GraphLearning 2022

International Workshop on Graph Learning


April 25, 2022, Online

A workshop of The ACM Web Conference 2022





Structure-based Large-scale Dynamic Heterogeneous Graphs Processing: Applications, Challenges and Solutions


Prof. Wenjie Zhang, University of New South Wales, Australia


Wenjie Zhang is a Professor, ARC Future Fellow, Deputy Head of School (Research and Operations) and Head of Data and Knowledge Research Group in School of Computer Science and Engineering, University of New South Wales Australia. Her research interests lie in developing efficient (e.g., real-time) and scalable techniques for data intensive applications. She has published over 180 research papers in leading international journals and conferences. Her research has been supported by 9 Australian Research Council funded projects and several industry projects. Wenjie serves as an Associate Editor for IEEE Transactions on Knowledge and Data Engineering, a senior PC or track chair for VLDB 2023/2022, CIKM 2022/2021/2019/2015, and ICDE 2019, and organization committee member or PC member for more than 50 international conferences. Wenjie is the recipient of the Australasian CORE Chris Wallace Research Award in 2019. Her works receive the ACM SIGMOD Research Highlight Award 2021, one of the Best Papers in SIGMOD 2020, ICDE 2013/2012/2010, and several Best (Student) Paper Awards from international conferences. 



Graphs in Computer Vision Then and Now: How Deep Learning has Reinvigorated Structural Pattern Recognition


Prof. Donatello Conte, University of Tours, France


Donatello Conte received his Ph.D. degree in 2006 by a joint supervision between LIRIS laboratory of the INSA of Lyon (France) and MIVIA laboratory of the University of Salerno (Italy). He has been an Assistant Professor from 2006 to 2013, in Italy at the University of Salerno. From 2013 to date, he is Associate Professor at the Computer Science Laboratory of the University of Tours. He is currently head of the Computer Science Department at Polytech Tours School of Engineering. Currently he is co-head of the RFAI team at the Computer Science Laboratory and he participates, as member and sometimes as local coordinator, to several regional projects on image and video analysis. His main research fields are: structural pattern recognition (graph matching, graph kernels, combinatorial maps), video analysis (objects detection and tracking, trajectories analysis, behavioral analysis, etc.), and affective computing (emotion recognition, multimodality analysis for affective analysis, physiological measures by video analysis, etc.). He is the author of more than 70 publications and reviewers in the main journals in his research field (PAMI, PR, CVIU, TIP, etc.). He is member of the Editorial Board of the Elsevier Journal Internet of Things, MDPI Journal of Imaging and he is Guest Editor for the Pattern Recognition Letters journal.



Graph Neural Networks beyond Weisfeiler-Lehman and vanilla Message Passing


Prof. Michael Bronstein, University of Oxford, United Kingdom


Michael Bronstein is the DeepMind Professor of AI at the University of Oxford and Head of Graph Learning Research at Twitter. He was previously a professor at Imperial College London and held visiting appointments at Stanford, MIT, and Harvard, and has also been affiliated with three Institutes for Advanced Study (at TUM as a Rudolf Diesel Fellow (2017-2019), at Harvard as a Radcliffe fellow (2017-2018), and at Princeton as a short-time scholar (2020)). Michael received his PhD from the Technion in 2007. He is the recipient of the Royal Society Wolfson Research Merit Award, Royal Academy of Engineering Silver Medal, five ERC grants, two Google Faculty Research Awards, and two Amazon AWS ML Research Awards. He is a Member of the Academia Europaea, Fellow of IEEE, IAPR, BCS, and ELLIS, ACM Distinguished Speaker, and World Economic Forum Young Scientist. In addition to his academic career, Michael is a serial entrepreneur and founder of multiple startup companies, including Novafora, Invision (acquired by Intel in 2012), Videocites, and Fabula AI (acquired by Twitter in 2019).


