تقرير
CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection
| العنوان: | CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection |
|---|---|
| المؤلفون: | Li, Yifan, Tan, Zhen, Shu, Kai, Cao, Zongsheng, Kong, Yu, Liu, Huan |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
| الوصف: | Graph Neural Networks (GNNs) have emerged as a powerful tool for representation learning on graphs, but they often suffer from overfitting and label noise issues, especially when the data is scarce or imbalanced. Different from the paradigm of previous methods that rely on single-node confidence, in this paper, we introduce a novel Class-wise Selection for Graph Neural Networks, dubbed CSGNN, which employs a neighbor-aggregated latent space to adaptively select reliable nodes across different classes. Specifically, 1) to tackle the class imbalance issue, we introduce a dynamic class-wise selection mechanism, leveraging the clustering technique to identify clean nodes based on the neighbor-aggregated confidences. In this way, our approach can avoid the pitfalls of biased sampling which is common with global threshold techniques. 2) To alleviate the problem of noisy labels, built on the concept of the memorization effect, CSGNN prioritizes learning from clean nodes before noisy ones, thereby iteratively enhancing model performance while mitigating label noise. Through extensive experiments, we demonstrate that CSGNN outperforms state-of-the-art methods in terms of both effectiveness and robustness. Comment: For the privacy issue |
| نوع الوثيقة: | Working Paper |
| الوصول الحر: | http://arxiv.org/abs/2311.11473Test |
| رقم الانضمام: | edsarx.2311.11473 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |