Time_Series
-
FAN: Fourier Analysis Networks
2024-10-03 17:02:21Yihong Dong, Ge Li, Yongding Tao, Xue Jiang, Kechi Zhang, Jia Li, Jing Su, Jun Zhang, Jingjing XuAbstract
Despite the remarkable success achieved by neural networks, particularly those represented by MLP and Transformer, we reveal that they exhibit potential flaws in the modeling and reasoning of periodicity, i.e., they tend to memorize the periodic data rather than genuinely understanding the underlying principles of periodicity. However, periodicity is a crucial trait in various forms of reasoning and generalization, underpinning predictability across natural and engineered systems through recurring patterns in observations. In this paper, we propose FAN, a novel network architecture based on Fourier Analysis, which empowers the ability to efficiently model and reason about periodic phenomena. By introducing Fourier Series, the periodicity is naturally integrated into the structure and computational processes of the neural network, thus achieving a more accurate expression and prediction of periodic patterns. As a promising substitute to multi-layer perceptron (MLP), FAN can seamlessly replace MLP in various models with fewer parameters and FLOPs. Through extensive experiments, we demonstrate the effectiveness of FAN in modeling and reasoning about periodic functions, and the superiority and generalizability of FAN across a range of real-world tasks, including symbolic formula representation, time series forecasting, and language modeling.
Abstract (translated)
尽管神经网络取得了令人瞩目的成功，尤其是那些用MLP和Transformer表示的神经网络，但我们发现它们在周期性建模和推理中存在潜在缺陷，即它们倾向于记忆周期性数据而不是真正理解周期性背后的原则。然而，周期性在各种推理和泛化形式中是一个关键特征，通过观察到观测到的重复模式，为自然和工程系统提供可预测性。在本文中，我们提出了FAN，一种基于傅里叶分析的新网络架构，它具有高效建模和推理周期性现象的能力。通过引入傅里叶级数，周期性自然地整合到神经网络的结构和计算过程中，从而实现更准确地表达和预测周期性模式。作为多层感知器（MLP）的有前途的替代品，FAN可以在具有较少参数和FLOPs的各种模型中替换MLP。通过广泛的实验，我们证明了FAN在建模和推理周期性函数方面的有效性，以及FAN在各种现实世界任务中的优越性和普适性，包括符号公式表示、时间序列预测和语言建模。
URL
https://arxiv.org/abs/2410.02675
PDF
-
Plots Unlock Time-Series Understanding in Multimodal Models
2024-10-03 16:23:13Mayank Daswani, Mathias M. J. Bellaiche, Marc Wilson, Desislav Ivanov, Mikhail Papkov, Eva Schnider, Jing Tang, Kay Lamerigts, Gabriela Botea, Michael A. Sanchez, Yojan Patel, Shruthi Prabhakara, Shravya Shetty, Umesh TelangAbstract
While multimodal foundation models can now natively work with data beyond text, they remain underutilized in analyzing the considerable amounts of multi-dimensional time-series data in fields like healthcare, finance, and social sciences, representing a missed opportunity for richer, data-driven insights. This paper proposes a simple but effective method that leverages the existing vision encoders of these models to "see" time-series data via plots, avoiding the need for additional, potentially costly, model training. Our empirical evaluations show that this approach outperforms providing the raw time-series data as text, with the additional benefit that visual time-series representations demonstrate up to a 90% reduction in model API costs. We validate our hypothesis through synthetic data tasks of increasing complexity, progressing from simple functional form identification on clean data, to extracting trends from noisy scatter plots. To demonstrate generalizability from synthetic tasks with clear reasoning steps to more complex, real-world scenarios, we apply our approach to consumer health tasks - specifically fall detection, activity recognition, and readiness assessment - which involve heterogeneous, noisy data and multi-step reasoning. The overall success in plot performance over text performance (up to an 120% performance increase on zero-shot synthetic tasks, and up to 150% performance increase on real-world tasks), across both GPT and Gemini model families, highlights our approach's potential for making the best use of the native capabilities of foundation models.
Abstract (translated)
虽然多模态基础模型现在可以原生地处理数据，包括文本以外，但在医疗、金融和社会科学等领域中处理大量多维度时间序列数据时，它们仍然没有被充分利用，这代表了一个丰富的数据驱动见解的错失机会。本文提出了一种简单而有效的的方法，利用现有模型的视觉编码器来“通过绘制图表”看待时间序列数据，无需进行昂贵的额外模型训练。我们的实证评估结果表明，这种方法在提供原始时间序列数据作为文本的同时超过了它，并且还具有使视觉时间序列表示减少模型API成本的额外优势。我们通过模拟数据任务来验证我们的假设，从简单的功能形式识别开始，逐渐进展到从嘈杂散点图提取趋势。为了从模拟任务中展示从清晰推理步骤到更复杂、现实世界场景的泛化能力，我们将该方法应用于消费者健康任务——尤其是跌倒检测、活动识别和准备评估，这些任务涉及异质、嘈杂数据和多步骤推理。在基于文本的绘制表现与基于图的绘制表现之间（在零散投放虚拟任务中的性能增加达到120%，在真实世界任务中的性能增加达到150%）的全面成功，突出了我们在基础模型上充分利用原功能的能力。
URL
https://arxiv.org/abs/2410.02637
PDF
-
Embedded Topic Models Enhanced by Wikification
Abstract
Topic modeling analyzes a collection of documents to learn meaningful patterns of words. However, previous topic models consider only the spelling of words and do not take into consideration the homography of words. In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities. We evaluate our method on two datasets, 1) news articles of \textit{New York Times} and 2) the AIDA-CoNLL dataset. Our experiments show that our method improves the performance of neural topic models in generalizability. Moreover, we analyze frequent terms in each topic and the temporal dependencies between topics to demonstrate that our entity-aware topic models can capture the time-series development of topics well.
