|国家预印本平台
首页|Learn Beneficial Noise as Graph Augmentation

Learn Beneficial Noise as Graph Augmentation

Learn Beneficial Noise as Graph Augmentation

来源:Arxiv_logoArxiv
英文摘要

Although graph contrastive learning (GCL) has been widely investigated, it is still a challenge to generate effective and stable graph augmentations. Existing methods often apply heuristic augmentation like random edge dropping, which may disrupt important graph structures and result in unstable GCL performance. In this paper, we propose Positive-incentive Noise driven Graph Data Augmentation (PiNGDA), where positive-incentive noise (pi-noise) scientifically analyzes the beneficial effect of noise under the information theory. To bridge the standard GCL and pi-noise framework, we design a Gaussian auxiliary variable to convert the loss function to information entropy. We prove that the standard GCL with pre-defined augmentations is equivalent to estimate the beneficial noise via the point estimation. Following our analysis, PiNGDA is derived from learning the beneficial noise on both topology and attributes through a trainable noise generator for graph augmentations, instead of the simple estimation. Since the generator learns how to produce beneficial perturbations on graph topology and node attributes, PiNGDA is more reliable compared with the existing methods. Extensive experimental results validate the effectiveness and stability of PiNGDA.

Siqi Huang、Yanchen Xu、Hongyuan Zhang、Xuelong Li

计算技术、计算机技术

Siqi Huang,Yanchen Xu,Hongyuan Zhang,Xuelong Li.Learn Beneficial Noise as Graph Augmentation[EB/OL].(2025-05-25)[2025-07-03].https://arxiv.org/abs/2505.19024.点此复制

评论