Summary of Federated Incomplete Multi-view Clustering with Heterogeneous Graph Neural Networks, by Xueming Yan et al.
Federated Incomplete Multi-View Clustering with Heterogeneous Graph Neural Networks
by Xueming Yan, Ziqi Wang, Yaochu Jin
First submitted to arxiv on: 12 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces Federated Incomplete Multi-View Clustering Framework with Heterogeneous Graph Neural Networks (FIM-GNNs) for developing a global clustering model using distributed data. The framework addresses challenges like label information absence, data privacy, feature heterogeneity, and incompleteness across views. FIM-GNNs employ autoencoders built on heterogeneous graph neural networks for feature extraction at client sites, aggregating features into a global representation. Global pseudo-labels are generated to enhance the clustering process, refining it across different views. The proposed method is evaluated on public benchmark datasets, outperforming state-of-the-art algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper develops a new way to group similar things together using information from multiple sources of data. This is important because sometimes data is spread out and not all of it has labels (which are like instructions that help computers understand what the data means). The new method, called FIM-GNNs, helps solve this problem by combining different views of the data in a way that takes into account any missing information. It’s tested on some public datasets to show how well it works. |
Keywords
» Artificial intelligence » Clustering » Feature extraction