Abstract (translated)
主题建模分析了一组文档，以学习有意义的单词模式。然而，之前的主题模型仅考虑单词的拼写，而没有考虑单词的同余性。在这项研究中，我们将维基百科的知识融入了神经主题模型中，使它能够考虑到命名实体。我们对我们的方法在两个数据集上的实验进行了评估，1)《纽约时报》的新闻文章集，2) AIDA-CoNLL数据集。我们的实验结果表明，与神经主题模型的一般化性能相比，我们的方法有所提高。此外，我们分析了每个主题中的高频词汇和主题之间的时间依赖关系，以证明我们的实体意识主题模型可以很好地捕捉主题的时间序列发展。
URL
https://arxiv.org/abs/2410.02441
PDF
-
Data Optimisation of Machine Learning Models for Smart Irrigation in Urban Parks
2024-10-03 09:42:16Nasser Ghadiri, Bahman Javadi, Oliver Obst, Sebastian PfautschAbstract
Urban environments face significant challenges due to climate change, including extreme heat, drought, and water scarcity, which impact public health, community well-being, and local economies. Effective management of these issues is crucial, particularly in areas like Sydney Olympic Park, which relies on one of Australia's largest irrigation systems. The Smart Irrigation Management for Parks and Cool Towns (SIMPaCT) project, initiated in 2021, leverages advanced technologies and machine learning models to optimize irrigation and induce physical cooling. This paper introduces two novel methods to enhance the efficiency of the SIMPaCT system's extensive sensor network and applied machine learning models. The first method employs clustering of sensor time series data using K-shape and K-means algorithms to estimate readings from missing sensors, ensuring continuous and reliable data. This approach can detect anomalies, correct data sources, and identify and remove redundant sensors to reduce maintenance costs. The second method involves sequential data collection from different sensor locations using robotic systems, significantly reducing the need for high numbers of stationary sensors. Together, these methods aim to maintain accurate soil moisture predictions while optimizing sensor deployment and reducing maintenance costs, thereby enhancing the efficiency and effectiveness of the smart irrigation system. Our evaluations demonstrate significant improvements in the efficiency and cost-effectiveness of soil moisture monitoring networks. The cluster-based replacement of missing sensors provides up to 5.4% decrease in average error. The sequential sensor data collection as a robotic emulation shows 17.2% and 2.1% decrease in average error for circular and linear paths respectively.
Abstract (translated)
由于气候变化，城市环境面临重大挑战，包括极端高温、干旱和水资源短缺，这些都影响了公共卫生、社区福祉和当地经济。有效管理这些问题至关重要，尤其是在像悉尼奥林匹克公园这样的地区，该地区依赖澳大利亚最大的灌溉系统。2021年启动的智能公园和 cool 城镇项目（SIMPaCT）利用先进的技术和机器学习模型优化灌溉和诱导物理降温。本文介绍了两种新的方法，增强 SIMPaCT 系统的广泛传感器网络的效率，并应用机器学习模型。第一种方法采用 K-形状和 K-means 算法对传感器时间序列数据进行聚类，估计缺失传感器的读数，确保连续和可靠的数据。这种方法可以检测异常，纠正数据来源，并识别和删除冗余传感器，从而降低维护成本。第二种方法涉及使用机器人系统从不同传感器位置进行顺序数据收集，从而大大减少了需要的高数量静态传感器的需要。 Together，这些方法旨在在优化传感器部署的同时降低维护成本，从而提高智能灌溉系统的效率和效果。我们的评估结果表明，土壤水分监测网络的效率和成本效益都有显著提高。基于聚类的缺失传感器替换平均误差降低了至多 5.4%。作为机器人仿真的顺序传感器数据收集，环形和线性路径的平均误差分别降低了 17.2% 和 2.1%。
URL
https://arxiv.org/abs/2410.02335
PDF
-
BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
2024-10-03 04:16:49Xiao Lin, Zhining Liu, Dongqi Fu, Ruizhong Qiu, Hanghang TongAbstract
Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerful deep learning models have been developed for this task, few works have explored the robustness of MTS forecasting models to malicious attacks, which is crucial for their trustworthy employment in high-stake scenarios. To address this gap, we dive deep into the backdoor attacks on MTS forecasting models and propose an effective attack method named this http URL subtly injecting a few stealthy triggers into the MTS data, BackTime can alter the predictions of the forecasting model according to the attacker's intent. Specifically, BackTime first identifies vulnerable timestamps in the data for poisoning, and then adaptively synthesizes stealthy and effective triggers by solving a bi-level optimization problem with a GNN-based trigger generator. Extensive experiments across multiple datasets and state-of-the-art MTS forecasting models demonstrate the effectiveness, versatility, and stealthiness of \method{} attacks. The code is available at \url{this https URL}.
