paper-with-me

Papers

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

2023-03-24 · Taiqiang Wu, Zhe Zhao, Jiahao Wang, Xingyu Bai, Lei Wang, Ngai Wong, Yujiu Yang

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 nodes and fails to effectively capture the graph structural information. Previous methods address this issue by processing graph edges into extra inputs for MLPs, but such graph structures may be unavailable for various scenarios. To this end, we propose Prototype-Guided Knowledge Distillation (PGKD), which does not require graph edges (edge-free setting) yet learns structure-aware MLPs. Our insight is to distill graph structural information from GNNs. Specifically, we first employ the class prototypes to analyze the impact of graph structures on GNN teachers, and then design two losses to distill such information from GNNs to MLPs. Experimental results on popular graph benchmarks demonstrate the effectiveness and robustness of the proposed PGKD.

📄 PDF Abstract BibTeX arXiv:2303.13763

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Physics-Informed Structure Anchoring With Capture-Aware Prototype Calibration for Cross-Environment RF Fingerprinting

2026-07-06 · Fengchong Yao, Jianbing Li, Qing Liu, Qikun Liu 외 arxiv

Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Internet of Things (IoT) devices, but deep models often degrade across acquisition…

Representation Learning

Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation

2024-03-12 · CVPR 2024 1 · Feilong Tang, Zhongxing Xu, Zhaojun Qu, Wei Feng 외

Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between …

Learning TheorySemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation

2026-06-02 · Ankang Yang, Jitao Zhao, Dongxiao He, Liang Yang 외 arxiv

Graph foundation models aim to learn transferable knowledge from diverse graphs for generalization to unseen graphs and tasks. Unlike text and images, graphs lack a shared vocabulary or regular spatial grid, making cross…

Domain Generalization

Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning

2023-06-02 · Yihong Cao, HUI ZHANG, Xiao Lu, Zheng Xiao 외

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage…

Domain AdaptationSegmentationSemantic SegmentationSource-Free Domain Adaptation+1

Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting

2026-03-12 · Chantal Pellegrini, Adrian Delchev, Ege Özsoy, Nassir Navab 외 arxiv

Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decisions about rare findings and attributes …