用启发式方法教MLP做图链接预测，效果更好且更快。
Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction
- 用启发式方法替代复杂GNN做教师模型，降低训练成本。
- 在10个数据集上平均性能提升7.93%，训练时间减少1.95至3.32倍。
- 适合追求高效高精度链接预测的工业应用和资源受限场景。
链接预测是图学习中的关键任务，广泛应用于引文预测与产品推荐。将图神经网络（GNN）教师模型蒸馏为无图依赖的多层感知机（MLP）学生模型，可实现高性能并降低计算开销。然而现有方法仅使用标准GNN作为教师，忽视了专门针对链接预测的GNN4LP及启发式方法（如共同邻居）。本文首次探索不同教师对GNN到MLP蒸馏的影响。令人意外的是，更强的教师并不总能产出更强的学生：从GNN4LP蒸馏出的MLP反而可能劣于从简单GNN蒸馏的结果；而更弱的启发式方法却能使MLP达到接近GNN的性能，且训练成本大幅下降。基于此，我们提出集成启发式蒸馏的MLP（EHDM），通过门控机制融合互补信号，彻底消除图依赖。在10个数据集上的实验表明，相比先前方法平均提升7.93%，训练时间减少1.95–3.32倍，验证了EHDM在效率与性能上的优越性。代码已开源。
原文摘要 · Abstract (English)
Link prediction is a crucial graph-learning task with applications including citation prediction and product recommendation. Distilling Graph Neural Networks (GNNs) teachers into Multi-Layer Perceptrons (MLPs) students has emerged as an effective approach to achieve strong performance and reducing computational cost by removing graph dependency. However, existing distillation methods only use standard GNNs and overlook alternative teachers such as specialized model for link prediction (GNN4LP) and heuristic methods (e.g., common neighbors). This paper first explores the impact of different teachers in GNN-to-MLP distillation. Surprisingly, we find that stronger teachers do not always produce stronger students: MLPs distilled from GNN4LP can underperform those distilled from simpler GNNs, while weaker heuristic methods can teach MLPs to near-GNN performance with drastically reduced training costs. Building on these insights, we propose Ensemble Heuristic-Distilled MLPs (EHDM), which eliminates graph dependencies while effectively integrating complementary signals via a gating mechanism. Experiments on ten datasets show an average 7.93% improvement over previous GNN-to-MLP approaches with 1.95-3.32 times less training time, indicating EHDM is an efficient and effective link prediction method. Our code is available at https://github.com/ZongyueQin/EHDM
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。