Time series forecasting always faces the challenge of concept drift, where data distributions evolve over time, leading to a decline in forecast model performance. Existing solutions are based on online learning, which continually organize recent time series observations as new training samples and update model parameters according to the forecasting feedback on recent data. However, they overlook a critical issue: obtaining ground-truth future values of each sample should be delayed until after the forecast horizon. This delay creates a temporal gap between the training samples and the test sample. Our empirical analysis reveals that the gap can introduce concept drift, causing forecast models to adapt to outdated concepts. In this paper, we present Proceed, a novel proactive model adaptation framework for online time series forecasting. Proceed first estimates the concept drift between the recently used training samples and the current test sample. It then employs an adaptation generator to efficiently translate the estimated drift into parameter adjustments, proactively adapting the model to the test sample. To enhance the generalization capability of the framework, Proceed is trained on synthetic diverse concept drifts. Extensive experiments on five real-world datasets across various forecast models demonstrate that Proceed brings more performance improvements than the state-of-the-art online learning methods, significantly facilitating forecast models' resilience against concept drifts. Code is available at https://github.com/SJTU-DMTai/OnlineTSF.

Scaling laws motivate the development of Time Series Foundation Models (TSFMs) that pre-train vast parameters and achieve remarkable zero-shot forecasting performance. Surprisingly, even after fine-tuning, TSFMs cannot consistently outperform smaller, specialized models trained on full-shot downstream data. A key question is how to realize effective adaptation of TSFMs for a target forecasting task. Through empirical studies on various TSFMs, the pre-trained models often exhibit inherent sparsity and redundancy in computation, suggesting that TSFMs have learned to activate task-relevant network substructures to accommodate diverse forecasting tasks. To preserve this valuable prior knowledge, we propose a structured pruning method to regularize the subsequent fine-tuning process by focusing it on a more relevant and compact parameter space. Extensive experiments on seven TSFMs and six benchmarks demonstrate that fine-tuning a smaller, pruned TSFM significantly improves forecasting performance compared to fine-tuning original models. This ``prune-then-finetune'' paradigm often enables TSFMs to achieve state-of-the-art performance and surpass strong specialized baselines. Source code is made publicly available at \url{https://github.com/SJTU-DMTai/Prune-then-Finetune}.

Recently, channel-independent methods have achieved state-of-the-art performance in multivariate time series (MTS) forecasting. Despite reducing overfitting risks, these methods miss potential opportunities in utilizing channel dependence for accurate predictions. We argue that there exist locally stationary lead-lag relationships between variates, i.e., some lagged variates may follow the leading indicators within a short time period. Exploiting such channel dependence is beneficial since leading indicators offer advance information that can be used to reduce the forecasting difficulty of the lagged variates. In this paper, we propose a new method named LIFT that first efficiently estimates leading indicators and their leading steps at each time step and then judiciously allows the lagged variates to utilize the advance information from leading indicators. LIFT plays as a plugin that can be seamlessly collaborated with arbitrary time series forecasting methods. Extensive experiments on six real-world datasets demonstrate that LIFT improves the state-of-the-art methods by 5.4% in average forecasting performance. Our code is available at https://github.com/SJTU-Quant/LIFT.

Stock trend forecasting is a fundamental task of quantitative investment where precise predictions of price trends are indispensable. As an online service, stock data continuously arrive over time. It is practical and efficient to incrementally update the forecast model with the latest data which may reveal some new patterns recurring in the future stock market. However, incremental learning for stock trend forecasting still remains under-explored due to the challenge of distribution shifts (a.k.a. concept drifts). With the stock market dynamically evolving, the distribution of future data can slightly or significantly differ from incremental data, hindering the effectiveness of incremental updates. To address this challenge, we propose DoubleAdapt, an end-to-end framework with two adapters, which can effectively adapt the data and the model to mitigate the effects of distribution shifts. Our key insight is to automatically learn how to adapt stock data into a locally stationary distribution in favor of profitable updates. Complemented by data adaptation, we can confidently adapt the model parameters under mitigated distribution shifts. We cast each incremental learning task as a meta-learning task and automatically optimize the adapters for desirable data adaptation and parameter initialization. Experiments on real-world stock datasets demonstrate that DoubleAdapt achieves state-of-the-art predictive performance and shows considerable efficiency.