Date: Monday, April 25, 2022
Time Zone: Central European Summer Time (CEST, UTC+2)


8:00 – 8:10 Opening Remarks


8:10 – 8:50 Keynote I
Structure-based Large-scale Dynamic Heterogeneous Graphs Processing: Applications, Challenges and Solutions
Wenjie Zhang


8:50 – 10:20 Technical Session I
Deep Partial Multiplex Network Embedding
Qifan Wang, Yi Fang, Ruining He, Anirudh Ravula, Bin Shen, Jingang Wang, Xiaojun Quan and Dongfang Liu


Multi-view Omics Translation with Multiplex Graph Neural Networks
Costa Georgantas and Jonas Richiardi


A Triangle Framework Among Subgraph Isomorphism, pharmacophore and structure-function relationship
Mengjiao Guo, Hui Zheng, Tengfei Ji and Jing He


CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
Yassaman Ommi, Matin Yousefabadi, Faezeh Faez, Amirmojtaba Sabour, Mahdieh Soleymani Baghshah and Hamid R. Rabiee


Mining Multivariate Implicit Relationships in Academic Networks
Bo Xu, Bowen Chen, Tianyu Zhang, Jiaying Liu, Chunke Liao and Zhehuan Zhao


SchemaWalk: Schema Aware Random Walks for Heterogeneous Graph Embedding
Ahmed E. Samy, Lodovico Giaretta, Zekarias T. Kefato and Sarunas Girdzijauskas


10:20 – 10:45 Break


10:45 – 11:25 Keynote II
Graphs in Computer Vision Then and Now: How Deep Learning Has Reinvigorated Structural Pattern Recognition?
Donatello Conte


11:25 – 12:55 Technical Session II
Graph Augmentation Learning
Shuo Yu, Huafei Huang, Minh Dao and Feng Xia


Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
Fan Zhang, Qiuying Peng, Yulin Wu, Zheng Pan, Rong Zeng, Da Lin and Yue Qi


Mining Homophilic Groups of Users using Edge Attributed Node Embedding from Enterprise Social Networks
Priyanka Sinha, Ritu Patel, Pabitra Mitra, Dilys Thomas and Lipika Dey


RePS: Relation, Position and Structure aware Entity Alignment
Anil Surisetty, Deepak Chaurasiya, Nitish Kumar, Alok Singh, Gaurav Dhama, Aakarsh Malhotra, Vikrant Dey and Ankur Arora


Scaling R-GCN Training with Graph Summarization
Alessandro Generale, Till Blume and Michael Cochez


JGCL: Joint Self-Supervised and Supervised Graph Contrastive Learning
Selahattin Akkas and Ariful Azad


12:55 – 13:10 Break


13:10 – 13:50 Keynote III
Graph Neural Networks beyond Weisfeiler-Lehman and vanilla Message Passing
Michael Bronstein


13:50 – 15:20 Technical Session III
MarkovGNN: Graph Neural Networks on Markov Diffusion
Md. Khaledur Rahman, Abhigya Agrawal and Ariful Azad


Unsupervised Superpixel-Driven Parcel Segmentation of Remote Sensing Images Using Graph Convolutional Network
Fulin Huang, Zhicheng Yang, Hang Zhou, Chen Du, Andy J.Y. Wong, Yuchuan Gou, Mei Han and Jui-Hsin Lai


Improving Bundles Recommendation Coverage in Sparse Product Graphs
Saloni Agarwal, Aparupa Das Gupta and Amit Pande


Revisiting Neighborhood-based Link Prediction for Collaborative Filtering
Hao-Ming Fu, Patrick Poirson, Kwot Sin Lee and Chen Wang


Understanding Dropout for Graph Neural Networks
Juan Shu, Bowei Xi, Yu Li, Fan Wu, Charles Kamhoua and Jianzhu Ma


Surj: Ontological Learning for Fast, Accurate, and Robust Hierarchical Multi-label Classification
Sean Yang and Bill Howe


15:20 – 15:30 Closing

[PDF]  [TXT]  [PNG]

Graphs (also known as networks) are a popular and widely-used representation of various complex data, such as World Wide Web, knowledge graphs, social networks, biological networks, traffic networks, citation networks, and communication networks. Graph data are now ubiquitous. Recent years have witnessed a surge of research and development in machine learning with/on graphs thanks to the revival of AI. This is leading to the rapid emergence of the field of graph learning. Built upon theories and techniques from multiple areas, including e.g. AI, machine learning, network science, graph theory, web science, and data science, graph learning as a powerful tool has attracted remarkable attention from many communities. Over the past few years, a lot of effective graph learning models and algorithms (e.g. graph neural networks, network embedding, network representation learning, etc.) have been developed to address various challenges in real-world applications, with promising results achieved. 


