Workshop Scope
The workshop will delve into both foundational and advanced issues in FL, incorporating a focus on graph analytics within the following four categories. Different from the previous workshops, FedGraph at ICDM 2023 or Federated Learning for Distributed Data Mining at KDD 2023, the workshop will bring in new challenges accompanied by the emergence of large models, generative AI, and new interdisciplinary applications in science.
(1) Scalability of FL facing increasingly larger and more heterogenous data, models, and computation-or-communication resources. Essentially, we look for studies on how the effectiveness of existing or new FL algorithms changes by the scaling. Specific topics include:
- Learning for larger language/vision models with more parameters, pre-training data, etc.;
- Learning with an increasing number of clients to billion scales;
- Learning from highly heterogeneous data distributions;
- Learning from heterogeneous hardware or computation capabilities with increasing gaps in hardware capabilities;
(2) Safety. Problems and solutions for the security, privacy, and social alignment of FL systems and the resultant models. Especially, when training large generative AI models, the potential risks and countermeasures in FL systems are welcome to discuss. Specific topics include
- Privacy leakage during distributed training and inference;
- Risks for generative AI safety from the distributed data sources;
- Uncertainty in data collection with noisy labels or data;
- Backdoor attacks in training and inference;
- Data poisoning due to more and more generated web data.
(3) Graph Analytics. Intuitions and solutions to close the gap between centralized and decentralized graph analysis.
- Handling more complex data correlation and heterogeneity attributed to intricate graph structure;
- Communication efficiency with large-scale graph analytics;
- Privacy requirements on both statistical and structural information of graph data;
- Evaluation of innovative Graph Neural Network (GNN) models and FL algorithms towards realistic applications such as knowledge graph completion, and recommendation in e-commerce networks;
- Extending the concepts and algorithms of FL 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;
- Federated graph algorithms beyond GNNs such as graph kernels, belief propagation, and spectral analysis;
- Optimization of existing FL systems based on graph mining principles and techniques.
(4) Other high-stakes applications. Explorations on novel research problems of FL and FL algorithms for real-world applications, including
- Bioinformatics and biomedical informatics;
- Financial engineering and quantitative finance;
- Medical imaging;
- Drug discovery;
- Social networks and graph-based learning;
- Natural language processing;
- Computer vision.
Not limited to above topics, we aim to attract high-quality original research of federated learning with applications, evaluation, and algorithms. We also welcome open discussions on controversial yet crucial topics regarding FL systems and discuss their barriers in data mining.
Submission Guidelines
Format:
We invite short technical papers - up to 5 pages including references and unlimited pages of appendix.
All manuscripts should be submitted in a single PDF file including all content, figures, tables, and references, following the new Standard ACM Conference Proceedings Template.
For LaTeX users: unzip acmart.zip, make, and use sample-sigconf.tex as a template; Additional information about formatting and style files is available online at ACM Proceedings Template.
Additionally, papers must be in the two-column format, with the recommended setting for Latex file: \documentclass[sigconf, anonymous, review]{acmart}.
Camera ready: Accepted papers can have up to 5 pages and unlimited pages of references and appendix. Please use the new acmart.cls when preparing submissions.
Submission: Papers should be submitted at the openreview website.
Review: All papers will be double-blinded and peer-reviewed by at least 2 reviewers.
Presentation: 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). All accepted papers are expected to be presented in person. The workshop will not provide support for virtual talks or posters. We will also present accepted papers on our website.
According to the policy of the KDD conference, the accepted papers will NOT be included in proceedings or any form of publication.
Awards: The organizing committee will select best paper award(s) supported by our sponsors.
Important Dates
- Submission site open: April 20, 2024
- Paper submissions:
May 28th 11:59, June 11th 11:59 (GMT), 2024 - Paper notifications: June 26th, 2024
- Early-bird registration due: July 10th, 2024 (registration link)
- Workshop date: Monday, August 26, 2:00 PM - 6:00 PM, 2024