提出联合去噪框架RIDGE，提升有符号图神经网络在噪声下的鲁棒性。
Toward Robust Signed Graph Learning through Joint Input-Target Denoising
- 通过重参数化与变分近似，同时净化输入图和监督目标中的噪声
- 在四个数据集上验证，不同噪声水平下均显著提升主流SGNN的性能
- 首个理论指导的有符号图学习去噪框架，适合噪声数据场景应用
有符号图神经网络（SGNN）广泛用于分析包含正负边的复杂图结构。由于现实连接具有噪声特性，SGNN的鲁棒性成为关键研究方向。尽管基于经验性质的图结构学习已展现一定鲁棒性，但缺乏理论指导的鲁棒SGNN研究仍较匮乏。受图信息瓶颈（GIB）在信息提取中成功启发，本文提出RIDGE：一种通过联合输入与目标去噪实现鲁棒有符号图学习的新框架。不同于基础GIB，RIDGE扩展了理论能力，支持目标空间噪声去除，因输入与目标空间均存在噪声。具体实现中，通过重参数化机制与变分近似构建可计算的目标函数，有效净化输入数据与监督目标。在四个主流有符号图数据集上进行充分验证，结果表明，在多种噪声水平下，RIDGE显著提升了现有主流SGNN模型的鲁棒性。
原文摘要 · Abstract (English)
Signed Graph Neural Networks (SGNNs) are widely adopted to analyze complex patterns in signed graphs with both positive and negative links. Given the noisy nature of real-world connections, the robustness of SGNN has also emerged as a pivotal research area. Under the supervision of empirical properties, graph structure learning has shown its robustness on signed graph representation learning, however, there remains a paucity of research investigating a robust SGNN with theoretical guidance. Inspired by the success of graph information bottleneck (GIB) in information extraction, we propose RIDGE, a novel framework for Robust sI gned graph learning through joint Denoising of Graph inputs and supervision targEts. Different from the basic GIB, we extend the GIB theory with the capability of target space denoising as the co-existence of noise in both input and target spaces. In instantiation, RIDGE effectively cleanses input data and supervision targets via a tractable objective function produced by reparameterization mechanism and variational approximation. We extensively validate our method on four prevalent signed graph datasets, and the results show that RIDGE clearly improves the robustness of popular SGNN models under various levels of noise.
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。