面向不平衡时间序列分类的局部参考几何残差增强
Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification
浏览论文内容
中文总结 AI 辅助
针对不平衡时间序列分类中少数类特征空间局部可靠性不足的问题，提出LRG模块，通过增强特征提升分类性能，验证其在多类表示及高风险区域的有效性。
中文摘要 AI 辅助
不平衡时间序列分类通常通过调整训练分布、目标函数、logits或最终阈值来解决。这些干预措施针对了重要偏差，但未衡量表示层面的问题：在少数类样本支持减少后，学习到的特征空间在少数类区域周围是否仍保持局部可靠性？我们发现一种训练局部几何失效现象：在不平衡情况下，即使表示保留了有用的全局类结构，少数类样本也可能位于稀疏、多数类主导或混合的特征空间邻域中。为诊断并修复该失效，我们提出局部参考几何（Local Reference Geometry, LRG），这是一种轻量级事后特征增强模块，应用于固定特征提取器与分类器头之间。仅使用训练特征，LRG测量局部暴露度和类混合风险，随后为每个固定特征添加来自附近训练几何的标准化有符号位移，以及LDA投影的残差摘要。在受控的UCR/Bake Off Redux不平衡基准上，原始特征与LRG增强特征的配对对比显示，对于学习到的、预训练的和固定的表示均有提升，包括将LRG与训练级干预措施及编码器后分类器校正结合时。消融实验表明，增益来自附加到原始特征的有符号局部残差，而非通用原型距离、亲和特征、标量统计或VLAD风格编码。进一步分析支持所提出的局部几何失效假设：少数类邻域在不平衡下逐渐变得更受多数类暴露，训练局部风险可识别易出错区域，且LRG增益集中在这些高风险区域。
英文摘要
Imbalanced time series classification is often addressed by changing the training distribution, objective, logits, or final threshold. These interventions address important biases, yet leave a representation-level question unmeasured: after minority support is reduced, does a learned feature space remain locally reliable around minority regions? We identify a training-local geometry failure: under imbalance, minority cases can lie in sparse, rest-dominated, or mixed feature-space neighborhoods, even when the representation retains useful global class structure. To diagnose and repair this failure, we propose Local Reference Geometry (LRG), a lightweight post-hoc feature augmentation module applied between a fixed feature extractor and the classifier head. Using training features only, LRG measures local exposure and class-mixture risk, then augments each fixed feature with a standardized signed displacement from nearby training geometry and an LDA-projected residual summary. On controlled UCR/Bake Off Redux imbalance benchmarks, paired raw-versus-LRG comparisons show gains for learned, pretrained, and fixed representations, including when LRG is combined with training-level interventions and post-encoder classifier corrections. Ablations show that the gain comes from the signed local residual appended to the original feature, rather than from generic prototype distances, affinity features, scalar statistics, or VLAD-style codes. Further analyses support the proposed local-geometry failure hypothesis: minority neighborhoods become increasingly rest-exposed under imbalance, training-local risk identifies error-prone regions, and LRG gains concentrate in those high-risk regions.
