针对异质超图神经网络，提出自适应知识蒸馏方法提升学生模型性能。
Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural Networks
- 根据节点异质性动态评估教师模型可靠性，指导知识传递。
- 在多个真实超图数据集上，学生模型性能超越教师，推理速度提升12.3倍。
- 适用于需高效部署的异质超图学习场景，尤其适合资源受限环境。
超图知识蒸馏旨在通过轻量级学生模型降低超图神经网络（HNN）的推理开销，同时保持预测性能。本文发现，当节点通过语义多样的超边连接时，HNN在异质节点上的预测性能显著下降，表明教师知识的可靠性在不同节点间存在差异。受此启发，我们提出HADES——一种面向异质性的自适应蒸馏方法。HADES量化节点异质性，并将其作为教师可靠性的估计值，在蒸馏过程中动态调节知识传递。在真实超图数据集上的实验表明，HADES在多种HNN教师和蒸馏目标下均能持续提升学生模型性能。许多情况下，学生模型的预测性能超过其教师，且推理速度最高提升12.3倍。
原文摘要 · Abstract (English)
Hypergraph knowledge distillation aims to retain the predictive performance of a hypergraph neural network (HNN) teacher while reducing inference costs through a lightweight student model. In this work, we observe that HNNs exhibit substantially lower prediction performance on heterophilic nodes connected through semantically diverse hyperedges, indicating that the reliability of teacher knowledge varies across nodes. Motivated by this observation, we propose HADES, a heterophily-aware adaptive distillation method for hypergraph neural networks. HADES quantifies node heterophily and leverages it as an estimate of teacher reliability to modulate the transfer of teacher knowledge during distillation. Experimental results on real-world hypergraphs demonstrate that HADES consistently improves student performance across different HNN teachers and distillation objectives. In many cases, the resulting student models surpass the predictive performance of their teachers while achieving up to 12.3 times faster inference.
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。