We propose two solutions to outlier detection in time series based on recurrent autoencoder ensembles. The solutions exploit autoencoders built using sparsely-connected recurrent neural networks (S-RNNs). Such networks make it possible to generate multiple autoencoders with different neural network connection structures. The two solutions are ensemble frameworks, specifically an independent framework and a shared framework, both of which combine multiple S-RNN based autoencoders to enable outlier detection. This ensemble-based approach aims to reduce the effects of some autoencoders being overfitted to outliers, this way improving overall detection quality. Experiments with two large real-world time series data sets, including univariate and multivariate time series, offer insight into the design properties of the proposed frameworks and demonstrate that the resulting solutions are capable of outperforming both baselines and the state-of-the-art methods.

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods demonstrate good forecasting abilities, they have three fundamental limitations. (i). Discrete neural architectures: Interlacing individually parameterized spatial and temporal blocks to encode rich underlying patterns leads to discontinuous latent state trajectories and higher forecasting numerical errors. (ii). High complexity: Discrete approaches complicate models with dedicated designs and redundant parameters, leading to higher computational and memory overheads. (iii). Reliance on graph priors: Relying on predefined static graph structures limits their effectiveness and practicability in real-world applications. In this paper, we address all the above limitations by proposing a continuous model to forecast M ultivariate T ime series with dynamic G raph neural O rdinary D ifferential E quations ( MTGODE ). Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing, allowing deeper graph propagation and fine-grained temporal information aggregation to characterize stable and precise latent spatial-temporal dynamics. Our experiments demonstrate the superiorities of MTGODE from various perspectives on five time series benchmark datasets.

When planning routes, drivers usually consider a multitude of different travel costs, e.g., distances, travel times, and fuel consumption. Different drivers may choose different routes between the same source and destination because they may have different driving preferences (e.g., time-efficient driving v.s. fuel-efficient driving). However, existing routing services support little in modeling multiple travel costs and personalization-they usually deliver the same routes that minimize a single travel cost (e.g., the shortest routes or the fastest routes) to all drivers. We study the problem of how to recommend personalized routes to individual drivers using big trajectory data. First, we provide techniques capable of modeling and updating different drivers' driving preferences from the drivers' trajectories while considering multiple travel costs. To recommend personalized routes, we provide techniques that enable efficient selection of a subset of trajectories from all trajectories according to a driver's preference and the source, destination, and departure time specified by the driver. Next, we provide techniques that enable the construction of a small graph with appropriate edge weights reflecting how the driver would like to use the edges based on the selected trajectories. Finally, we recommend the shortest route in the small graph as the personalized route to the driver. Empirical studies with a large, real trajectory data set from 52,211 taxis in Beijing offer insight into the design properties of the proposed techniques and suggest that they are efficient and effective.

Due to the continued digitization of industrial and societal processes, including the deployment of networked sensors, we are witnessing a rapid proliferation of time-ordered observations, known as time series. For example, the behavior of drivers can be captured by GPS or accelerometer as a time series of speeds, directions, and accelerations. We propose a framework for outlier detection in time series that, for example, can be used for identifying dangerous driving behavior and hazardous road locations. Specifically, we first propose a method that generates statistical features to enrich the feature space of raw time series. Next, we utilize an autoencoder to reconstruct the enriched time series. The autoencoder performs dimensionality reduction to capture, using a small feature space, the most representative features of the enriched time series. As a result, the reconstructed time series only capture representative features, whereas outliers often have non-representative features. Therefore, deviations of the enriched time series from the reconstructed time series can be taken as indicators of outliers. We propose and study autoencoders based on convolutional neural networks and long-short term memory neural networks. In addition, we show that embedding of contextual information into the framework has the potential to further improve the accuracy of identifying outliers. We report on empirical studies with multiple time series data sets, which offers insight into the design properties of the proposed framework, indicating that it is effective at detecting outliers.

Due to the sweeping digitalization of processes, increasingly vast amounts of time series data are being produced. Accurate classification of such time series facilitates decision making in multiple domains. State-of-the-art classification accuracy is often achieved by ensemble learning where results are synthesized from multiple base models. This characteristic implies that ensemble learning needs substantial computing resources, preventing their use in resource-limited environments, such as in edge devices. To extend the applicability of ensemble learning, we propose the LightTS framework that compresses large ensembles into lightweight models while ensuring competitive accuracy. First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model. Second, we propose means of identifying Pareto optimal settings w.r.t. model accuracy and model size, thus enabling users with a space budget to select the most accurate lightweight model. We report on experiments using 128 real-world time series sets and different types of base models that justify key decisions in the design of LightTS and provide evidence that LightTS is able to outperform competitors.