无需负采样，用谱信号增强图表示学习
Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations
- 利用谱归一化优化生成结构增强数据
- 在多个基准上超越现有自监督方法
- 适合需要高效图表示的学习场景
我们提出LaplaceGNN，一种新型自监督图学习框架，通过谱自举技术避免负采样。该方法将拉普拉斯信号融入学习过程，无需对比目标或手工设计增强，即可有效捕捉丰富的结构表征。通过聚焦正样本对齐，LaplaceGNN实现线性扩展，提供更简单高效的自监督替代方案，适用于多种领域。主要贡献有二：一是通过最大最小中心性引导的优化预计算谱增强，实现无需手工设计的丰富结构监督；二是引入对抗性自举训练机制，进一步强化特征学习与鲁棒性。在多个基准数据集上的广泛实验表明，LaplaceGNN在性能上优于当前最优的自监督图学习方法，为高效学习表达性强的图表示提供了新方向。
原文摘要 · Abstract (English)
We present LaplaceGNN, a novel self-supervised graph learning framework that bypasses the need for negative sampling by leveraging spectral bootstrapping techniques. Our method integrates Laplacian-based signals into the learning process, allowing the model to effectively capture rich structural representations without relying on contrastive objectives or handcrafted augmentations. By focusing on positive alignment, LaplaceGNN achieves linear scaling while offering a simpler, more efficient, self-supervised alternative for graph neural networks, applicable across diverse domains. Our contributions are twofold: we precompute spectral augmentations through max-min centrality-guided optimization, enabling rich structural supervision without relying on handcrafted augmentations, then we integrate an adversarial bootstrapped training scheme that further strengthens feature learning and robustness. Our extensive experiments on different benchmark datasets show that LaplaceGNN achieves superior performance compared to state-of-the-art self-supervised graph methods, offering a promising direction for efficiently learning expressive graph representations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。