Biography

Dr. Guodong Long is an Associate Professor in School of Computer Science, Faculty of Engineering and IT (FEIT), University of Technology Sydney (UTS), Australia.

He is currently leading a research group to conduct application-driven research on machine learning and data science. Particularly, his research interests focus on several application domains, such as health data analysis, climate change and IoT. He is dedicating on exploring the blue-sky research ideas with real-world value and impact.

We are looking for self-motivated PhD candidates to explore the research direction on federated learning and its applications, please send the CV if you are interested to join in Guodong’s team. More information at here

Interests

  • Federated Learning
  • Health data analysis
  • Climate Change
  • Privacy Preservation
  • Graph Data Processing

Requirement for applying PhD Candidate

  • Computer science or relevant disciplines
  • Demonstrated research experience and outputs
  • Strong background on programming and math
  • Capable to balance team work and indepent work

News

  • Mar 2024, Chunxu Zhang has one paper (IFedRec: Item-Guided Federated Aggregation for Cold-Start) accepted by WebConf (previously known as WWW conference) 2024.
  • Feb 2022, Shengchao Chen has one paper (Foundation models for weather and climate data understanding: A comprehensive survey) released to arXiv.
  • Feb 2024, Zhiwei Li has one paper (Federated Recommendation with Additive Personalization) accepted by ICLR 2024.
  • ---------------- 2023-2024 separate line-------------------
  • Oct 2023, Zhihong Deng has one paper (False Correlation Reduction for Offline Reinforcement Learning) accepted by IEEE TPAMI.
  • Jul 2023, Zhihong Deng has one paper (Causal Reinforcement Learning: A Survey) accepted by TMLR.
  • Jul 2023, Jie Ma has one paper (Structured Federated Learning through Clustered Additive Modeling) accepted by NeurIPS 2023. It is this first time to propose structured federated learning that aim to leverage the structural knowledge among distributed clients.
  • Jul 2023, Yue Tan has one paper (Is heterogeneity notorious? taming heterogeneity to handle test-time shift in federated learning) accepted by NeurIPS 2023. It is joint work with Sone AI to explore a practical problem that is to tackle test-time shift challenge on deployed federated learning system.
  • May 2023, Shengchao Chen has one paper (Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data) accepted by IJCAI 2023. It is the first to conduct federated prompt learning for weather forcasting.
  • May 2023, Chunxu Zhang has one paper (Dual Personalization on Federated Recommendation) accepted by IJCAI 2023. This is the first to conduct fine-grained presonalisation modelling by leveraging dual parties in a privacy-preserving federated receommondation framework.
  • May 2023, Haiyan Zhao has one paper (Does Continual Learning Equally Forget All Parameters?) accepted by ICML 2023.
  • May 2023, Yijun Yang has one paper (Continual Task Allocation in Meta-Policy Network via Sparse Prompting) accepted by ICML 2023.
  • Apr 2023, Tao Shen has one paper (Unifier: A unified retriever for large-scale retrieval) accepted by SIG KDD 2023.
  • Apr 2023, Peng Yan has one paper (Personalization Disentanglement for Federated Learning) accepted by ICME 2023. It is the first to discusss interpretablity problem on personality in federated settings.
  • Feb 2023, Yue Tan has one paper (Federated Learning on Non-IID Graphs via Structural Knowledge Sharing) accepted by AAAI 2023. It is a pioneer work to conduct federated graph learning.
  • ---------------- 2022-2023 separate line-------------------
  • Aug 2022, Yue Tan has one paper (Federated Learning from Pre-Trained Models: A Contrastive Learning Approach) accepted by NeurIPS 2022. It is a pioneer work to design novel Federated learning moethod by leveraging existing pre-trained models.
