Ordinary Differential Equations (ODE)-based models have become popular foundation models to solve many time-series problems. Combining neural ODEs with traditional RNN models has provided the best representation for irregular time series. However, ODE-based models require the trajectory of hidden states to be defined based on the initial observed value or the last available observation. This fact raises questions about how long the generated hidden state is sufficient and whether it is effective when long sequences are used instead of the typically used shorter sequences. In this article, we introduce CrossPyramid, a novel ODE-based model that aims to enhance the generalizability of sequences representation. CrossPyramid does not rely only on the hidden state from the last observed value; it also considers ODE latent representations learned from other samples. The main idea of our proposed model is to define the hidden state for the unobserved values based on the non-linear correlation between samples. Accordingly, CrossPyramid is built with three distinctive parts: (1) ODE Auto-Encoder to learn the best data representation. (2) Pyramidal attention method to categorize the learned representations (hidden state) based on the relationship characteristics between samples. (3) Cross-level ODE-RNN to integrate the previously learned information and provide the final latent state for each sample. Through extensive experiments on partially-observed synthetic and real-world datasets, we show that the proposed architecture can effectively model the long gaps in intermittent series and outperforms state-of-the-art approaches. The results show an average improvement of 10\% on univariate and multivariate datasets for both forecasting and classification tasks.
Predicting the health risks of patients using Electronic Health Records (EHR) has attracted considerable attention in recent years, especially with the development of deep learning techniques. Health risk refers to the probability of the occurrence of a specific health outcome for a specific patient. The predicted risks can be used to support decision-making by healthcare professionals. EHRs are structured patient journey data. Each patient journey contains a chronological set of clinical events, and within each clinical event, there is a set of clinical/medical activities. Due to variations of patient conditions and treatment needs, EHR patient journey data has an inherently high degree of missingness that contains important information affecting relationships among variables, including time. Existing deep learning-based models generate imputed values for missing values when learning the relationships. However, imputed data in EHR patient journey data may distort the clinical meaning of the original EHR patient journey data, resulting in classification bias. This paper proposes a novel end-to-end approach to modeling EHR patient journey data with Integrated Convolutional and Recurrent Neural Networks. Our model can capture both long- and short-term temporal patterns within each patient journey and effectively handle the high degree of missingness in EHR data without any imputation data generation. Extensive experimental results using the proposed model on two real-world datasets demonstrate robust performance as well as superior prediction accuracy compared to existing state-of-the-art imputation-based prediction methods.
In this paper, we propose a novel pipeline that leverages language foundation models for temporal sequential pattern mining, such as for human mobility forecasting tasks. For example, in the task of predicting Place-of-Interest (POI) customer flows, typically the number of visits is extracted from historical logs, and only the numerical data are used to predict visitor flows. In this research, we perform the forecasting task directly on the natural language input that includes all kinds of information such as numerical values and contextual semantic information. Specific prompts are introduced to transform numerical temporal sequences into sentences so that existing language models can be directly applied. We design an AuxMobLCast pipeline for predicting the number of visitors in each POI, integrating an auxiliary POI category classification task with the encoder-decoder architecture. This research provides empirical evidence of the effectiveness of the proposed AuxMobLCast pipeline to discover sequential patterns in mobility forecasting tasks. The results, evaluated on three real-world datasets, demonstrate that pre-trained language foundation models also have good performance in forecasting temporal sequences. This study could provide visionary insights and lead to new research directions for predicting human mobility.
Self-Supervised Learning (SSL) is a new paradigm for learning discriminative representations without labelled data and has reached comparable or even state-of-the-art results in comparison to supervised counterparts. Contrastive Learning (CL) is one of the most well-known approaches in SSL that attempts to learn general, informative representations of data. CL methods have been mostly developed for applications in computer vision and natural language processing where only a single sensor modality is used. A majority of pervasive computing applications, however, exploit data from a range of different sensor modalities. While existing CL methods are limited to learning from one or two data sources, we propose COCOA (Cross mOdality COntrastive leArning), a self-supervised model that employs a novel objective function to learn quality representations from multisensor data by computing the cross-correlation between different data modalities and minimizing the similarity between irrelevant instances. We evaluate the effectiveness of COCOA against eight recently introduced state-of-the-art self-supervised models, and two supervised baselines across five public datasets. We show that COCOA achieves superior classification performance to all other approaches. Also, COCOA is far more label-efficient than the other baselines including the fully supervised model using only one-tenth of available labelled data.
