The comparative performance of hierarchical classification (HC) and flat classification (FC) methodologies in the realm of time series data analysis is investigated in this study. Dissimilarity measures, including Jensen-Shannon Distance (JSD), Task Similarity Distance (TSD), and Classifier Based Distance (CBD), are leveraged alongside various classifiers such as MINIROCKET, STSF, and SVM. A subset of datasets from the UCR archive, focusing on multi-class cases comprising more than two classes, is employed for analysis. A significant trend is observed wherein HC demonstrates significant superiority over FC when paired with MINIROCKET utilizing TSD, diverging from conventional understandings. Conversely, FC exhibits consistent dominance across all configurations when employing alternative classifiers such as STSF and SVM. Moreover, TSD is found to consistently outperform both CBD and JSD across nearly all scenarios, except in instances involving the STSF classifier where CBD showcases superior performance. This discrepancy underscores the nuanced nature of dissimilarity measures and emphasizes the importance of their tailored selection based on the dataset and classifier employed. Valuable insights into the dynamic interplay between classification methodologies and dissimilarity measures in the realm of time series data analysis are provided by these findings. By elucidating the performance variations across different configurations, a foundation is laid for refining classification methodologies and dissimilarity measures to optimize performance in diverse analytical scenarios. Furthermore, the need for continued research aimed at elucidating the underlying mechanisms driving classification performance in time series data analysis is underscored, with implications for enhancing predictive modeling and decision-making in various domains.
Time series analysis is vital for numerous applications, and transformers have become increasingly prominent in this domain. Leading methods customize the transformer architecture from NLP and CV, utilizing a patching technique to convert continuous signals into segments. Yet, time series data are uniquely challenging due to significant distribution shifts and intrinsic noise levels. To address these two challenges,we introduce the Sparse Vector Quantized FFN-Free Transformer (Sparse-VQ). Our methodology capitalizes on a sparse vector quantization technique coupled with Reverse Instance Normalization (RevIN) to reduce noise impact and capture sufficient statistics for forecasting, serving as an alternative to the Feed-Forward layer (FFN) in the transformer architecture. Our FFN-free approach trims the parameter count, enhancing computational efficiency and reducing overfitting. Through evaluations across ten benchmark datasets, including the newly introduced CAISO dataset, Sparse-VQ surpasses leading models with a 7.84% and 4.17% decrease in MAE for univariate and multivariate time series forecasting, respectively. Moreover, it can be seamlessly integrated with existing transformer-based models to elevate their performance.
In this study, we present aLLM4TS, an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning. Central to our approach is that we reconceive time-series forecasting as a self-supervised, multi-patch prediction task, which, compared to traditional mask-and-reconstruction methods, captures temporal dynamics in patch representations more effectively. Our strategy encompasses two-stage training: (i). a causal continual pre-training phase on various time-series datasets, anchored on next patch prediction, effectively syncing LLM capabilities with the intricacies of time-series data; (ii). fine-tuning for multi-patch prediction in the targeted time-series context. A distinctive element of our framework is the patch-wise decoding layer, which departs from previous methods reliant on sequence-level decoding. Such a design directly transposes individual patches into temporal sequences, thereby significantly bolstering the model's proficiency in mastering temporal patch-based representations. aLLM4TS demonstrates superior performance in several downstream tasks, proving its effectiveness in deriving temporal representations with enhanced transferability and marking a pivotal advancement in the adaptation of LLMs for time-series analysis.
Generative diffusion models and many stochastic models in science and engineering naturally live in infinite dimensions before discretisation. To incorporate observed data for statistical and learning tasks, one needs to condition on observations. While recent work has treated conditioning linear processes in infinite dimensions, conditioning non-linear processes in infinite dimensions has not been explored. This paper conditions function valued stochastic processes without prior discretisation. To do so, we use an infinite-dimensional version of Girsanov's theorem to condition a function-valued stochastic process, leading to a stochastic differential equation (SDE) for the conditioned process involving the score. We apply this technique to do time series analysis for shapes of organisms in evolutionary biology, where we discretise via the Fourier basis and then learn the coefficients of the score function with score matching methods.
In the burgeoning field of autonomous vehicles (AVs), trajectory prediction remains a formidable challenge, especially in mixed autonomy environments. Traditional approaches often rely on computational methods such as time-series analysis. Our research diverges significantly by adopting an interdisciplinary approach that integrates principles of human cognition and observational behavior into trajectory prediction models for AVs. We introduce a novel "adaptive visual sector" mechanism that mimics the dynamic allocation of attention human drivers exhibit based on factors like spatial orientation, proximity, and driving speed. Additionally, we develop a "dynamic traffic graph" using Convolutional Neural Networks (CNN) and Graph Attention Networks (GAT) to capture spatio-temporal dependencies among agents. Benchmark tests on the NGSIM, HighD, and MoCAD datasets reveal that our model (GAVA) outperforms state-of-the-art baselines by at least 15.2%, 19.4%, and 12.0%, respectively. Our findings underscore the potential of leveraging human cognition principles to enhance the proficiency and adaptability of trajectory prediction algorithms in AVs. The code for the proposed model is available at our Github.
Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful convergence to the optimal policy during training, may obfuscate overfitting or dependence on the experimental setup. Although researchers in RL have proposed reliability metrics that account for uncertainty to better understand each algorithm's strengths and weaknesses, the recommendations of past work do not assume the presence of out-of-distribution observations. We propose a set of evaluation methods that measure the robustness of RL algorithms under distribution shifts. The tools presented here argue for the need to account for performance over time while the agent is acting in its environment. In particular, we recommend time series analysis as a method of observational RL evaluation. We also show that the unique properties of RL and simulated dynamic environments allow us to make stronger assumptions to justify the measurement of causal impact in our evaluations. We then apply these tools to single-agent and multi-agent environments to show the impact of introducing distribution shifts during test time. We present this methodology as a first step toward rigorous RL evaluation in the presence of distribution shifts.
Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis, distinguished by its focus on extensive input sequences, in contrast to the constrained lengths typical of traditional approaches. While longer sequences inherently convey richer information, potentially enhancing predictive precision, prevailing techniques often respond by escalating model complexity. These intricate models can inflate into millions of parameters, incorporating parameter-intensive elements like positional encodings, feed-forward networks and self-attention mechanisms. This complexity, however, leads to prohibitive model scale, particularly given the time series data's semantic simplicity. Motivated by the pursuit of parsimony, our research employs conditional correlation and auto-correlation as investigative tools, revealing significant redundancies within the input data. Leveraging these insights, we introduce the HDformer, a lightweight Transformer variant enhanced with hierarchical decomposition. This novel architecture not only inverts the prevailing trend toward model expansion but also accomplishes precise forecasting with drastically fewer computations and parameters. Remarkably, HDformer outperforms existing state-of-the-art LTSF models, while requiring over 99\% fewer parameters. Through this work, we advocate a paradigm shift in LTSF, emphasizing the importance to tailor the model to the inherent dynamics of time series data-a timely reminder that in the realm of LTSF, bigger is not invariably better.
To handle the complexities of irregular and incomplete time series data, we propose an invertible solution of Neural Differential Equations (NDE)-based method. While NDE-based methods are a powerful method for analyzing irregularly-sampled time series, they typically do not guarantee reversible transformations in their standard form. Our method suggests the variation of Neural Controlled Differential Equations (Neural CDEs) with Neural Flow, which ensures invertibility while maintaining a lower computational burden. Additionally, it enables the training of a dual latent space, enhancing the modeling of dynamic temporal dynamics. Our research presents an advanced framework that excels in both classification and interpolation tasks. At the core of our approach is an enhanced dual latent states architecture, carefully designed for high precision across various time series tasks. Empirical analysis demonstrates that our method significantly outperforms existing models. This work significantly advances irregular time series analysis, introducing innovative techniques and offering a versatile tool for diverse practical applications.
This survey delves into the application of diffusion models in time-series forecasting. Diffusion models are demonstrating state-of-the-art results in various fields of generative AI. The paper includes comprehensive background information on diffusion models, detailing their conditioning methods and reviewing their use in time-series forecasting. The analysis covers 11 specific time-series implementations, the intuition and theory behind them, the effectiveness on different datasets, and a comparison among each other. Key contributions of this work are the thorough exploration of diffusion models' applications in time-series forecasting and a chronologically ordered overview of these models. Additionally, the paper offers an insightful discussion on the current state-of-the-art in this domain and outlines potential future research directions. This serves as a valuable resource for researchers in AI and time-series analysis, offering a clear view of the latest advancements and future potential of diffusion models.
Contrastive representation learning is crucial in time series analysis as it alleviates the issue of data noise and incompleteness as well as sparsity of supervision signal. However, existing constrastive learning frameworks usually focus on intral-temporal features, which fails to fully exploit the intricate nature of time series data. To address this issue, we propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp to obtain optimized sub-sequences. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series to learn the underlying structure feature on the unlabeled time series. Meanwhile, we design a supervised task to learn more robust representations and facilitate the contrastive learning process. Finally, we jointly optimize the above two tasks. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task. Extensive experiments, in comparison with state-of-the-arts, well demonstrate the effectiveness of DE-TSMCL, where the maximum improvement can reach to 27.3%.