{"title":"对非 IID 批次进行加权,以检测配送外情况","authors":"Zhilin Zhao, Longbing Cao","doi":"10.1007/s10994-024-06605-z","DOIUrl":null,"url":null,"abstract":"<p>A standard network pretrained on in-distribution (ID) samples could make high-confidence predictions on out-of-distribution (OOD) samples, leaving the possibility of failing to distinguish ID and OOD samples in the test phase. To address this over-confidence issue, the existing methods improve the OOD sensitivity from modeling perspectives, i.e., retraining it by modifying training processes or objective functions. In contrast, this paper proposes a simple but effective method, namely Weighted Non-IID Batching (WNB), by adjusting batch weights. WNB builds on a key observation: increasing the batch size can improve the OOD detection performance. This is because a smaller batch size may make its batch samples more likely to be treated as non-IID from the assumed ID, i.e., associated with an OOD. This causes a network to provide high-confidence predictions for all samples from the OOD. Accordingly, WNB applies a weight function to weight each batch according to the discrepancy between batch samples and the entire training ID dataset. Specifically, the weight function is derived by minimizing the generalization error bound. It ensures that the weight function assigns larger weights to batches with smaller discrepancies and makes a trade-off between ID classification and OOD detection performance. Experimental results show that incorporating WNB into state-of-the-art OOD detection methods can further improve their performance.</p>","PeriodicalId":49900,"journal":{"name":"Machine Learning","volume":"267 1","pages":""},"PeriodicalIF":4.3000,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Weighting non-IID batches for out-of-distribution detection\",\"authors\":\"Zhilin Zhao, Longbing Cao\",\"doi\":\"10.1007/s10994-024-06605-z\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>A standard network pretrained on in-distribution (ID) samples could make high-confidence predictions on out-of-distribution (OOD) samples, leaving the possibility of failing to distinguish ID and OOD samples in the test phase. To address this over-confidence issue, the existing methods improve the OOD sensitivity from modeling perspectives, i.e., retraining it by modifying training processes or objective functions. In contrast, this paper proposes a simple but effective method, namely Weighted Non-IID Batching (WNB), by adjusting batch weights. WNB builds on a key observation: increasing the batch size can improve the OOD detection performance. This is because a smaller batch size may make its batch samples more likely to be treated as non-IID from the assumed ID, i.e., associated with an OOD. This causes a network to provide high-confidence predictions for all samples from the OOD. Accordingly, WNB applies a weight function to weight each batch according to the discrepancy between batch samples and the entire training ID dataset. Specifically, the weight function is derived by minimizing the generalization error bound. It ensures that the weight function assigns larger weights to batches with smaller discrepancies and makes a trade-off between ID classification and OOD detection performance. Experimental results show that incorporating WNB into state-of-the-art OOD detection methods can further improve their performance.</p>\",\"PeriodicalId\":49900,\"journal\":{\"name\":\"Machine Learning\",\"volume\":\"267 1\",\"pages\":\"\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-08-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Machine Learning\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s10994-024-06605-z\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine Learning","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s10994-024-06605-z","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
摘要
对分布内(ID)样本进行预训练的标准网络可以对分布外(OOD)样本进行高置信度预测,但在测试阶段可能无法区分 ID 和 OOD 样本。为解决这一过度置信问题,现有方法从建模角度提高了 OOD 灵敏度,即通过修改训练过程或目标函数对其进行再训练。相比之下,本文提出了一种简单而有效的方法,即通过调整批次权重来实现加权非 IID 批处理(WNB)。WNB 基于一个重要的观察结果:增加批次大小可以提高 OOD 检测性能。这是因为,较小的批次规模可能会使其批次样本更有可能从假定的 ID 被视为非 IID,即与 OOD 相关联。这将导致网络对来自 OOD 的所有样本提供高置信度预测。因此,WNB 根据批次样本与整个训练 ID 数据集之间的差异,应用加权函数对每个批次进行加权。具体来说,权重函数是通过最小化泛化误差边界得出的。它确保权重函数为差异较小的批次分配较大的权重,并在 ID 分类和 OOD 检测性能之间做出权衡。实验结果表明,将 WNB 纳入最先进的 OOD 检测方法可以进一步提高其性能。
Weighting non-IID batches for out-of-distribution detection
A standard network pretrained on in-distribution (ID) samples could make high-confidence predictions on out-of-distribution (OOD) samples, leaving the possibility of failing to distinguish ID and OOD samples in the test phase. To address this over-confidence issue, the existing methods improve the OOD sensitivity from modeling perspectives, i.e., retraining it by modifying training processes or objective functions. In contrast, this paper proposes a simple but effective method, namely Weighted Non-IID Batching (WNB), by adjusting batch weights. WNB builds on a key observation: increasing the batch size can improve the OOD detection performance. This is because a smaller batch size may make its batch samples more likely to be treated as non-IID from the assumed ID, i.e., associated with an OOD. This causes a network to provide high-confidence predictions for all samples from the OOD. Accordingly, WNB applies a weight function to weight each batch according to the discrepancy between batch samples and the entire training ID dataset. Specifically, the weight function is derived by minimizing the generalization error bound. It ensures that the weight function assigns larger weights to batches with smaller discrepancies and makes a trade-off between ID classification and OOD detection performance. Experimental results show that incorporating WNB into state-of-the-art OOD detection methods can further improve their performance.
期刊介绍:
Machine Learning serves as a global platform dedicated to computational approaches in learning. The journal reports substantial findings on diverse learning methods applied to various problems, offering support through empirical studies, theoretical analysis, or connections to psychological phenomena. It demonstrates the application of learning methods to solve significant problems and aims to enhance the conduct of machine learning research with a focus on verifiable and replicable evidence in published papers.