你无法忽视任何一方:统一结构与特征去噪以实现鲁棒图学习
You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning
AI总结:
本文提出统一图去噪框架UGD,通过高阶邻域邻近性识别噪声边和图自编码器重构特征,并迭代优化获得干净图,以同时应对图结构与特征中的噪声,实现鲁棒图学习。
摘要:
近年来,关于图神经网络(GNNs)在噪声或攻击下的鲁棒性研究因其在现实应用中的重要性而引起了广泛关注。大多数先前的方法只探索单一噪声源,要么通过可靠的结构偏置来恢复被破坏的节点嵌入,要么利用可靠的节点特征来开展结构学习。然而,图中的噪声和攻击可能同时来自结构和特征,这使得图去噪成为一个两难且具有挑战性的问题。在本文中,我们提出了一个统一的图去噪(UGD)框架,以解开结构去噪与特征去噪之间的僵局。具体而言,考虑到特征可能同时受到扰动,我们提出了一种高阶邻域邻近性评估方法来识别噪声边。此外,我们提出基于图自编码器进行重构以精炼噪声特征。进一步设计了一种迭代更新算法来优化该框架并获得干净的图,从而为下游任务实现鲁棒图学习。我们的UGD框架是自监督的,并且可以轻松地作为即插即用模块实现。我们进行了大量实验,证明了我们方法的有效性和优势。代码可在 https://github.com/YoungTimmy/UGD 获取。
英文摘要:
Recent research on the robustness of Graph Neural Networks (GNNs) under noises or attacks has attracted great attention due to its importance in real-world applications. Most previous methods explore a single noise source, recovering corrupt node embedding by reliable structures bias or developing structure learning with reliable node features. However, the noises and attacks may come from both structures and features in graphs, making the graph denoising a dilemma and challenging problem. In this paper, we develop a unified graph denoising (UGD) framework to unravel the deadlock between structure and feature denoising. Specifically, a high-order neighborhood proximity evaluation method is proposed to recognize noisy edges, considering features may be perturbed simultaneously. Moreover, we propose to refine noisy features with reconstruction based on a graph auto-encoder. An iterative updating algorithm is further designed to optimize the framework and acquire a clean graph, thus enabling robust graph learning for downstream tasks. Our UGD framework is self-supervised and can be easily implemented as a plug-and-play module. We carry out extensive experiments, which proves the effectiveness and advantages of our method. Code is avalaible at https://github.com/YoungTimmy/UGD.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。