2023/03/12 by Xiaojun Guo, Yifei Wang, Guo, Xiaojun +5 · 4 citations
Computer Science · Neuroscience · #Advanced Graph Neural Networks #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM
paper · pdf · doi:10.48550/arxiv.2303.06562
openalex publication_date 2023/03/12 · openalex created_date 2023/03/16 · openalex updated_date 2026/07/28
Oversmoothing is a common phenomenon in a wide range of Graph Neural Networks (GNNs) and Transformers, where performance worsens as the number of layers increases. Instead of characterizing oversmoothing from the view of complete collapse in which representations converge to a single point, we dive into a more general perspective of dimensional collapse in which representations lie in a narrow cone. Accordingly, inspired by the effectiveness of contrastive learning in preventing dimensional collapse, we propose a novel normalization layer called ContraNorm. Intuitively, ContraNorm implicitly shatters representations in the embedding space, leading to a more uniform distribution and a slighter dimensional collapse. On the theoretical analysis, we prove that ContraNorm can alleviate both complete collapse and dimensional collapse under certain conditions. Our proposed normalization layer can be easily integrated into GNNs and Transformers with negligible parameter overhead. Experiments on various real-world datasets demonstrate the effectiveness of our proposed ContraNorm. Our implementation is available at https://github.com/PKU-ML/ContraNorm.