  • May 2022, Fengwen Chen has one paper (Personalized Federated Learning With a Graph) accepted by IJCAI 2022. It is the first to propose graph-guided aggregation on federated learning with non-IID data.
  • July 2022, our paper (Multi-center federated learning: clients clustering for better personalization) has been accepted by Wold Wide Web journal.
  • Our book chapter (Federated learning for privacy-preserving open innovation future on digital health) has been published.
  • Apr 2022, Wensi Tang has one paper (Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification) accepted by ICLR 2022. It is a effective tool to run 1D-CNN models on bechmark datasets.
  • May 2022, Fengwen Chen has one paper (Personalized Federated Learning With a Graph) accepted by IJCAI 2022. It is the first to propose graph-guided aggregation on federated learning with non-IID data.
  • Nov 2021, I am invited to participate peer-review for CVPR, ICML, IJCAI and KDD 2022.
  • Nov 2021, Yue Tan has one paper (FedProto: Federated Prototype Learning on Heterogeneous Clients) accepted by AAAI 2022.
  • Oct 2021, Ao Shuang has one paper accepted by NeurIPS 2021.
  • Nov 2021, I are participating peer-review for ACL 2021 and ICLR 2022.
  • Aug 2021, Xueping Peng has one paper accepted by ICDM 2021.
  • Jul 2021, I have a new book chapter "Federated Learning for Privacy-Preserving Open Innovation Future on Digital Health" in a Springer book "Humanity Drive AI".
  • Jun 2021, Hao Huang has one paper accepted by ACL 2021.
  • Jan 2021, Bo Wang with Tao Shen has one paper accepted by WebConf 2021.
  • Jan 2021, big congratulations to Ms Lu Liu for her two accepted papers on ICLR 2021.
  • Dec 2020, congratulations to Tao Shen and Chun Wang for submitting PhD thesis.
  • Dec 2020, Hao Huang, Yang Li, andn Tao Shen have two papers accepted by COLING'21.
  • Dec 2020, I was promoted to Associate Professor in UTS.
  • Nov 2020, I have a new book chapter "Federated Learning for Open Banking" has been published in a Springer book "Federated Learning - Privacy and Incentive" edited by Prof Qiang Yang.
  • Jun 2020, Han Zheng’s paper “Cooperative Heterogeneous Deep Reinforcement Learning” has been accepted by NeurIPS 2020.
  • Sep 2020, Tao Shen’s paper “Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning” has been accepted by EMNLP 2020.
  • Aug 2020, Xueping Peng and Chun Wang have two papers accepted by IEEE ICDM 2020.
  • Jun 2020, Lu Liu’s paper “Many-class few-shot learning on multi-granularity class hierarchy” has been accepted by IEEE TKDE.
  • Jun 2020, Xueping Peng and Zhuowei Wang have two papers accepted by ECML/PKDD 2020.
  • May 2020, Zonghan Wu’s paper “Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks” was accepted by KDD 2020.
  • Apr 2020, Tao Shen’s paper “Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering” was accepted by IJCAI 2020.
  • Mar 2020, as impacted by COVID-19, all members of our group work from home. We had the first video conference for group meeting. I believe it changed our group’s collaborative style to be more physical location independent.
  • Mar 2020, our survey paper is accpeted by IEEE TNNLS. “A Comprehensive Survey on Graph Neural Networks”, the paper attracted more than 200 citations in one year since being uploaded to arxiv at 2019, students - Zonghan Wu, and Fenwen Chen
  • Feb 2020, one AAAI’18 paper attracted more than 200 citations in two years, paper - “Disan: Directional self-attention network for rnn/cnn-free language understanding”, student - Tao Shen.
  • Dec 2019, I win the bid for hosting AusAI’21 in Sydney.
  • Dec 2019, I had an invited talk at the Australian Commonwealth Department of Health.
  • Nov 2019, our group has three papers accepted by AAAI 2020, students - Ruiqi Hu, Lu Liu, and Yang Li (with Tao Shen).
  • Sep 2019, our group has one paper accepted by NeurIPS 2019. “Learning to Propagate for Graph Meta-Learning”, student - Lu Liu.

