.png){kind=icon}
返回
GNN Cleaner: Label Cleaner for Graph Structured Data
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2023.3288002.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph Neural Network (GNN) has emerged as a predominant tool for graph data analysis. Despite their proliferation, the low-quality labels of many real-world graphs will undermine their performance dramatically. Existing studies on learning neural networks with noisy labels mainly focus on independent data and thus cannot fully exploit the structural information of graph data. Currently, there are few studies of robustness to noisy labels for graph-structured data even if this problem is commonly seen in real-world settings. To remedy this deficiency, we propose GNN Cleaner which utilizes structural information of graph data to combat noisy labels. More specifically, a pseudo label is computed from the neighboring labels for each node in the training set via a modified version of label propagation. Additionally, a novel method is developed to learn to correct the labels adaptively and dynamically. Extensive experiments show that GNN Cleaner can train GNNs robustly and correct both the synthetic and real-world noisy labels even if the noise is severe. Moreover, GNN Cleaner is model-agnostic and can be combined with various GNNs to improve their robustness against label noise.
Keyword:
Data cleaning
graph neural networks
node classification
noisy labels
robustness
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
In Situ IgM Production and Clonal Expansion of B-1 Cells in Peritoneal Cavity Promote Elimination of C. albicans Infection in IgH Transgenic Mice with VH Derived from a Natural Antibody.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏
A novel and efficient xanthenic dye–organometallic ion‐pair complex for photoinitiating polymerization一种用于光引发聚合的新型高效的黄原胶染料-有机金属离子对配合物
PREAI
分享收藏分享收藏
查看更多内容