发现链接预测模型依赖批处理偏差，导致泛化能力被高估。
Mini-Batch Class Composition Bias in Link Prediction
- 模型通过批归一化学到与批次相关的简单规则
- 修正后表示与节点分类特征对齐度显著提升
- 提醒研究者警惕训练方式对模型泛化性的误导
先前研究表明，图神经网络（GNN）在共享图属性的场景下可学习跨图迁移的表示。对于固定图，我们预期链接预测训练出的表示应与节点分类一致。然而我们发现该直觉在一般情况下不成立。主流链接预测模型能利用批归一化层，学习一种依赖于小批量数据的平凡启发式规则来完成边分类任务。在纠正此偏差后，观察到网络表示与节点类别相关特征的对齐度显著提高，表明模型学到了更符合图固有属性的表示。结果表明，标准链接预测训练可能使我们高估了链接预测器学习通用图表示的能力。
原文摘要 · Abstract (English)
Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that learnt for node classification. We show this intuition does not hold in the general case. Instead, we find popular link prediction models can learn a trivial mini-batch dependent heuristic, enabled by batch-normalisation layers, to solve the edge classification task. When correcting for this, we observe increased alignment of the network representation with node-class relevant features, suggesting the network has learnt a graph representation that better aligns with the underlying graph's properties. Our findings suggest that standard link prediction training may be leading us to overestimate link predictors' ability to learn a generalised representation of a graph that is consistent across tasks.
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。