on Data Mining (ICDM), 2017

  • ICLR 2022, WWW 2022, ACL Rolling Review 2022, SDM 2022,KDD 2022, EMNLP 2022, NeurIPS 2022, WSDM 2022
  • ICLR 2021, AAAI 2021, NAACL 2021, ACL 2021, KDD 2021, ICML 2021, EMNLP 2021, NeurIPS 2021
  • ICML 2020, KDD 2020, BigData 2020
  • Bilsland Dissertation Fellowship, Purdue University, 2022
  • Travel Awards: CIKM 2020, KDD 2020, AAAI 2020, KDD 2018, ICDM 2017
  • Presidential Fellowship, SUNY Buffalo, 2016-2020
  • Last updated: Nov 2021.