Abstract (translated)
多变量时间序列（MTS）预测是一种基本任务，具有许多现实应用，如交通、气候和流行病学。虽然为这个任务已经开发了无数个强大的深度学习模型，但很少有研究探索MTS预测模型的稳健性，这对它们在高风险场景中可靠使用的至关重要。为填补这个空白，我们深入研究了针对MTS预测模型的后门攻击，并提出了一个有效攻击方法：隐式注入，通过这个URL悄悄地向MTS数据中注入了一些隐形的触发器，BackTime可以根据攻击者的意图改变预测模型的预测。具体来说，BackTime首先确定数据中可能被下毒的易受攻击的戳，然后通过基于GNN的触发器生成器解决二元优化问题，生成 stealthy（隐形的）和 effective（有效的）触发器。在多个数据集和最先进的MTS预测模型上进行广泛的实验证明了这个方法的的有效性、多样性和隐秘性。代码可以在这个URL上找到。
URL
https://arxiv.org/abs/2410.02195
PDF
-
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
2024-10-03 02:12:03Gaurav Patel, Christopher Sandino, Behrooz Mahasseni, Ellen L Zippi, Erdrin Azemi, Ali Moin, Juri MinxhaAbstract
In this paper, we propose a framework for efficient Source-Free Domain Adaptation (SFDA) in the context of time-series, focusing on enhancing both parameter efficiency and data-sample utilization. Our approach introduces an improved paradigm for source-model preparation and target-side adaptation, aiming to enhance training efficiency during target adaptation. Specifically, we reparameterize the source model's weights in a Tucker-style decomposed manner, factorizing the model into a compact form during the source model preparation phase. During target-side adaptation, only a subset of these decomposed factors is fine-tuned, leading to significant improvements in training efficiency. We demonstrate using PAC Bayesian analysis that this selective fine-tuning strategy implicitly regularizes the adaptation process by constraining the model's learning capacity. Furthermore, this re-parameterization reduces the overall model size and enhances inference efficiency, making the approach particularly well suited for resource-constrained devices. Additionally, we demonstrate that our framework is compatible with various SFDA methods and achieves significant computational efficiency, reducing the number of fine-tuned parameters and inference overhead in terms of MACs by over 90% while maintaining model performance.
Abstract (translated)
在本文中，我们提出了一个在时间序列背景下实现高效源自由领域适应（SFDA）的框架，重点关注提高参数效率和数据样本利用率。我们的方法引入了一种改进的源模型准备和目标侧适应范式，旨在在目标适应过程中提高训练效率。具体来说，我们在源模型权重分解的方式下重新参数化源模型的权重，在源模型准备阶段将模型分解为紧凑的形式。在目标侧适应过程中，仅对分解因子进行微调，导致训练效率显著提高。我们通过PAC贝叶斯分析证明，这种选择性微调策略通过限制模型的学习能力 implicitly 规范了适应过程。此外，这种重新参数化还减小了整体模型大小，提高了推理效率，使得该方法特别适用于资源受限的设备。我们还证明了我们的框架与各种SFDA方法兼容，在保持模型性能的同时，降低了微调参数的数量和对MAC的推理开销，减少了90%以上。
URL
https://arxiv.org/abs/2410.02147
PDF
-
Model Comparisons: XNet Outperforms KAN
Abstract
In the fields of computational mathematics and artificial intelligence, the need for precise data modeling is crucial, especially for predictive machine learning tasks. This paper explores further XNet, a novel algorithm that employs the complex-valued Cauchy integral formula, offering a superior network architecture that surpasses traditional Multi-Layer Perceptrons (MLPs) and Kolmogorov-Arnold Networks (KANs). XNet significant improves speed and accuracy across various tasks in both low and high-dimensional spaces, redefining the scope of data-driven model development and providing substantial improvements over established time series models like LSTMs.
Abstract (translated)
在计算数学和人工智能领域，精确的数据建模至关重要，尤其是在预测机器学习任务中。本文进一步探讨了XNet，一种采用复值Cauchy积分公式的新型算法，为神经网络提供了卓越的网络结构，超越了传统的多层感知器（MLPs）和Kolmogorov-Arnold网络（KANs）。XNet在低维和高维空间各种任务上显著提高了速度和精度，重新定义了数据驱动模型开发的范围，并在如LSTMs等现有时间序列模型的基础上提供了显著的改进。
URL
https://arxiv.org/abs/2410.02033
PDF
-
TiVaT: Joint-Axis Attention for Time Series Forecasting with Lead-Lag Dynamics
2024-10-02 13:24:24Junwoo Ha, Hyukjae Kwon, Sungsoo Kim, Kisu Lee, Ha Young KimAbstract
Multivariate time series (MTS) forecasting plays a crucial role in various real-world applications, yet simultaneously capturing both temporal and inter-variable dependencies remains a challenge. Conventional Channel-Dependent (CD) models handle these dependencies separately, limiting their ability to model complex interactions such as lead-lag dynamics. To address these limitations, we propose TiVaT (Time-Variable Transformer), a novel architecture that integrates temporal and variate dependencies through its Joint-Axis (JA) attention mechanism. TiVaT's ability to capture intricate variate-temporal dependencies, including asynchronous interactions, is further enhanced by the incorporation of Distance-aware Time-Variable (DTV) Sampling, which reduces noise and improves accuracy through a learned 2D map that focuses on key interactions. TiVaT effectively models both temporal and variate dependencies, consistently delivering strong performance across diverse datasets. Notably, it excels in capturing complex patterns within multivariate time series, enabling it to surpass or remain competitive with state-of-the-art methods. This positions TiVaT as a new benchmark in MTS forecasting, particularly in handling datasets characterized by intricate and challenging dependencies.
