Irregularly, asynchronously and sparsely sampled multivariate time series (IASS-MTS) are characterized by sparse and uneven time intervals and nonsynchronous sampling rates, posing significant challenges for machine learning models to learn complex relationships within and beyond IASS-MTS to support various inference tasks. The existing methods typically either focus solely on single-task forecasting or simply concatenate them through a separate preprocessing imputation procedure for the subsequent classification application. However, these methods often ignore valuable annotated labels or fail to discover meaningful patterns from unlabeled data. Moreover, the approach of separate prefilling may introduce errors due to the noise in raw records, and thus degrade the downstream prediction performance. To overcome these challenges, we propose the time-aware dual attention and memory-augmented network (DAMA) with stochastic generative imputation (SGI). Our model constructs a joint task learning architecture that unifies imputation and classification tasks collaboratively. First, we design a new time-aware DAMA that accounts for irregular sampling rates, inherent data nonalignment, and sparse values in IASS-MTS data. The proposed network integrates both attention and memory to effectively analyze complex interactions within and across IASS-MTS for the classification task. Second, we develop the stochastic generative imputation (SGI) network that uses auxiliary information from sequence data for inferring the time series missing observations. By balancing joint tasks, our model facilitates interaction between them, leading to improved performance on both classification and imputation tasks. Third, we evaluate our model on real-world datasets and demonstrate its superior performance in terms of imputation accuracy and classification results, outperforming the baselines.

Irregularly, asynchronously and sparsely sampled multivariate time series (IASS-MTS) are characterized by sparse non-uniform time intervals between successive observations and different sampling rates amongst series. Those properties pose substantial challenges to mainstream machine learning models for learning complicated relations within and across IASS-MTS. This is because that most of the models assume that the time series in question are even, complete (fixed-dimensional features) and synchronous. To address these challenges, we present a novel time-aware Dual-Attention and Memory-Augmented Network (DAMA-Net). The proposed model can leverage both time irregularity, multi-sampling rates and global temporal patterns information inherent in IASS-MTS so as to learn more effective representations for improving prediction performance. Comprehensive experiments on real datasets show that the DAMA-Net outperforms the state-of-the-art methods in multivariate time series classification task.

Long-term traffic flow prediction plays a crucial role in intelligent transportation systems. However, the temporal nonstationary nature of data from traffic detector nodes and the interdependence among nodes pose significant challenges in this prediction task. Therefore, we propose a traffic prediction transformer framework, called TPformer, to learn the spatiotemporal correlations of traffic features among traffic detector nodes. The success of applying the transformer to traffic flow prediction relies on the following key factors: 1) The length of both the input sequence and the predicted sequence is equal to the number of detector nodes, facilitating the construction of a node-node attention mechanism. 2) A node triplet encoding is introduced to allocate additional local contextual structural features to each node. 3) The topological structural features of the transportation network are incorporated into the self-attention mechanism, allowing the model to focus more on neighboring nodes when encoding the node traffic feature. Experimental results on two real-world datasets from the Performance Measurement System (PeMS) demonstrate that the proposed model outperforms state-of-the-art baselines in both short-term and long-term prediction tasks.

Over the past few years, deep learning-based approaches have come to dominate the areas of image processing, with no exception to the field of image denoising. Recently, self-supervised denoising networks have garnered extensive attention in the zero-shot domain. Nevertheless, training the denoising network solely with zero-shot data will lead to significant detail loss, thereby influencing the denoising quality. In this work, we proposed a novel dual mask mechanism based on Euclidean distance selection as a global masker for the blind spot network, thereby enhancing image quality and mitigating image detail loss. Furthermore, we also constructed a recurrent framework, named Blind2Grad, which integrated the gradient-regularized loss and a uniform loss for training the denoiser and enabled the double-mask mechanism to be continuously updated. This framework was capable of directly acquiring information from the original noisy image, giving priority to the key information that needed to be retained without succumbing to equivalent mapping. Moreover, we conducted a thorough theoretical analysis of the convergence properties of our Blind2Grad loss from both probabilistic and game-theoretic viewpoints, demonstrating its consistency with supervised methods. Our Blind2Grad not only demonstrated outstanding performance on both synthetic and real-world datasets, but also exhibited significant efficacy in processing images with high noise levels.