论文标题
贝叶斯强大的图形对比度学习
Bayesian Robust Graph Contrastive Learning
论文作者
论文摘要
图形神经网络（GNN）已被广泛用于学习节点表示，并且在各种任务（例如节点分类）上具有出色的性能。但是，在现实世界图数据中不可避免地存在噪声会大大降低GNN的性能，因为通过图形结构很容易传播噪声。在这项工作中，我们提出了一种新颖而健壮的方法，即贝叶斯强大的图形对比度学习（BRGCL），该方法训练GNN编码器学习稳健的节点表示。 BRGCL编码器是一个完全无监督的编码器。在训练BRGCL编码器的每个时期，都会迭代执行两个步骤：（1）通过一种新型的贝叶斯非参数方法来估计节点表示的自信节点和鲁棒群集原型； （2）节点表示与稳健簇原型之间的原型对比度学习。公共和大规模基准的实验证明了BRGCL的出色性能以及学习的节点表示的鲁棒性。 BRGCL的代码可在\ url {https://github.com/brgcl-code/brgcl-code}上获得。
Graph Neural Networks (GNNs) have been widely used to learn node representations and with outstanding performance on various tasks such as node classification. However, noise, which inevitably exists in real-world graph data, would considerably degrade the performance of GNNs as the noise is easily propagated via the graph structure. In this work, we propose a novel and robust method, Bayesian Robust Graph Contrastive Learning (BRGCL), which trains a GNN encoder to learn robust node representations. The BRGCL encoder is a completely unsupervised encoder. Two steps are iteratively executed at each epoch of training the BRGCL encoder: (1) estimating confident nodes and computing robust cluster prototypes of node representations through a novel Bayesian nonparametric method; (2) prototypical contrastive learning between the node representations and the robust cluster prototypes. Experiments on public and large-scale benchmarks demonstrate the superior performance of BRGCL and the robustness of the learned node representations. The code of BRGCL is available at \url{https://github.com/BRGCL-code/BRGCL-code}.
