论文标题
维也纳图形网络改进图表自我监督学习
Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning
论文作者
论文摘要
图表自我监督学习（SSL）已被大大使用，从未标记的图表学习表示形式。现有方法可以大致分为预测性学习和对比学习，在这种学习中，后者以更好的经验表现吸引了更多的研究注意力。我们认为，与对比模型相比，用强大的解码器武器武器武器的预测模型可以实现可比较甚至更好的表示能力。在这项工作中，我们提出了一个Wiener Graph Deoncolutional网络（WGDN），这是一种增强自适应解码器，由Graph Wiener Filter授权以执行信息重建。理论分析证明了图形滤波器的出色重建能力。各种数据集的广泛实验结果证明了我们方法的有效性。
Graph self-supervised learning (SSL) has been vastly employed to learn representations from unlabeled graphs. Existing methods can be roughly divided into predictive learning and contrastive learning, where the latter one attracts more research attention with better empirical performance. We argue that, however, predictive models weaponed with powerful decoder could achieve comparable or even better representation power than contrastive models. In this work, we propose a Wiener Graph Deconvolutional Network (WGDN), an augmentation-adaptive decoder empowered by graph wiener filter to perform information reconstruction. Theoretical analysis proves the superior reconstruction ability of graph wiener filter. Extensive experimental results on various datasets demonstrate the effectiveness of our approach.
