arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.02551cs.LGcs.AIcs.CV
收藏

EEO-TFV:面向网络级时间序列预测和视觉分析的逃逸-探索优化器

EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis

School of Computer and Artificial Intelligence, Ludong University(计算机与人工智能学院,鲁东大学);School of Computer Science and Technology, Shandong Technology and Business University(计算机科学与技术学院,山东技术与商务大学)

Hua Wang, Jinghao Lu, Fan Zhang

AI总结:

EEO-TFV通过轻量级Transformer架构与逃逸-探索优化器,提升网络级时间序列预测和视觉分析的性能与泛化能力。

摘要:

基于Transformer的基础模型在时间序列预测和图像分割等任务中取得了显著进展。然而,它们在多变量长序列预测中经常出现误差累积,并在图像相关任务中表现出对分布外样本的脆弱性。此外,这些挑战在大规模网络数据分析任务中尤为突出,通常涉及复杂的时序模式和多模态特征。这种复杂性显著增加了优化难度,使模型容易在高维参数空间中陷入鞍点。为了解决这些问题,我们提出了一种轻量级的Transformer架构,结合了新颖的逃逸-探索优化器(EEO)。该优化器在增强探索性和泛化能力的同时,有效避免了尖峰极小值和鞍点陷阱。实验结果表明,在典型的网络数据场景中,我们的方法在11个时间序列基准数据集和Synapse医学图像分割任务中与最先进的模型性能相当。此外,它展示了卓越的泛化能力和稳定性,从而验证了其作为跨任务基础模型在网络级数据挖掘和分析中的潜力。

英文摘要:

Transformer-based foundation models have achieved remarkable progress in tasks such as time-series forecasting and image segmentation. However, they frequently suffer from error accumulation in multivariate long-sequence prediction and exhibit vulnerability to out-of-distribution samples in image-related tasks. Furthermore, these challenges become particularly pronounced in large-scale Web data analysis tasks, which typically involve complex temporal patterns and multimodal features. This complexity substantially increases optimization difficulty, rendering models prone to stagnation at saddle points within high-dimensional parameter spaces. To address these issues, we propose a lightweight Transformer architecture in conjunction with a novel Escape-Explore Optimizer (EEO). The optimizer enhances both exploration and generalization while effectively avoiding sharp minima and saddle-point traps. Experimental results show that, in representative Web data scenarios, our method achieves performance on par with state-of-the-art models across 11 time-series benchmark datasets and the Synapse medical image segmentation task. Moreover, it demonstrates superior generalization and stability, thereby validating its potential as a versatile cross-task foundation model for Web-scale data mining and analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