analiza aiqbench
This research introduces CC-GMNet-TS, a novel framework that leverages Transformer backbones and class-specific Gaussian mixtures to improve prevalence estimation in imbalanced time series data. By assigning distinct latent mixtures to each class rather than sharing a single global model, the approach effectively captures rare patterns critical for applications like biosignal monitoring and fall detection. The method demonstrates superior accuracy over existing deep quantifiers across multiple benchmarks, highlighting its potential to enhance reliability in scenarios with significant class imbalance.
Class-Conditioned Gaussian Mixture Modeling for Imbalanced Time Series Quantification
arXiv:2608.21473v1 Announce Type: new Abstract: Quantification, estimating class prevalences in bags of unlabeled instances is vital in domains where aggregate statistics are more important than individual instance labels, such as biosignal monitoring, fall detection, and activity recognition. We investigate this issue in the challenging setting of imbalanced time series data and develop CC-GMNet-TS, a class-conditioned Gaussian mixture quantifier that combines a Transformer-based feature extractor with per-class latent mixtures. Unlike previous mixture-based quantifiers, which use a single Gaussian mixture shared by all classes, CC-GMNet-TS assigns each class its own compact mixture in a bounded latent space and scores segment embeddings against these class-specific components to create bag-level representations that emphasize rare but informative patterns. Bags are constructed from labeled pools using the Artificial Prevalence Protocol (APP) and prior shift bag sampling (PShift) to cover a wide range of class prevalence scenarios, and the model is trained end-to-end with a quantification-oriented loss. Experiments on three benchmarks: EMG Data for Gestures, SmartFallMM, and UCI-HAR show that CC-GMNet-TS achieves lower error across the three benchmarks compared to traditional aggregators and recent deep quantifiers, while ablations confirm the contributions of both the Transformer backbone and class-conditioned mixtures during PShift.
Abstract:Quantification, estimating class prevalences in bags of unlabeled instances is vital in domains where aggregate statistics are more important than individual instance labels, such as biosignal monitoring, fall detection, and activity recognition. We investigate this issue in the challenging setting of imbalanced time series data and develop CC-GMNet-TS, a class-conditioned Gaussian mixture quantifier that combines a Transformer-based feature extractor with per-class latent mixtures. Unlike previous mixture-based quantifiers, which use a single Gaussian mixture shared by all classes, CC-GMNet-TS assigns each class its own compact mixture in a bounded latent space and scores segment embeddings against these class-specific components to create bag-level representations that emphasize rare but informative patterns. Bags are constructed from labeled pools using the Artificial Prevalence Protocol (APP) and prior shift bag sampling (PShift) to cover a wide range of class prevalence scenarios, and the model is trained end-to-end with a quantification-oriented loss. Experiments on three benchmarks: EMG Data for Gestures, SmartFallMM, and UCI-HAR show that CC-GMNet-TS achieves lower error across the three benchmarks compared to traditional aggregators and recent deep quantifiers, while ablations confirm the contributions of both the Transformer backbone and class-conditioned mixtures during PShift.
13 pages, 2 figures, 2 tables. Accepted at PAKDD 2026 (Pacific-Asia Conference on Knowledge Discovery and Data Mining), LNAI 16599, pp. 560-572, Springer, Singapore
Machine Learning (cs.LG)
arXiv:2608.21473 [cs.LG]
(or arXiv:2608.21473v1 [cs.LG] for this version)
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2026), LNAI 16599, pp. 560-572, Springer, Singapore, 2026
https://doi.org/10.1007/978-981-92-1465-5_44 DOI(s) linking to related resources
Text integral sub licența deschisă a publicației · 247 cuvinte
Subiecte conexe
Exploding variance of means of exponentials: least-squares to the rescue – Machine Learning Research Blog
francisbach.com · 27 sept. 2026
[AINews] not much happened today
Latent Space · 10 sept. 2026
Gaussian Mixture Copula Processes for Irregular Time Series
arXiv · 30 sept. 2026
Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining
arXiv · 15 iun. 2026