Introduction
Deep Learning models are at the core of research in Artificial Intelligence research today. In the era of big data, the importance of being able to effectively mine and learn from graph data is growing, as more and more structured and semi-structured data is becoming available. The success of graph can be attributed to its ability to capture the structural information of the data, extract meaningful features, and reveal the causal inference behind the data. It is a great deal of interest in analyzing data that is best represented as a graph, such as social networks, biological networks, communication networks, and molecular structure networks. The intersection of graph theory and deep learning has also influenced other fields of science, including computer vision, natural language processing, program synthesis and analysis, automated planning, reinforcement learning, and data security. Despite these successes, graph neural networks still face many methodological, applicable, or interpretable challenges. This workshop aims to bring together researchers from data mining and machine learning domains to discuss the latest developments and applications of graph-related works. We encourage a lively exchange of ideas and perceptions to share and discuss their latest findings, focused on data-driven science and data mining. The workshop will feature invited talks and contributed papers to provide a platform for exchanging ideas and fostering collaborations.
Submissions
Topics of Interest
The focus areas include, but are not limited to:
- Data mining and AI applications for Graphs
- Data mining approaches in social attributed networks and natural language processing
- Dealing with the heterogeneity of the data
- Data mining for healthcare and biological science
- Handling dynamic and changing data
- Security data fusion (e.g., event correlation) across multiple data sources
- Knowledge discovery and data mining
- Modelling and simulation of cyber systems and system components
- Event correlation and anomaly detection
- Addressing each of these issues at scale
Proceedings
All papers accepted for this workshop will be published in the Workshop Proceedings of IEEE Big Data Conference, made available in the IEEE eXplore digital library.
Submission Instructions
- Camera-ready version of accepted papers must be compliant with the IEEE Xplore format for publication.
- Submissions must be in PDF format.
- Submissions are required to be within 6 pages for short paper or 10 pages for full paper (including references).
- Submissions must be single-spaced, 2-column pages in IEEE Xplore format.
- Submissions are NOT double-blind.
- Only web-based submissions are allowed.
- All submission deadlines are Anywhere on Earth (AOE).
- Please submit your paper via the submission system.
- Submission link: Cyberchair submissions website.
Important Dates
- Paper Submission: October 1, 2023
- Paper Acceptance Notification: November 1, 2023
- Camera-ready Deadline: November 20, 2023
- Workshop: December 15-18, 2023
Speakers
- Fuchun Sun, Tsinghua University
- Jiawei Zhang, New York University
- Fenglong Ma, Pennsylvania State University
- Lingfei Wu, Pinterest
- Wenpeng Yin, Penn State University
- Yasushi Sakurai, Osaka University
Organizers
Program Chairs
- Kai Zhao, University of Alabama at Birmingham
- Sian Jin, Temple University
- Jieyang Chen, University of Alabama at Birmingham
Web Chair
- Longtao Zhang, University of Alabama at Birmingham
Steering Committee
- Dingwen Tao, Indiana University
- Sheng Di, Argonne National Laboratory
- Xin Liang, University of Kentucky
Program Committee (Planned)
- William Godoy, Oak Ridge National Laboratory
- Pascal Grosset, Los Alamos National Laboratory
- Shaomeng Li, National Center for Atmospheric Research
- Xiaodong Yu, Argonne National Laboratory
- Jiannan Tian, Indiana University