用经典算法预训练图神经网络，提升分子性质预测准确率
Leveraging Classical Algorithms for Graph Neural Networks
- 用24种经典算法预训练GNN，再冻结部分层用于分子任务
- 在ogbg-molhiv上最高提升6%，ogbg-molclintox上提升3%
- 适合研究图神经网络泛化与算法先验融合的学者
神经网络擅长处理非结构化数据，但常在分布外数据上表现不佳；经典算法虽保证正确性，却缺乏灵活性。本文探索在经典算法上预训练图神经网络（GNN）是否能提升其在分子性质预测任务上的表现。实验使用来自CLRS算法推理基准的24种经典算法对GNN进行预训练，并将部分层初始化并冻结，用于后续分子预测任务。在Open Graph Benchmark的ogbg-molhiv（HIV抑制）和ogbg-molclintox（临床毒性）任务中，相比随机初始化基线，预训练模型均取得一致胜势或持平。其中，以Segments Intersect算法预训练在ogbg-molhiv上实现6%的绝对性能提升，而Dijkstra算法预训练在ogbg-molclintox上带来3%的提升。结果表明，将经典算法先验嵌入GNN可提供有效归纳偏置，显著提升复杂真实图数据上的性能。
原文摘要 · Abstract (English)
Neural networks excel at processing unstructured data but often fail to generalise out-of-distribution, whereas classical algorithms guarantee correctness but lack flexibility. We explore whether pretraining Graph Neural Networks (GNNs) on classical algorithms can improve their performance on molecular property prediction tasks from the Open Graph Benchmark: ogbg-molhiv (HIV inhibition) and ogbg-molclintox (clinical toxicity). GNNs trained on 24 classical algorithms from the CLRS Algorithmic Reasoning Benchmark are used to initialise and freeze selected layers of a second GNN for molecular prediction. Compared to a randomly initialised baseline, the pretrained models achieve consistent wins or ties, with the Segments Intersect algorithm pretraining yielding a 6% absolute gain on ogbg-molhiv and Dijkstra pretraining achieving a 3% gain on ogbg-molclintox. These results demonstrate embedding classical algorithmic priors into GNNs provides useful inductive biases, boosting performance on complex, real-world graph data.
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。