Abstract (translated)
多变量时间序列（MTS）预测在各种现实应用中扮演着关键角色，然而同时捕捉时空和变量依赖仍然具有挑战性。传统的通道相关（CD）模型分别处理这些依赖，从而限制了它们对复杂交互建模的能力，如滞后动态。为了应对这些限制，我们提出了TiVaT（时间变量转换器），一种新颖的架构，通过联合轴（JA）注意力机制集成时空和变量依赖。TiVaT通过结合复杂变量-时依赖的能力，包括异步相互作用，进一步增强了其捕捉复杂变体（如多变量时间序列中的复杂模式）的能力。TiVaT通过引入距离感知时间变量（DTV）采样，通过学习关注关键交互的2D图，有效减少了噪声并提高了准确性。TiVaT在各种数据集上有效建模时空和变量依赖， consistently在多样数据集上实现强劲的性能。值得注意的是，它特别擅长捕捉多变量时间序列中的复杂模式，使其能够超越或与最先进的方法竞争。这使得TiVaT在MTS预测领域成为了一个新的基准，尤其是在处理具有复杂和具有挑战性的依赖的数据集时。
URL
https://arxiv.org/abs/2410.01531
PDF
-
Deep Multimodal Fusion for Semantic Segmentation of Remote Sensing Earth Observation Data
2024-10-01 07:50:37Ivica Dimitrovski, Vlatko Spasev, Ivan KitanovskiAbstract
Accurate semantic segmentation of remote sensing imagery is critical for various Earth observation applications, such as land cover mapping, urban planning, and environmental monitoring. However, individual data sources often present limitations for this task. Very High Resolution (VHR) aerial imagery provides rich spatial details but cannot capture temporal information about land cover changes. Conversely, Satellite Image Time Series (SITS) capture temporal dynamics, such as seasonal variations in vegetation, but with limited spatial resolution, making it difficult to distinguish fine-scale objects. This paper proposes a late fusion deep learning model (LF-DLM) for semantic segmentation that leverages the complementary strengths of both VHR aerial imagery and SITS. The proposed model consists of two independent deep learning branches. One branch integrates detailed textures from aerial imagery captured by UNetFormer with a Multi-Axis Vision Transformer (MaxViT) backbone. The other branch captures complex spatio-temporal dynamics from the Sentinel-2 satellite image time series using a U-Net with Temporal Attention Encoder (U-TAE). This approach leads to state-of-the-art results on the FLAIR dataset, a large-scale benchmark for land cover segmentation using multi-source optical imagery. The findings highlight the importance of multi-modality fusion in improving the accuracy and robustness of semantic segmentation in remote sensing applications.
Abstract (translated)
准确的地形分割遥感影像对于各种地球观测应用至关重要，如土地覆盖地图、城市规划和国际环境监测。然而，数据源通常存在限制此任务的局限性。高分辨率（VHR）航空影像提供了丰富的空间细节，但不能捕捉到土地覆盖变化的时间信息。相反，卫星图像时间序列（SITS）可以捕捉到植被随季节变化的动态，但分辨率有限，导致难以区分细粒度物体。本文提出了一种 late fusion deep learning model（LF-DLM）用于语义分割，该模型利用VHR航空影像和SITS的互补优势。所提出的模型由两个独立的深度学习分支组成。一个分支将UNetFormer捕获的航空影像的详细纹理与多轴视觉Transformer（MaxViT）骨干相结合。另一个分支使用U-Net Temporal Attention Encoder（U-TAE）从Sentinel-2卫星图像时间序列中捕获复杂的空间-时间动态。这种方法在FLAIR数据集上取得了最先进的成果，这是使用多源光学影像进行大面积土地覆盖分割的一个大型的基准。这些发现突出了在遥感应用中进行多模态融合提高语义分割精度和鲁棒性的重要性。
URL
https://arxiv.org/abs/2410.00469
PDF
-
Bayes-CATSI: A variational Bayesian approach for medical time series data imputation
2024-10-01 07:37:52Omkar Kulkarni, Rohitash ChandraAbstract
Medical time series datasets feature missing values that need data imputation methods, however, conventional machine learning models fall short due to a lack of uncertainty quantification in predictions. Among these models, the CATSI (Context-Aware Time Series Imputation) stands out for its effectiveness by incorporating a context vector into the imputation process, capturing the global dependencies of each patient. In this paper, we propose a Bayesian Context-Aware Time Series Imputation (Bayes-CATSI) framework which leverages uncertainty quantification offered by variational inference. We consider the time series derived from electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), electrocardiology (EKG). Variational Inference assumes the shape of the posterior distribution and through minimization of the Kullback-Leibler(KL) divergence it finds variational densities that are closest to the true posterior distribution. Thus , we integrate the variational Bayesian deep learning layers into the CATSI model. Our results show that Bayes-CATSI not only provides uncertainty quantification but also achieves superior imputation performance compared to the CATSI model. Specifically, an instance of Bayes-CATSI outperforms CATSI by 9.57 %. We provide an open-source code implementation for applying Bayes-CATSI to other medical data imputation problems.
