paper-with-me

홈 › Papers

NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs

2022-08-22 · Yijun Tian, Chuxu Zhang, Zhichun Guo, Xiangliang Zhang, Nitesh V. Chawla

While Graph Neural Networks (GNNs) have demonstrated their efficacy in dealing with non-Euclidean structural data, they are difficult to be deployed in real applications due to the scalability constraint imposed by multi-hop data dependency. Existing methods attempt to address this scalability issue by training multi-layer perceptrons (MLPs) exclusively on node content features using labels derived from trained GNNs. Even though the performance of MLPs can be significantly improved, two issues prevent MLPs from outperforming GNNs and being used in practice: the ignorance of graph structural information and the sensitivity to node feature noises. In this paper, we propose to learn NOise-robust Structure-aware MLPs On Graphs (NOSMOG) to overcome the challenges. Specifically, we first complement node content with position features to help MLPs capture graph structural information. We then design a novel representational similarity distillation strategy to inject structural node similarities into MLPs. Finally, we introduce the adversarial feature augmentation to ensure stable learning against feature noises and further improve performance. Extensive experiments demonstrate that NOSMOG outperforms GNNs and the state-of-the-art method in both transductive and inductive settings across seven datasets, while maintaining a competitive inference efficiency. Codes are available at https://github.com/meettyj/NOSMOG.

📄 PDF Abstract BibTeX arXiv:2208.10010

Code (2)

meettyj/nosmog 공식 구현 pytorch
rufaim/routing-by-memory pytorch

Similar Papers 제목 키워드 기반

SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP

2022-10-18 · Jie Chen, Shouzhen Chen, Mingyuan Bai, Junbin Gao 외

The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and aggregation in message-passing cause infere…

Knowledge DistillationNode Classification

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs

2023-03-24 · Taiqiang Wu, Zhe Zhao, Jiahao Wang, Xingyu Bai 외

Distilling high-accuracy Graph Neural Networks (GNNs) to low-latency multilayer perceptions (MLPs) on graph tasks has become a hot research topic. However, conventional MLP learning relies almost exclusively on graph nod…

Knowledge Distillation

Training MLPs on Graphs without Supervision

2024-12-05 · Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye

Graph Neural Networks (GNNs) have demonstrated their effectiveness in various graph learning tasks, yet their reliance on neighborhood aggregation during inference poses challenges for deployment in latency-sensitive app…

Fraud DetectionGraph ClassificationGraph LearningInductive Bias+3

SimMLP: Training MLPs on Graphs without Supervision

2024-02-14 · Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye

Graph Neural Networks (GNNs) have demonstrated their effectiveness in various graph learning tasks, yet their reliance on neighborhood aggregation during inference poses challenges for deployment in latency-sensitive app…

Fraud DetectionGraph ClassificationGraph LearningInductive Bias+3

On Graph Neural Networks versus Graph-Augmented MLPs

2020-10-28 · ICLR 2021 1 · Lei Chen, Zhengdao Chen, Joan Bruna

From the perspective of expressive power, this work compares multi-layer Graph Neural Networks (GNNs) with a simplified alternative that we call Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments nod…

Community DetectionIsomorphism Testing