arXiv cs.AI· Junxian Li, Bin Shi, Erfei Cui, Hua Wei, Qinghua Zheng·· 3 天前AI 评分22
让 MLP 获得更多图信息：三阶段多任务知识蒸馏框架
Teaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework
AI 导读
针对图神经网络在大规模图推理任务中时间和内存开销巨大的问题，研究者提出一种三阶段多任务知识蒸馏框架，通过 Positional Encoding 捕捉位置信息、引入 Neural Heat Kernels 并匹配隐藏层输出，将图知识蒸馏到学生 MLP。
正文 · 原文
Abstract:We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome it by reducing reliance on graph structure. Even though distilling graph knowledge to student MLP is an excellent idea, it faces two major problems of positional information loss and low generalization. To solve the problems, we propose a new three-stage multitask distillation framework. In detail, we use Positional Encoding to capture positional information. Also, we introduce Neural Heat Kernels responsible for graph data processing in GNN and utilize hidden layer outputs matching for better performance of student MLP's hidden layers. To the best of our knowledge, it is the first work to include hidden layer distillation for student MLP on graphs and to combine graph Positional Encoding with MLP. We test its performance and robustness with several settings and draw the conclusion that our work can outperform well with good stability. Code implementation is in this https URL.
| Comments: | 20 pages, with Appendix |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2403.01079 [cs.LG] |
| (or arXiv:2403.01079v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2403.01079 arXiv-issued DOI via DataCite |
Submission history
From: Junxian Li [view email]
[v1]
Sat, 2 Mar 2024 03:29:11 UTC (1,780 KB)
[v2]
Sun, 11 Oct 2026 15:31:27 UTC (1,091 KB)
来源：arXiv cs.AI · arxiv.org