paper-with-me

Papers

Adaptive Fine-Tuning via Pattern Specialization for Deep Time Series Forecasting

2025-08-11 · Amal Saadallah, Abdulaziz Al-Ademi arxiv

Time series forecasting poses significant challenges in non-stationary environments where underlying patterns evolve over time. In this work, we propose a novel framework that enhances deep neural network (DNN) performance by leveraging specialized model adaptation and selection. Initially, a base DNN is trained offline on historical time series data. A reserved validation subset is then segmented to extract and cluster the most dominant patterns within the series, thereby identifying distinct regimes. For each identified cluster, the base DNN is fine-tuned to produce a specialized version that captures unique pattern characteristics. At inference, the most recent input is matched against the cluster centroids, and the corresponding fine-tuned version is deployed based on the closest similarity measure. Additionally, our approach integrates a concept drift detection mechanism to identify and adapt to emerging patterns caused by non-stationary behavior. The proposed framework is generalizable across various DNN architectures and has demonstrated significant performance gains on both traditional DNNs and recent advanced architectures implemented in the GluonTS library.

📄 PDF Abstract BibTeX arXiv:2508.07927

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Forecasting

Similar Papers 제목 키워드 기반

Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language?

2026-04-01 · Luis Frentzen Salim, Lun-Wei Ku, Hsing-Kuo Kenneth Pao arxiv

Adapting large language models (LLMs) to new languages is an expensive and opaque process. Understanding how language models acquire new languages and multilingual abilities is key to achieve efficient adaptation. Prior …

Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation

2025-09-21 · Junzhuo Li, Bo Wang, Xiuze Zhou, Xuming Hu arxiv

Mixture-of-Experts (MoE) models offer immense capacity via sparsely gated expert subnetworks, yet adapting them to multiple domains without catastrophic forgetting remains an open challenge. Existing approaches either in…

Domain Adaptation

WaveTuner: Comprehensive Wavelet Subband Tuning for Time Series Forecasting

2025-11-24 · Yubo Wang, Hui He, Chaoxi Niu, Zhendong Niu arxiv

Due to the inherent complexity, temporal patterns in real-world time series often evolve across multiple intertwined scales, including long-term periodicity, short-term fluctuations, and abrupt regime shifts. While exist…

Time Series Forecasting

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

2022-11-01 · Yihan Wang, Si Si, Daliang Li, Michal Lukasik 외

Pretrained large language models (LLMs) are general purpose problem solvers applicable to a diverse set of tasks with prompts. They can be further improved towards a specific task by fine-tuning on a specialized dataset.…

Binary ClassificationDomain GeneralizationFew-Shot LearningIn-Context Learning+3

Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns

2022-05-01 · Findings (ACL) 2022 5 · Zihan Wang, Jiuxiang Gu, Jason Kuen, Handong Zhao 외

We present a comprehensive study of sparse attention patterns in Transformer models. We first question the need for pre-training with sparse attention and present experiments showing that an efficient fine-tuning only ap…