Abstract (translated)
医疗时间序列数据集存在缺失值，需要数据插值方法，然而，传统的机器学习模型由于预测不确定性量化不足而陷入缺陷。在这些模型中，CATSI（上下文感知时间序列插值）通过将上下文向量引入插值过程而脱颖而出，捕捉每个患者的全局依赖关系。在本文中，我们提出了一个基于贝叶斯上下文感知时间序列插值的（Bayes-CATSI）框架，利用了贝叶斯推理提供的不确定性量化。我们考虑了从脑电图（EEG）、眼电图（EOG）、肌电图（EMG）和心电图（EKG）生成的时间序列。贝叶斯推理假设后验分布的形状，通过最小化Kullback-Leibler（KL）差异找到最接近真实后验分布的随机的密度。因此，我们将贝叶斯贝叶斯深度学习层融入CATSI模型中。我们的结果表明，Bayes-CATSI不仅提供了不确定性量化，而且比CATSI模型具有更卓越的插值性能。具体来说，一个Bayes-CATSI实例比CATSI模型提高了9.57%。我们还提供了将Bayes-CATSI应用于其他医学数据插值问题的开源代码实现。
URL
https://arxiv.org/abs/2410.01847
PDF
-
Contrastive Representation Learning for Predicting Solar Flares from Extremely Imbalanced Multivariate Time Series Data
2024-10-01 01:20:47Onur Vural, Shah Muhammad Hamdi, Soukaina Filali BoubrahimiAbstract
Major solar flares are abrupt surges in the Sun's magnetic flux, presenting significant risks to technological infrastructure. In view of this, effectively predicting major flares from solar active region magnetic field data through machine learning methods becomes highly important in space weather research. Magnetic field data can be represented in multivariate time series modality where the data displays an extreme class imbalance due to the rarity of major flare events. In time series classification-based flare prediction, the use of contrastive representation learning methods has been relatively limited. In this paper, we introduce CONTREX, a novel contrastive representation learning approach for multivariate time series data, addressing challenges of temporal dependencies and extreme class imbalance. Our method involves extracting dynamic features from the multivariate time series instances, deriving two extremes from positive and negative class feature vectors that provide maximum separation capability, and training a sequence representation embedding module with the original multivariate time series data guided by our novel contrastive reconstruction loss to generate embeddings aligned with the extreme points. These embeddings capture essential time series characteristics and enhance discriminative power. Our approach shows promising solar flare prediction results on the Space Weather Analytics for Solar Flares (SWAN-SF) multivariate time series benchmark dataset against baseline methods.
Abstract (translated)
大太阳活动是太阳磁场中突然的激增，对技术基础设施造成显著风险。因此，在空间天气研究中，从太阳活动区磁场数据预测大太阳活动变得非常重要。磁场数据可以通过多元时间序列模式表示，由于大太阳活动事件的稀有性，数据表现出极端的类不平衡。基于时间序列分类的大太阳活动预测，使用对比性表示学习方法的应用相对较少。在本文中，我们引入了CONTREX，一种用于多维时间序列数据的对比性表示学习方法，解决了时间依赖关系和极端类不平衡的挑战。我们的方法包括从多维时间序列实例中提取动态特征，从正负类特征向量中分别得到两个极端值，基于我们新颖的对比性重构损失对原始多维时间序列数据进行训练，以生成与极端点对齐的嵌入。这些嵌入抓住了基本的时间序列特征并提高了判别能力。我们的方法在SWAN-SF多维时间序列基准数据集上的太阳活动预测结果表明，与基线方法相比具有 promising 的结果。
URL
https://arxiv.org/abs/2410.00312
PDF
-
StreamEnsemble: Predictive Queries over Spatiotemporal Streaming Data
2024-09-30 23:50:16Anderson Chaves, Eduardo Ogasawara, Patrick Valduriez, Fabio PortoAbstract
Predictive queries over spatiotemporal (ST) stream data pose significant data processing and analysis challenges. ST data streams involve a set of time series whose data distributions may vary in space and time, exhibiting multiple distinct patterns. In this context, assuming a single machine learning model would adequately handle such variations is likely to lead to failure. To address this challenge, we propose StreamEnsemble, a novel approach to predictive queries over ST data that dynamically selects and allocates Machine Learning models according to the underlying time series distributions and model characteristics. Our experimental evaluation reveals that this method markedly outperforms traditional ensemble methods and single model approaches in terms of accuracy and time, demonstrating a significant reduction in prediction error of more than 10 times compared to traditional approaches.
Abstract (translated)
预测性查询在时空流数据上具有显著的数据处理和分析挑战。时空流数据涉及一系列时间序列，这些数据分布可能在空间和时间上有所不同，呈现多种不同的模式。在这种情况下，假设单个机器学习模型能够适当地处理这种变化可能是失败的。为了应对这个挑战，我们提出了StreamEnsemble，一种新的处理时空流数据的预测性查询的方法，根据底层时间序列分布和模型特征动态选择和分配机器学习模型。我们的实验评估表明，与传统方法和单模型方法相比，这种方法在准确性和时间方面都明显优越，显示出比传统方法减少预测误差超过10倍。
URL
https://arxiv.org/abs/2410.00933
PDF
-
Stream-level flow matching from a Bayesian decision theoretic perspective
Abstract
Flow matching (FM) is a family of training algorithms for fitting continuous normalizing flows (CNFs). A standard approach to FM, called conditional flow matching (CFM), exploits the fact that the marginal vector field of a CNF can be learned by fitting least-square regression to the so-called conditional vector field specified given one or both ends of the flow path. We show that viewing CFM training from a Bayesian decision theoretic perspective on parameter estimation opens the door to generalizations of CFM algorithms. We propose one such extension by introducing a CFM algorithm based on defining conditional probability paths given what we refer to as ``streams'', instances of latent stochastic paths that connect pairs of noise and observed data. Further, we advocates the modeling of these latent streams using Gaussian processes (GPs). The unique distributional properties of GPs, and in particular the fact that the velocities of a GP is still a GP, allows drawing samples from the resulting stream-augmented conditional probability path without simulating the actual streams, and hence the ``simulation-free" nature of CFM training is preserved. We show that this generalization of the CFM can substantially reduce the variance in the estimated marginal vector field at a moderate computational cost, thereby improving the quality of the generated samples under common metrics. Additionally, we show that adopting the GP on the streams allows for flexibly linking multiple related training data points (e.g., time series) and incorporating additional prior information. We empirically validate our claim through both simulations and applications to two hand-written image datasets.