This workshop aims to bring together researchers and practitioners from academia and industry to discuss recent advances and core challenges of graph learning. This workshop will be established as a platform for multiple disciplines such as computer science, applied mathematics, physics, social sciences, data science, complex networks, and systems engineering. Core challenges in regard to theory, methodology, and applications of graph learning will be the main center of discussions at the workshop. 


In this workshop, we desire to explore the most challenging topics in the emerging field of graph learning and seek answers to noteworthy research questions such as:
- What are the core theories and models that underpin graph learning?
- How to build trustworthy and/or responsible AI systems with graph learning?
- Can graph learning be used for large-scale and complex networks/systems?
- When will graph learning fail, and why?
- How should new comers from diverse disciplines be educated so as to take advantage of graph learning?


Topics of interest include but not limited to:
- Foundations and understanding of graph learning
- Novel models and algorithms for graph learning
- Trustworthy graph learning
- Fairness, transparency, explainability, and robustness
- Graph learning on/for the Web
- Graph learning for complex systems and big networks
- Graph learning for social good
- Representation learning
- AI in knowledge graphs
- Lifelong graph learning systems
- Graph learning in various domains
- Graph learning applications, services, platforms, and education



Submission deadline: February 15, 2022 (Anywhere on Earth, Firm)
Acceptance notification: March 3, 2022
Camera-ready version: March 10, 2022
Workshop date: April 25, 2022

Authors are invited to submit original papers that must not have been submitted to or published in any other workshop, conference, or journal. The workshop will accept full papers describing completed work, work-in-progress papers with preliminary results, as well as position papers reporting inspiring and intriguing new ideas. Note that papers related to the Web are particularly welcome. We encourage you to submit your paper to the Workshop on Graph Learning Benchmarks (GLB 2022@TheWebConf 2022: instead of this workshop in case it contributes mainly to benchmarks of graph learning. 


All papers should be no more than 12 pages in length (maximum 8 pages for the main paper content + maximum 2 pages for appendixes + maximum 2 pages for references). Papers must be submitted in PDF according to the ACM format published in the ACM guidelines (, selecting the generic “sigconf” sample. The PDF files must have all non-standard fonts embedded. Papers must be self-contained and in English. 


All submissions will be peer-reviewed by members of the Program Committee and be evaluated for originality, quality and appropriateness to the workshop. At least one author of each accepted papers must present their work at the workshop. All accepted and presented papers will be published in The ACM Web Conference 2022 proceedings (companion volume), through the ACM Digital Library. 



Feng Xia, Federation University Australia
Renaud Lambiotte, University of Oxford
Charu Aggarwal, IBM T. J. Watson Research Center




Saloni Agarwal, University of Texas at Dallas
Ariful Azad, Indiana University Bloomington
Lei Bai, University of Sydney
Tanmoy Chakraborty, Indraprastha Institute of Information Technology Delhi
Michael Cochez, Vrije Universiteit Amsterdam
Tyler Derr, Vanderbilt University
Falih Febrinanto, Federation University Australia
Mingliang Hou, Dalian University of Technology
Zhao Kang, University of Electronic Science and Technology of China
Seyed Mehran Kazemi, Google Research
Zekarias Kefato, KTH Royal Institute of Technology
Junhyun Lee, Korea University
Radosław Michalski, Wrocław University of Science and Technology
Shirui Pan, Monash University
Chanyoung Park, Korea Advanced Institute of Science and Technology
Ciyuan Peng, Federation University Australia

Jonas Richiardi, University of Lausanne
Tara Safavi, University of Michigan
Vivek Sharma, MIT
Ke Sun, Dalian University of Technology
Pengyang Wang, University of Macau
Shan Xue, University of Wollongong
Leo Yu Zhang, Deakin University