Call for Papers
Submission Guideline
This workshop is a forum for exchanging ideas and methods for federated learning with graph data, developing new common understandings of the problems at hand, sharing of data sets where applicable, and leveraging existing knowledge from different disciplines. The goal is to bring together researchers from academia, industry, and government, to create a forum for discussing recent advances and future directions. In doing so, we aim to better understand the overarching principles and the limitations of our current knowledge and methods, and to inspire research on new algorithms and techniques for federated learning with graph data.
To reflect the broad scope of work on federated learning with graph data, we encourage submissions that span the spectrum from theoretical analysis to algorithms and implementation, to applications, empirical studies, and reflection papers. Topics of interest include, but are not limited to:
How to achieve near optimal utility that is close to the centralized training setting with distributed graph datasets?
How to handle more complex data correlation and heterogeneity under the context of graph mining?
How to scale up the number of clients when the graph structures require heavy communications?
How to reduce and compress communications among clients by exploring the architectures of graph models to achieve training efficiency?
How to rigorously protect clients’ graph data privacy during collaboration?
How to properly evaluate innovative GNN models and FL algorithms towards realistic applications such as knowledge graph completion, recommendation in e-commerce networks and diagnosis prediction in healthcare networks?
How to extend the concepts and algorithms of FedGraph to a broader range of complex data beyond classic graphs, such as heterogeneous networks, spatiotemporal networks, text-rich networks, multi-view networks, point clouds, trees, manifolds, and fractals?
How to conduct federated learning with graph algorithms beyond GNNs such as graph kernels, belief propagation and spectral analysis?
How to enhance the optimization of existing FL systems based on graph mining principles and techniques?
How to guarantee fairness, ethics, and trustworthiness in the FedGraph context?
We welcome many kinds of papers, such as, but not limited to:
Novel research papers
Demo papers
Work-in-progress papers
Visionary papers (white papers)
Appraisal papers of existing methods and tools (e.g., lessons learned)
Evaluatory papers which revisit validity of domain assumptions
Relevant work that has been previously published
Work that will be presented at the main conference
Authors should clearly indicate in their abstracts the kinds of submissions that the papers belong to, to help reviewers better understand their contributions.
All papers will be single-blinded and peer-reviewed. Submissions must be in PDF, no more than 10 pages long, including all contents, figures, tables, references, and appendices— shorter papers are welcome— and formatted according to the standard double-column ACM Proceedings Style. Additionally, papers must be in the two-column format, with the recommended setting for Latex file: \documentclass[sigconf, review]{acmart}.
The accepted papers will be published on the workshop’s website and will not be considered archival for resubmission purposes. While all accepted papers will be presented with posters, high-quality accepted papers will also have the opportunity to participate in the oral/spotlight presentation, and win our Best Paper Award(s).
For paper submission, please proceed to the submission website (https://easychair.org/conferences/?conf=fedgraph2022).
Best Paper Award(s)
With pride and gratitude, we announce that we will have several Best Paper Awards (with cash prizes), and possibly some travel awards, sponsored by JZTData Technology, Tencent, FedML, and USC-Amazon Center.
Important Dates
Submission: August 22 (August 15), 11:59pm AoE
Notification: September 15
Camera-ready: October 15
Workshop date: October 21