Graph neural networks have achieved strong performance on graph-structured data, but their effectiveness depends heavily on the quality of the observed graph. In real applications, graph topology is often imperfect: noisy edges may connect unrelated nodes, while missing edges may prevent useful information from being propagated. Existing robust graph learning methods mainly address this problem by removing suspicious edges or by learning a new graph structure during training. However, edge removal alone cannot recover missing connections, and graph structure learning may introduce additional optimization complexity. In this paper, we propose Topology-Aware Gaussian Repair (TAGR), a simple graph repair framework for robust message passing in graph neural networks. Instead of learning a dense adjacency matrix, TAGR constructs a sparse feature-neighborhood graph using an adaptive Gaussian kernel and combines it with a topology-aware residual correction of the observed graph. The Gaussian repair component introduces auxiliary edges between feature-similar nodes, while the residual correction preserves and reweights the original topology according to local feature and structural consistency. The repaired graph can be used directly with standard graph neural networks without changing their architectures. Extensive experiments on benchmark citation networks show that TAGR improves the robustness of GNNs under both noisy-edge and missing-edge settings. The analysis further show that Gaussian feature-neighborhood repair provides the main robustness gain, while topology-aware residual correction improves stability when the observed graph is incomplete. These results suggest that effective graph robustness can be achieved through lightweight sparse graph repair rather than dense graph structure learning.
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
State Key Lab of Processors, Institute of Computing Technology, CAS（中国科学院计算技术研究所处理器芯片国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Microelectronics, CAS（中国科学院微电子研究所）
Overcoming Representation Bias in Fairness-Aware data Repair using Optimal Transport
Dyson School of Design Engineering, Imperial College London（帝国理工学院伦敦分校设计工程学院）；Department of Electronic and Electrical Engineering, Trinity College Dublin（都柏林信任学院电子与电气工程系）
ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning
Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet（深圳市下一代工业互联网安全重点实验室）；Department of Statistics and Data Science, Southern University of Science and Technology（南方科技大学统计与数据科学系）
RES-DARE: Failure-Aware Expert Adaptation and Rollback-Safe Self-Repair for Intrusion Detection
Department of Computer Science（计算机科学系）；Jamia Hamdard（贾迈亚·哈姆达德）；Kalinga Institute of Industrial Technology（卡林加工业技术学院）；Department of Computer Science and Business Systems（计算机科学与商业系统系）；Gargi Memorial Institute of Technology（加里纪念技术学院）；Maulana Abul Kalam Azad University of Technology（穆拉纳·阿卜杜勒·卡里姆·阿扎德技术大学）；Homi Bhabha National Institute（霍米·巴哈瓦国家研究所）；Computer and Informatics Group（计算机与信息组）；Variable Energy Cyclotron Centre（变能回旋加速器中心）
Foundation University（费登大学）；Ton Duc Thang University（同塔大学）；Wuhan University（武汉大学）；Wuhan University of Technology（武汉理工大学）；Palestine Technical University（巴勒斯坦技术大学）；Oxford Brookes University（牛津布鲁克斯大学）；Obuda University（欧布达大学）；Bauhaus University Weimar（魏玛包豪斯大学）
