Summary of Graph Neural Networks with Coarse- and Fine-grained Division For Mitigating Label Sparsity and Noise, by Shuangjie Li et al.
Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise
by Shuangjie Li, Baoming Zhang, Jianqing Song, Gaoli Ruan, Chongjun Wang, Junyuan Xie
First submitted to arxiv on: 6 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This research proposes a novel Graph Neural Network (GNN) architecture called GNN-CFGD that addresses the challenges of noisy and sparse labels in semi-supervised node classification tasks. The key innovation is a coarse- and fine-grained division approach to reduce the impact of noisy labels, along with graph reconstruction. This involves linking unlabeled nodes to cleanly labeled nodes, using a Gaussian Mixture Model (GMM) based on the memory effect to identify clean and noisy labels, and fine-graining noisy labeled and unlabeled nodes into two candidate sets based on confidence. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops a new type of Graph Neural Network that can handle noisy and sparse labels. The idea is to divide the data into clean and noisy parts, then use this information to help train the model. This makes it better at learning from the data it has, even if some of it might be wrong. The researchers tested their approach on different datasets and found that it worked well. |
Keywords
» Artificial intelligence » Classification » Gnn » Graph neural network » Mixture model » Semi supervised
