调优后的GAE在链接预测上表现媲美新模型，且更快更省资源。
Reconsidering the Performance of GAE in Link Prediction
- 通过调参和通用优化技巧提升GAE性能。
- 在ogbl-ppa数据集上达78.41% Hits@100，为当前最优。
- 适合关注高效基线或结构信息主导场景的研究者。
近期图神经网络（GNN）在链接预测方面引入了复杂的训练方法与模型架构，但依赖过时基线可能夸大新方法的优势。为此，我们系统性地研究图自编码器（GAE），应用近期方法中的模型无关技巧并优化超参数。结果表明，经过良好调优的GAE可达到近期复杂模型的性能，同时在主流链接预测基准上具备更优的计算效率。该方法在结构信息主导、特征数据有限的数据集上表现显著提升。特别地，在ogbl-ppa数据集上，我们的GAE达到78.41%的Hits@100，创下新纪录。此外，我们分析了各类技巧的影响，揭示成功原因，为未来方法设计提供指导。本研究强调更新基线对准确评估GNN进展至关重要。代码已开源：https://github.com/GraphPKU/Refined-GAE。
原文摘要 · Abstract (English)
Recent advancements in graph neural networks (GNNs) for link prediction have introduced sophisticated training techniques and model architectures. However, reliance on outdated baselines may exaggerate the benefits of these new approaches. To tackle this issue, we systematically explore Graph Autoencoders (GAEs) by applying model-agnostic tricks in recent methods and tuning hyperparameters. We find that a well-tuned GAE can match the performance of recent sophisticated models while offering superior computational efficiency on widely-used link prediction benchmarks. Our approach delivers substantial performance gains on datasets where structural information dominates and feature data is limited. Specifically, our GAE achieves a state-of-the-art Hits@100 score of 78.41\% on the ogbl-ppa dataset. Furthermore, we examine the impact of various tricks to uncover the reasons behind our success and to guide the design of future methods. Our study emphasizes the critical need to update baselines for a more accurate assessment of progress in GNNs for link prediction. Our code is available at https://github.com/GraphPKU/Refined-GAE.
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。