Vrije Universiteit Amsterdam
Michael Cochez is an Assistant Professor in the Learning and Reasoning group (formerly part of the Knowledge Representation and Reasoning group) at the Vrije Universiteit Amsterdam. The subjects covered in his research are related to machine learning and graphs, and knowledge representation. He has also worked on evolutionary computing (optimization), frequent pattern mining, multi-agent systems, version control in IT education and scalable hierarchical clustering.
Petr Knoth leads the Big Scientific Data and Text Analytics Group (BSDTAG) undertaking R&D in the domains of text-mining, digital libraries and open access/science. Dr Knoth is the founder and head of CORE (core.ac.uk), a large full text aggregator of open access papers with millions of monthly active users. Dr Knoth has been involved as a researcher and Primary Investigator (PI) in over 20 European Commission, national and international funded research projects in the areas of text-mining, open science and eLearning.
Mayank Kejriwal is a Research Assistant Professor in the Department of Industrial and Systems Engineering, and a Research Lead at the USC Information Sciences Institute. His research has been, or is currently, funded by programs such as DARPA LORELEI, CauseEx, MEMEX, AIDA and D3M projects. Prior to joining ISI in 2016, he obtained his Ph.D. from the University of Texas at Austin. His dissertation, titled "Populating a Linked Data Entity Name System", was awarded the Best Dissertation Award by the Semantic Web Science Association in 2017. He is also the author of "Domain-specific Knowledge Graph Construction" (Springer), which has been downloaded thousands of times in the last year and is available internationally.
Tara Safavi is a Senior Researcher at Microsoft Research Redmond working on language models for universal interaction + content understanding. She completed her PhD at the University of Michigan in May 2022, working with Dr. Danai Koutra on machine learning over graphs + text. Her research was funded by an NSF Graduate Research Fellowship. She is the recipient of the ICDM 2019 best student paper award and the ICDM 2017 best paper runner-up.
Tyler Derr is an Assistant Professor in the Department of Computer Science, Teaching and Affiliate Faculty in the Data Science Institute, and Faculty Fellow in the Frist Center for Autism and Innovation at Vanderbilt University. He directs the Network and Data Science (NDS) lab, which focuses on data mining and machine learning, especially in social network analysis, deep learning on graphs, and data science for social good with applications in drug discovery, education, political science, and autism research. He received his PhD (2020) in Computer Science from Michigan State University under the supervision of Dr. Jiliang Tang and was a member of the Data Science and Engineering (DSE) Lab and Teachers in Social Media (TISM) Project. He had both completed his MS (2015) in Computer Science and dual BS (2013) in Computer Science and Mathematical Sciences at The Pennsylvania State University.
| International Workshop on Knowledge Graphs (KG) Workshop Chair: | ||
|---|---|---|
| Time (EST) | Title | Presenter/Author |
| 10:00-10:05 | Opening Remarks | Organizers |
| 10:05-10:45 | Learning to Query Graphs: Extracting Plausible Answers | Michael Cochez |
| 10:45-11:25 | Towards Open Scholarly Knowledge Graphs | Petr Knoth |
| 11:25-12:00 | Domain-Specific Knowledge Graph Construction: Opportunities and Challenges | Mayank Kejriwal |
| 12:00-13:00 | Lunch Break | |
| 13:00-13:40 | Augmenting Structure with Text for Improved Graph Learning | Tara Safavi |
| 13:40-14:20 | Overcoming Data Quality Issues in Graph Learning | Tyler Derr |
| 14:20-14:35 | Towards Fair Representation Learning in Knowledge Graph with Stable Adversarial Debiasing | Yihe Wang |
| 14:35-14:50 | Abnormal Entity-Aware Knowledge Graph Completion | Ke Sun |
| 14:50-15:05 | ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion | Pei Chen |
| 15:05-15:10 | Closing Remarks | Organizers |
Knowledge graph is essentially the knowledge base of semantic web, which is composed of entities (nodes) and relations (edges). As the representation of semantics, knowledge graphs can readily-easily formulate real-world entities, concepts, attributes, as well as their relations. All the specific features of knowledge graphs make it born with strong expressive ability and flexible modelling ability. At the same time, as a special kind of graph data, knowledge graphs are both human-readable and machine-friendly. With effective knowledge representation approaches, a variety of tasks can be resolved, including knowledge extraction, knowledge integration, knowledge management, and knowledge applications. Furthermore, efficient knowledge representation learning and reasoning can be one of the paths towards the emulation of high-level cognition and human-level intelligence. These trends naturally facilitate relevant downstream applications which inject structural knowledge into wide-applied neural architectures such as attention-based transformers and graph neural networks.
Recent years have witnessed the rapid growth in the number of academics and practitioners interested in knowledge graph and closely related areas. In particular, various deep neural network models have been developed for knowledge graph-based areas. Meanwhile, as knowledge graphs have been applied in various domains such as information retrieval, natural language understanding, question answering systems, recommender systems, financial risk control, etc., new challenges have emerged in the context of knowledge graphs from many perspectives including scalability, security, explainability, robustness, etc.
The workshop will bring together researchers and practitioners to discuss the fundamentals, methodologies, techniques, and applications of knowledge graphs. In this workshop, our goal is to contribute to the next generation of knowledge graphs and exploring them using artificial intelligence, data science, machine learning, network science, and other appropriate technologies.
Topics of interest include but not limited to:
This workshop would like to share exciting techniques to solve critical problems such as:
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.
All papers should be no more than 10 pages in length (max 8 pages plus 2 extra pages), in the IEEE 2-column format ( https://www.ieee.org/conferences/publishing/templates.html), including the bibliography and any possible appendices. Submissions longer than 10 pages will be rejected without review. Authors must complete a reproducibility checklist at the time of paper submission (the questions in PDF format) [ https://www.cs.mcgill.ca/~jpineau/ReproducibilityChecklist-v2.0.pdf].
All submissions will be peer-reviewed by members of the Program Committee and be evaluated for originality, quality and appropriateness to the workshop. Furthermore, as in previous years, papers that are not accepted by the main conference will be automatically sent to a workshop selected by the authors when the papers were submitted to the main conference. By the unique ICDM tradition, all accepted workshop papers will be published in the dedicated ICDMW proceedings published by the IEEE Computer Society Press.
In no particular order
