无需微调模型，用动态词典实现图数据OOD检测
Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries
- 测试时用双动态词典校准异常分数
- 仅用测试样本生成边界感知拓扑，不依赖外部异常数据
- 适合部署在无法获取真实异常样本的场景
图数据的分布外（OOD）检测面临训练阶段缺乏真实异常样本的挑战。现有方法通常只优化对分布内（ID）数据的特征捕捉，难以表征分布边界，导致检测不可靠。此外，图数据的潜在结构常受多重因素影响，尚未充分探索。为此，我们提出一种新型测试时图OOD检测方法BaCa，通过双动态更新词典校准异常分数，无需微调预训练模型。具体而言，BaCa估计图子（graphons），仅使用测试样本进行混合策略生成多样化的边界感知判别拓扑，避免引入辅助异常数据集。通过优先队列与注意力机制构建双动态词典，自适应捕获隐含的ID与OOD表示，并用于边界感知的异常分数校准。据我们所知，大量实验证明，BaCa在真实数据集上显著优于现有最先进方法。
原文摘要 · Abstract (English)
A key challenge in graph out-of-distribution (OOD) detection lies in the absence of ground-truth OOD samples during training. Existing methods are typically optimized to capture features within the in-distribution (ID) data and calculate OOD scores, which often limits pre-trained models from representing distributional boundaries, leading to unreliable OOD detection. Moreover, the latent structure of graph data is often governed by multiple underlying factors, which remains less explored. To address these challenges, we propose a novel test-time graph OOD detection method, termed BaCa, that calibrates OOD scores using dual dynamically updated dictionaries without requiring fine-tuning the pre-trained model. Specifically, BaCa estimates graphons and applies a mix-up strategy solely with test samples to generate diverse boundary-aware discriminative topologies, eliminating the need for exposing auxiliary datasets as outliers. We construct dual dynamic dictionaries via priority queues and attention mechanisms to adaptively capture latent ID and OOD representations, which are then utilized for boundary-aware OOD score calibration. To the best of our knowledge, extensive experiments on real-world datasets show that BaCa significantly outperforms existing state-of-the-art methods in OOD detection.
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。