Building models for health prediction based on Electronic Health Records (EHR) has become an active research area. EHR patient journey data consists of patient time-ordered clinical events/visits from patients. Most existing studies focus on modeling long-term dependencies between visits, without explicitly taking short-term correlations between consecutive visits into account, where irregular time intervals, incorporated as auxiliary information, are fed into health prediction models to capture latent progressive patterns of patient journeys. We present a novel deep neural network with four modules to take into account the contributions of various variables for health prediction: i) the Stacked Attention module strengthens the deep semantics in clinical events within each patient journey and generates visit embeddings, ii) the Short-Term Temporal Attention module models short-term correlations between consecutive visit embeddings while capturing the impact of time intervals within those visit embeddings, iii) the Long-Term Temporal Attention module models long-term dependencies between visit embeddings while capturing the impact of time intervals within those visit embeddings, iv) and finally, the Coupled Attention module adaptively aggregates the outputs of Short-Term Temporal Attention and Long-Term Temporal Attention modules to make health predictions. Experimental results on MIMIC-III demonstrate superior predictive accuracy of our model compared to existing state-of-the-art methods, as well as the interpretability and robustness of this approach. Furthermore, we found that modeling short-term correlations contributes to local priors generation, leading to improved predictive modeling of patient journeys.
Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in the field of computer vision, speech, natural language processing (NLP), and recently, with other types of modalities, including time series from sensors. The popularity of self-supervised learning is driven by the fact that traditional models typically require a huge amount of well-annotated data for training. Acquiring annotated data can be a difficult and costly process. Self-supervised methods have been introduced to improve the efficiency of training data through discriminative pre-training of models using supervisory signals that have been freely obtained from the raw data. Unlike existing reviews of SSRL that have pre-dominately focused upon methods in the fields of CV or NLP for a single modality, we aim to provide the first comprehensive review of multimodal self-supervised learning methods for temporal data. To this end, we 1) provide a comprehensive categorization of existing SSRL methods, 2) introduce a generic pipeline by defining the key components of a SSRL framework, 3) compare existing models in terms of their objective function, network architecture and potential applications, and 4) review existing multimodal techniques in each category and various modalities. Finally, we present existing weaknesses and future opportunities. We believe our work develops a perspective on the requirements of SSRL in domains that utilise multimodal and/or temporal data
Disentangled representation learning offers useful properties such as dimension reduction and interpretability, which are essential to modern deep learning approaches. Although deep learning techniques have been widely applied to spatio-temporal data mining, there has been little attention to further disentangle the latent features and understanding their contribution to the model performance, particularly their mutual information and correlation across features. In this study, we adopt two state-of-the-art disentangled representation learning methods and apply them to three large-scale public spatio-temporal datasets. To evaluate their performance, we propose an internal evaluation metric focusing on the degree of correlations among latent variables of the learned representations and the prediction performance of the downstream tasks. Empirical results show that our modified method can learn disentangled representations that achieve the same level of performance as existing state-of-the-art ST deep learning methods in a spatio-temporal sequence forecasting problem. Additionally, we find that our methods can be used to discover real-world spatial-temporal semantics to describe the variables in the learned representation.
As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal predictive modeling for crowd movements is a challenging task particularly considering scenarios where societal events drive mobility behavior deviated from the normality. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes nor adaptive to unprecedented volatility brought by potential societal events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced event-aware spatio-temporal network, namely EAST-Net, is evaluated on several real-world datasets with a wide variety and coverage of societal events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/underdoc-wang/EAST-Net.
Existing human mobility forecasting models follow the standard design of the time-series prediction model which takes a series of numerical values as input to generate a numerical value as a prediction. Although treating this as a regression problem seems straightforward, incorporating various contextual information such as the semantic category information of each Place-of-Interest (POI) is a necessary step, and often the bottleneck, in designing an effective mobility prediction model. As opposed to the typical approach, we treat forecasting as a translation problem and propose a novel forecasting through a language generation pipeline. The paper aims to address the human mobility forecasting problem as a language translation task in a sequence-to-sequence manner. A mobility-to-language template is first introduced to describe the numerical mobility data as natural language sentences. The core intuition of the human mobility forecasting translation task is to convert the input mobility description sentences into a future mobility description from which the prediction target can be obtained. Under this pipeline, a two-branch network, SHIFT (Translating Human Mobility Forecasting), is designed. Specifically, it consists of one main branch for language generation and one auxiliary branch to directly learn mobility patterns. During the training, we develop a momentum mode for better connecting and training the two branches. Extensive experiments on three real-world datasets demonstrate that the proposed SHIFT is effective and presents a new revolutionary approach to forecasting human mobility.
Heterogeneity and irregularity of multi-source data sets present a significant challenge to time-series analysis. In the literature, the fusion of multi-source time-series has been achieved either by using ensemble learning models which ignore temporal patterns and correlation within features or by defining a fixed-size window to select specific parts of the data sets. On the other hand, many studies have shown major improvement to handle the irregularity of time-series, yet none of these studies has been applied to multi-source data. In this work, we design a novel architecture, PIETS, to model heterogeneous time-series. PIETS has the following characteristics: (1) irregularity encoders for multi-source samples that can leverage all available information and accelerate the convergence of the model; (2) parallelised neural networks to enable flexibility and avoid information overwhelming; and (3) attention mechanism that highlights different information and gives high importance to the most related data. Through extensive experiments on real-world data sets related to COVID-19, we show that the proposed architecture is able to effectively model heterogeneous temporal data and outperforms other state-of-the-art approaches in the prediction task.