Abstract (translated)
流匹配（FM）是一系列用于拟合连续归一化流（CNFs）的训练算法。一种标准的FM方法，称为条件流匹配（CFM），利用了给定流路径一或两个端点的条件向量场的可能学习性。我们证明了从贝叶斯决策理论的角度来看，从参数估计的角度看CFM训练会打开CFM算法的扩展。我们提出了一个这样的扩展，通过定义给定“流”的条件概率路径，利用我们所说的“流”，连接噪声和观测数据对对。此外，我们主张使用高斯过程（GPs）来建模这些潜在流。GPs的唯一分布特性，特别是GPs的速度仍然是一个GPs，使得从结果的流增强条件概率路径中抽样，而无需模拟实际流，从而保留了CFM训练的“无模拟”性质。我们证明了，以这种扩展CFM可以在中等计算成本下显著减少估计边际向量的方差，从而提高基于常见指标生成的样本的质量。此外，我们还证明了在流上采用GPs可以使多个相关训练数据点（例如时间序列）灵活地链接起来，并包含其他先验信息。我们通过模拟和应用两个手写图像数据集来实证验证我们的说法。
URL
https://arxiv.org/abs/2409.20423
PDF
-
Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
2024-09-30 15:07:16Weiwei Ye, Songgaojun Deng, Qiaosha Zou, Ning GuiAbstract
Time series forecasting typically needs to address non-stationary data with evolving trend and seasonal patterns. To address the non-stationarity, reversible instance normalization has been recently proposed to alleviate impacts from the trend with certain statistical measures, e.g., mean and variance. Although they demonstrate improved predictive accuracy, they are limited to expressing basic trends and are incapable of handling seasonal patterns. To address this limitation, this paper proposes a new instance normalization solution, called frequency adaptive normalization (FAN), which extends instance normalization in handling both dynamic trend and seasonal patterns. Specifically, we employ the Fourier transform to identify instance-wise predominant frequent components that cover most non-stationary factors. Furthermore, the discrepancy of those frequency components between inputs and outputs is explicitly modeled as a prediction task with a simple MLP model. FAN is a model-agnostic method that can be applied to arbitrary predictive backbones. We instantiate FAN on four widely used forecasting models as the backbone and evaluate their prediction performance improvements on eight benchmark datasets. FAN demonstrates significant performance advancement, achieving 7.76% ~ 37.90% average improvements in MSE.
Abstract (translated)
时间序列预测通常需要处理具有演变趋势和季节性模式的非平稳数据。为解决非平稳性，可最近地提出了可逆实例归一化（RIN）来减轻趋势对某些统计量（如均值和方差）的影响。尽管它们展示了 improved predictive accuracy，但它们只能表达基本趋势，无法处理季节性模式。为了克服这一限制，本文提出了一个新的实例归一化解决方案，称为频率自适应归一化（FAN），它扩展了实例归一化在处理动态趋势和季节性模式的能力。具体来说，我们采用傅里叶变换来识别每个实例上的主要高频分量，覆盖大多数非平稳因素。此外，输入和输出之间频率分量的差异明确建模为一种简单的 MLP 模型。FAN 是一种对任意预测骨干进行模型无关的方法。我们在四个广泛使用的预测模型上实例化 FAN，并使用八个基准数据集评估其预测性能改进。FAN 表现出显著的性能提升，平均 MSE 改进了 7.76% ~ 37.90%。
URL
https://arxiv.org/abs/2409.20371
PDF
-
GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Prediction
2024-09-30 12:02:17Chen Xie, Ciyun Lin, Xiaoyu Zheng, Bowen Gong, Dayong Wu, Antonio M. L\'opezAbstract
Understanding and predicting pedestrian crossing behavioral intention is crucial for autonomous vehicles driving safety. Nonetheless, challenges emerge when using promising images or environmental context masks to extract various factors for time-series network modeling, causing pre-processing errors or a loss in efficiency. Typically, pedestrian positions captured by onboard cameras are often distorted and do not accurately reflect their actual movements. To address these issues, GTransPDM -- a Graph-embedded Transformer with a Position Decoupling Module -- was developed for pedestrian crossing intention prediction by leveraging multi-modal features. First, a positional decoupling module was proposed to decompose the pedestrian lateral movement and simulate depth variations in the image view. Then, a graph-embedded Transformer was designed to capture the spatial-temporal dynamics of human pose skeletons, integrating essential factors such as position, skeleton, and ego-vehicle motion. Experimental results indicate that the proposed method achieves 92% accuracy on the PIE dataset and 87% accuracy on the JAAD dataset, with a processing speed of 0.05ms. It outperforms the state-of-the-art in comparison.
