Skip to content

Local Reference Geometry Residual Augmentation for Imbalanced Time Series Classification

Aug 2026 · 0 citations · 34 references
Computer Science

TL;DR

Local Reference Geometry (LRG), a lightweight post-hoc feature augmentation module applied between a fixed feature extractor and the classifier head, is proposed, supporting the proposed local-geometry failure hypothesis.

Abstract

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.

View source

Similar papers

Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs

Diagnostics limit explanations based solely on terminal optimization accuracy and distinguish numerical cost from quality, rank coverage and freshness; they establish neither practical-tracker convergence nor predictive or deployment benefits from basis availability.

Zhen-Lin Yao, Wei Xiong · 0 citations

Loss-Guided Pretraining Data Selection for Time-Series Foundation Models

This work connects forecasting loss to optimization difficulty by showing that normalized squared loss controls the per-sample gradient norm under a local Jacobian condition and defines a reference loss score and applies dataset-stratified selection to preserve the diversity of samples.

Yi-Ke Li, Shao-Xu Song, Jian-Min Wang · 0 citations
Preprint Aug 2026

Contrastive Representation-Guided Genetic Minority Oversampling for Imbalanced Time-Series Classification

Real-world time-series classification tasks often exhibit class imbalance, which can be extremely severe in some applications. To avoid training biased classifiers on imbalanced data, sampling is one of the most popular data pre-processing techniques because of its classifier-agnostic nature. However, due to the comple...

Wen-Bin Pei, Yunrong Hao, Zhen Liu et al. · 0 citations
#machine learning Preprint Oct 2026

Learning under Localized Minority Imbalance

A tree-based stratified approach that recursively partitions the feature space with the goal of reducing within-stratum LMI distortion, and introduces a gold-standard evaluation protocol that uses unbiased test sets and demonstrates that conventional hold-out evaluation from the same LMI-biased data can substantially m...

Amin Hosseininasab, Steven M. Shugan · 0 citations

SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification

This work proposes SwitchPFN, which learns a shared projection and regime codebook from the training sequences, making local dynamic operators and transition features directly comparable across samples, and achieves the highest mean accuracy among the evaluated methods.

Zhen-Yi Zhu, Jacqueline J. Pang, Pei-Lin Shen et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.