利用特征共振检测图数据中的分布外节点,无需标签即可实现高精度识别。
Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
- 基于特征向量在训练步中的移动变化,构建微粒级共振代理指标。
- 在13个真实图数据集上达到当前最优效果,显著提升分布外节点分离能力。
- 适用于无标签场景,特别适合缺乏类别标注的图学习任务。
图神经网络中检测分布外(OOD)节点极具挑战性,尤其当真实类别标签不可用时。本文转而关注特征空间,发现即使模型被训练为拟合随机目标,已知的内分布(ID)样本在优化过程中仍会引发未知ID样本的特征表示产生比OOD样本更显著的变化,这一现象称为特征共振。其原理在于局部流形仍可能保持平滑响应。基于此,提出新型图级OOD检测框架RSL,包含两个核心模块:(i) 一个更实用的微观层面特征共振代理,用于度量单次训练中特征向量的移动;(ii) 结合合成的OOD节点策略,训练出高效的分类器。理论推导表明,在共振阶段OOD节点具有更强可分性。在总计十三个真实图数据集上的大量实验验证了RSL性能领先于现有方法。
原文摘要 · Abstract (English)
Detecting out-of-distribution (OOD) nodes in the graph-based machine-learning field is challenging, particularly when in-distribution (ID) node multi-category labels are unavailable. Thus, we focus on feature space rather than label space and find that, ideally, during the optimization of known ID samples, unknown ID samples undergo more significant representation changes than OOD samples, even if the model is trained to fit random targets, which we called the Feature Resonance phenomenon. The rationale behind it is that even without gold labels, the local manifold may still exhibit smooth resonance. Based on this, we further develop a novel graph OOD framework, dubbed Resonance-based Separation and Learning (RSL), which comprises two core modules: (i) a more practical micro-level proxy of feature resonance that measures the movement of feature vectors in one training step. (ii) integrate with synthetic OOD nodes strategy to train an effective OOD classifier. Theoretically, we derive an error bound showing the superior separability of OOD nodes during the resonance period. Extensive experiments on a total of thirteen real-world graph datasets empirically demonstrate that RSL achieves state-of-the-art performance.
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。