Abstract (translated)
理解并预测行人过马路的意图对自动驾驶车辆的安全至关重要。然而，当使用期望的图像或环境上下文来提取时间序列网络模型的各种因素时，挑战就会出现，导致预处理错误或效率降低。通常，车载摄像机捕捉到的行人位置通常扭曲，并不能准确反映其实际运动。为解决这些问题，GTransPDM -- 一个图嵌入的Transformer with a Position Decoupling Module -- 是为了预测行人过马路的意图而开发的。该方法利用了多模态特征。首先，提出了一种位置解耦模块，以分解行人的横向运动并在图像视图中模拟深度变化。然后，设计了一个图嵌入的Transformer，以捕捉人类姿态骨架的空间-时间动态，包括位置、骨架和自车辆运动等关键因素。实验结果表明，与最先进的系统相比，所提出的方法在PIE数据集上的准确率为92%，在JAAD数据集上的准确率为87%，处理速度为0.05ms。该方法在比较中表现优异。
URL
https://arxiv.org/abs/2409.20223
PDF
-
Co-Movement and Trust Development in Human-Robot Teams
2024-09-30 11:56:22Nicola Webb, Sanja Milivojevic, Mehdi Sobhani, Zachary R. Madin, James C. Ward, Sagir Yusuf, Chris Baber, Edmund R. HuntAbstract
For humans and robots to form an effective human-robot team (HRT) there must be sufficient trust between team members throughout a mission. We analyze data from an HRT experiment focused on trust dynamics in teams of one human and two robots, where trust was manipulated by robots becoming temporarily unresponsive. Whole-body movement tracking was achieved using ultrasound beacons, alongside communications and performance logs from a human-robot interface. We find evidence that synchronization between time series of human-robot movement, within a certain spatial proximity, is correlated with changes in self-reported trust. This suggests that the interplay of proxemics and kinesics, i.e. moving together through space, where implicit communication via coordination can occur, could play a role in building and maintaining trust in human-robot teams. Thus, quantitative indicators of coordination dynamics between team members could be used to predict trust over time and also provide early warning signals of the need for timely trust repair if trust is damaged. Hence, we aim to develop the metrology of trust in mobile human-robot teams.
Abstract (translated)
为了形成一个有效的 human-robot 团队（HRT），在任务过程中，团队成员之间必须存在足够的信任。我们对一个由一人和两个机器人组成的 HRT 实验的数据进行了分析，该实验重点关注机器人暂时失去响应时信任动态。使用超声波信标实现全身运动跟踪，同时记录来自人机交互界面的人机通信和表现日志。我们发现，在一定空间接近性内，人机运动时间序列之间的同步与自我报告的信任变化相关。这表明，通过协调和隐性通信来共同移动，即通过空间中的相互作用进行隐性通信，可能在构建和维护人机团队信任中发挥作用。因此，可以用来预测信任的定量指标可以在时间上预测信任，并且还能提供及时信任修复的早期警告信号。因此，我们的目标是开发移动人机团队的信任度测量。
URL
https://arxiv.org/abs/2409.20218
PDF
-
Continuous-Time Linear Positional Embedding for Irregular Time Series Forecasting
2024-09-30 08:46:18Byunghyun Kim, Jae-Gil LeeAbstract
Irregularly sampled time series forecasting, characterized by non-uniform intervals, is prevalent in practical applications. However, previous research have been focused on regular time series forecasting, typically relying on transformer architectures. To extend transformers to handle irregular time series, we tackle the positional embedding which represents the temporal information of the data. We propose CTLPE, a method learning a continuous linear function for encoding temporal information. The two challenges of irregular time series, inconsistent observation patterns and irregular time gaps, are solved by learning a continuous-time function and concise representation of position. Additionally, the linear continuous function is empirically shown superior to other continuous functions by learning a neural controlled differential equation-based positional embedding, and theoretically supported with properties of ideal positional embedding. CTLPE outperforms existing techniques across various irregularly-sampled time series datasets, showcasing its enhanced efficacy.
Abstract (translated)
非均匀采样时间序列预测在实际应用中很普遍。然而，之前的研究主要集中在常规时间序列预测，通常依赖于Transformer架构。为了将Transformer扩展到处理非均匀时间序列，我们解决了位置嵌入问题，这代表数据的时序信息。我们提出了CTLPE方法，一种学习连续线性函数来编码时序信息的算法。通过学习连续时间函数和简洁的位置表示，解决了 irregular time series中的两个挑战：不规则的观察模式和不规则的时间间隔。此外，通过学习基于神经控制差分方程的位置嵌入，线性连续函数在经验上被证明比其他连续函数更优越，并且通过理想的定位嵌入性质得到了理论支持。CTLPE在各种不均匀采样时间序列数据集上优于现有技术，展示了其增强效果。
URL
https://arxiv.org/abs/2409.20092
PDF
-
Model Selection with a Shapelet-based Distance Measure for Multi-source Transfer Learning in Time Series Classification
2024-09-30 06:57:30Jiseok Lee, Brian Kenji IwanaAbstract
Transfer learning is a common practice that alleviates the need for extensive data to train neural networks. It is performed by pre-training a model using a source dataset and fine-tuning it for a target task. However, not every source dataset is appropriate for each target dataset, especially for time series. In this paper, we propose a novel method of selecting and using multiple datasets for transfer learning for time series classification. Specifically, our method combines multiple datasets as one source dataset for pre-training neural networks. Furthermore, for selecting multiple sources, our method measures the transferability of datasets based on shapelet discovery for effective source selection. While traditional transferability measures require considerable time for pre-training all the possible sources for source selection of each possible architecture, our method can be repeatedly used for every possible architecture with a single simple computation. Using the proposed method, we demonstrate that it is possible to increase the performance of temporal convolutional neural networks (CNN) on time series datasets.