Research Community Services

  • I will serve as area chair for AAAI 2022.
  • I will serve as PC chair to organize the International Conference Advanced Data Mining and Applications (ADMA) 2021 .
  • I will serve as PC member for CVPR, KDD, ICML, and ACL 2021.
  • I will serve as Senior PC member for IJCAI 2021.
  • I served as PC member for ICLR 2021.
  • I will be the program co-chair for Australian joint conference on AI 2021 by co-working with Prof. Mary-Anne Williams (UTS), Prof. Toby Walsh (UNSW), and Prof. Xinghuo Yu (RMIT).
  • I served as PC member for NeurIPS, AAAI, ACL and EMNLP 2020.
  • I served as Senior PC member for IJCAI 2020 and AAAI 2021.
  • I served as reviewer for journal IEEE TPAMI, TNNLS, TIP, TKDE and TKDD.
  • I served as Demo Co-Chair for ADMA 2019.
  • I chaired one session “ECR Spotlight talks – series 6” in IJCAI 2019.
  • I was one of the organisers for a special session in IJCNN 2019.
  • I organised a workshop AI4Edu in IJCAI 2019 by co-working with other three academics from world-leading research organisations: UC Berkeley, CMU, and SRI International.
  • I chaired one session “Recommender System – series 2” in ICDM 2018.
  • Since 2015, I regularly serve as a reviewer for ARC (Australia Research Council) proposals including DP, LP and DECRA.
  • Since 2017, I regularly serve as a reviewer for the top AI conferences and journals, e.g. IJCAI, AAAI, ICDM, IEEE TPMAI/TNNLS/TKDE/TSE/TCYB, ACM TKDD.
  • I was the Job Match Chair for KDD 2015 and IJCAI 2017. The Job Match program aims to provide a face-to-face recruitment opportunity for conference attendees and sponsors.

Talks

  • Talk in government, “Augmenting Healthcare Data Analytics with Deep Learning”, at Australian Government Department of Health, Canberra, Dec 2019. This talk is invited by Acting Deputy Secretary of the Department. The whole talk is recorded by Health TV, and it could be watched online from the Department’s intranet.
  • Tutorial talk, “Deep Learning for Healthcare Data Processing”, at DASFAA, Thailand, May 2019.
  • Talk and panel discussion, “PhD training in Computer Science”, Australian Computer Science Week, Jan 2019.
  • Short-course, “NLP with Deep Learning”, UTS, Australia, 2018.
  • Seminar talk, “Deep Learning: An Introduction”, at the South China University of Technology, China, July 2018.
  • Talk in government, “AI-as-a-Service in Healthcare”, Australian Government Department of Health, Canberra, Australia, May 2018.
  • Industry expo, “Health Expo - UTS Showcase”, Australian Government Department of Health, Canberra, Australia, 2018. In the meantime, we invited UTS Vice-Chancellor Prof. Attila Brungs to give a keynote speech in this expo, and he also joined in the panel discussion with Data61 CEO Mr Adrian Turner.
  • I organised a seminar to showcase our research work relating to AI for Social Goods, “Interaction Mining for Social Service”, UTS, Australia, 2017.

Research Showcase

  • Cyberbullying Message Detecting

  • Interactive Deep Metric Learning for Cohort Discovering

    • A paper co-authored with Department of Health won the runner-up paper award on Australia Data Mining Conference 2019.

  • Diagnosis Code Embedding with Temporal Self-Attention

    • A paper was published at ICDM 2019.

Apply Ph.D

  • How to contact Dr Guodong Long. Click to Email
  • How to apply for a PhD in UTS? Click here
  • How about UTS’ ranking? University ranking
  • How about UTS’s ranking in Computer Science(CS)?
  • Any other charateristics for UTS?
    • UTS is young university with only 30 years history.
    • UTS is a technology-focus university, especially computer science and information technology.
    • UTS locates on the southern gate of CBD area for Sydney, and it is close to “Central Station”, “Town Hall”, “China Town”, “Darling Habour”, and “Sydney Convention and Exhibition Centre”.
    • UTS city campus has been improved with $15 billions investment in past 10 years, and it is mixed with modern buildings and peaceful green areas.
    • From UTS, you can easily access hundreds of reseataurants, cafes, food courts, food streets, and shopping malls in 10-min walking distance.

Contact