Abstract (translated)
迁移学习是一种常见的方法，可以减轻训练神经网络所需的大量数据。它通过使用源数据集预训练模型，然后对目标任务进行微调来实现。然而，并不是每个源数据集都适用于每个目标数据集，尤其是对于时间序列数据。在本文中，我们提出了一种新的方法，用于为时间序列分类选择和利用多个数据集进行迁移学习。具体来说，我们的方法将多个数据集作为一个源数据集进行预训练。此外，为了选择多个来源，我们的方法基于形状根发现来衡量数据集的迁移性。虽然传统迁移学习方法需要相当长的时间来预训练每个可能架构的每个可能来源，但我们的方法可以进行简单的计算，即可用于所有可能的架构。通过使用所提出的方法，我们证明了在时间序列数据集上，可以提高时间卷积神经网络（CNN）的性能。
URL
https://arxiv.org/abs/2409.20005
PDF
-
TSI: A Multi-View Representation Learning Approach for Time Series Forecasting
2024-09-30 02:11:57Wentao Gao, Ziqi Xu, Jiuyong Li, Lin Liu, Jixue Liu, Thuc Duy Le, Debo Cheng, Yanchang Zhao, Yun ChenAbstract
As the growing demand for long sequence time-series forecasting in real-world applications, such as electricity consumption planning, the significance of time series forecasting becomes increasingly crucial across various domains. This is highlighted by recent advancements in representation learning within the field. This study introduces a novel multi-view approach for time series forecasting that innovatively integrates trend and seasonal representations with an Independent Component Analysis (ICA)-based representation. Recognizing the limitations of existing methods in representing complex and high-dimensional time series data, this research addresses the challenge by combining TS (trend and seasonality) and ICA (independent components) perspectives. This approach offers a holistic understanding of time series data, going beyond traditional models that often miss nuanced, nonlinear relationships. The efficacy of TSI model is demonstrated through comprehensive testing on various benchmark datasets, where it shows superior performance over current state-of-the-art models, particularly in multivariate forecasting. This method not only enhances the accuracy of forecasting but also contributes significantly to the field by providing a more in-depth understanding of time series data. The research which uses ICA for a view lays the groundwork for further exploration and methodological advancements in time series forecasting, opening new avenues for research and practical applications.
Abstract (translated)
随着实际应用中长序列时间预测需求的不断增长，例如电力消耗规划，时间序列预测的重要性在各个领域日益凸显。这凸显了领域内最近在表示学习方面的进展。这项研究引入了一种新颖的多视角方法来进行时间序列预测，创新地将趋势和季节表示与基于独立成分分析（ICA）的表示相结合。 Recognizing the limitations of existing methods in representing complex and high-dimensional time series data, this research addresses the challenge by combining TS (趋势和季节性) and ICA (独立成分) perspectives. 这种方法提供了一个全面理解时间序列数据的整体视角，超越了通常会忽视复杂非线性关系的老式模型。 TSI 模型的有效性通过在各种基准数据集上的全面测试得到了证实，它显示在多变量预测方面优于当前最先进的模型，尤其是在多元预测方面。这项方法不仅提高了预测的准确性，而且对领域做出了重要贡献，通过提供对时间序列数据的更深入的理解。使用 ICA 进行视角的研究为进一步探索时间序列预测方法和理论提供了基础，为研究和技术应用打开了新的途径。
URL
https://arxiv.org/abs/2409.19871
PDF
-
Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation
2024-09-29 09:46:50Yucheng Wang, Peiliang Gong, Min Wu, Felix Ott, Xiaoli Li, Lihua Xie, Zhenghua ChenAbstract
Source-Free Unsupervised Domain Adaptation (SFUDA) has gained popularity for its ability to adapt pretrained models to target domains without accessing source domains, ensuring source data privacy. While SFUDA is well-developed in visual tasks, its application to Time-Series SFUDA (TS-SFUDA) remains limited due to the challenge of transferring crucial temporal dependencies across domains. Although a few researchers begin to explore this area, they rely on specific source domain designs, which are impractical as source data owners cannot be expected to follow particular pretraining protocols. To solve this, we propose Temporal Source Recovery (TemSR), a framework that transfers temporal dependencies for effective TS-SFUDA without requiring source-specific designs. TemSR features a recovery process that leverages masking, recovery, and optimization to generate a source-like distribution with recovered source temporal dependencies. To ensure effective recovery, we further design segment-based regularization to restore local dependencies and anchor-based recovery diversity maximization to enhance the diversity of the source-like distribution. The source-like distribution is then adapted to the target domain using traditional UDA techniques. Extensive experiments across multiple TS tasks demonstrate the effectiveness of TemSR, even surpassing existing TS-SFUDA method that requires source domain designs. Code is available in this https URL.
Abstract (translated)
无监督源域适应（SFUDA）因其在不需要访问源域的情况下将预训练模型适应目标域的能力而受到欢迎，从而确保了源数据的隐私。尽管SFUDA在视觉任务上表现良好，但其在时间序列数据上的应用仍然受到将关键时间依赖关系从一个域转移到另一个域的挑战的限制。尽管一些研究人员开始探索这个领域，但他们依赖于特定的源域设计，这是不切实际的，因为源数据的所有者不可能期望遵循特定的预训练协议。为解决这个问题，我们提出了 Temporal Source Recovery（TemSR），一种不需要特定源域设计的有效时间序列数据源域适应（TS-SFUDA）框架。TemSR具有一个利用掩码、恢复和优化生成具有恢复的源时间依赖关系的源类似分布的恢复过程。为了确保有效的恢复，我们进一步设计了基于分段的正则化，以恢复局部依赖关系，并最大化了基于锚点的恢复多样性，以增强源类似分布的多样性。然后，使用传统的UDA技术将源类似分布适应目标域。在多个TS任务的不同实验中，TemSR的有效性得到了充分证明，甚至超过了需要源域设计的要求现有的TS-SFUDA方法。代码可以从该https URL找到。
URL
https://arxiv.org/abs/2409.19635
PDF