Click-through Rate (CTR) prediction on cold users is a challenging task in recommender systems. Recent researches have resorted to meta-learning to tackle the cold-user challenge, which either perform few-shot user representation learning or adopt optimization-based meta-learning. However, existing methods suffer from information loss or inefficient optimization process, and they fail to explicitly model global user preference knowledge, which is crucial to complement the sparse and insufficient preference information of cold users. In this article, we propose a novel and efficient approach named RESUS, which decouples the learning of global preference knowledge contributed by collective users from the learning of residual preferences for individual users. Specifically, we employ a shared predictor to infer basis user preferences, which acquires global preference knowledge from the interactions of different users. Meanwhile, we develop two efficient algorithms based on the nearest neighbor and ridge regression predictors, which infer residual user preferences via learning quickly from a few user-specific interactions. Extensive experiments on three public datasets demonstrate that our RESUS approach is efficient and effective in improving CTR prediction accuracy on cold users, compared with various state-of-the-art methods.

Unsupervised image-to-image (UI2I) translation methods aim to learn a mapping between different visual domains with well-preserved content and consistent structure. It has been proven that the generated images are quite useful for enhancing the performance of computer vision tasks like object detection in a different domain with distribution discrepancies. Current methods require large amounts of images in both source and target domains for successful translation. However, data collection and annotations in many scenarios are infeasible or even impossible. In this paper, we propose an Object-Aware Few-Shot UI2I Translation (OA-FSUI2IT) framework to address the few-shot cross domain (FSCD) object detection task with limited unlabeled images in the target domain. To this end, we first introduce a discriminator augmentation (DA) module into the OA-FSUI2IT framework for successful few-shot UI2I translation. Then, we present a patch pyramid contrastive learning (PPCL) strategy to further improve the quality of the generated images. Last, we propose a self-supervised content-consistency (SSCC) loss to enforce the content-consistency in the translation. We implement extensive experiments to demonstrate the effectiveness of our OA-FSUI2IT framework for FSCD object detection and achieve state-of-the-art performance on the benchmarks of Normal-to-Foggy, Day-to-Night, and Cross-scene adaptation. The source code of our proposed method is also available at https://github.com/emdata-ailab/FSCD-Det.

Unsupervised image-to-image (UI2I) translation methods aim to learn a mapping between different visual domains with well-preserved content and consistent structure. It has been proven that the generated images are useful for enhancing the performance of computer vision tasks like object detection in a different domain with distribution discrepancies. Current UI2I translation techniques are highly relied on cycle-structure consistency and content/style disentanglement. In-tense focus has been paid on global translation over an en-tire image, instead of the stylistic variations and complex structure among multiple disparate object instances and back-grounds, resulting in unsatisfactory performance gain for the downstream vision tasks. In this work, we propose Patch Pyramid Dual Contrastive Learning Unsupervised Image Translation (PPDCLUIT) framework to strengthen the cross domain object detection performance. We present patch pyra-mid dual contrastive learning strategy for coherent associations at each specific location and propose identity loss to further enforce the object instances preservation. We im-plement extensive experiments to demonstrate the efficacy of our PPDCLUIT framework for cross domain object detection and achieve state-of-the-art performance on the benchmarks of Normal-to-Foggy, and Day-to-Night.

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain sequential recommendation is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of behavioral information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a mixed information flow network for cross-domain sequential recommendation to consider both the flow of behavioral information and the flow of knowledge by incorporating a behavior transfer unit and a knowledge transfer unit . The proposed mixed information flow network is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed mixed information flow network is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of mixed information flow network s to a scenario with two domains, but the method can easily be extended to multiple domains.

Conventional sparsity-driven synthetic aperture radar (SAR) imagery often encounters the sensitivity of nonsystematic errors and highly computational load. In this article, a cooperative multitask learning algorithm is proposed based on an autocalibrated alternating direction method of multipliers (AutoCal-ADMM) framework, by which the sparse feature of the scenes/targets-of-interests can be enhanced, and simultaneously the nonmodeled motion errors of either airborne platform or moving target can be autocalibrated in a synergistic manner. By leveraging the entropy and sparsity regularizers in the AutoCal-ADMM framework, the proposed algorithm is particularly tailored to obtain focused SAR images with enhanced sparsity. A reasonable surrogate function is designed for a convex objective function, so that an analytical proximal mapping of the entropy regularizer can be derived. Both nonsystematic range cell migration (NsRCM) and azimuthal phase errors (APEs) are concerned and coherently compensated. A linear and complex soft-thresholding operator is introduced for the sparse solution. The proposed algorithm is capable of greatly alleviating “error propagation” between multiple tasks, where an optima balance between the sparse and focusing features can be achieved. Superior performance in terms of convergence and efficiency can be guaranteed. Both raw SAR and canonical ground moving target imaging (GMTIm) data sets are processed and comparisons with conventions are performed, where the effectiveness and superiority of the proposed AutoCal-ADMM algorithm are validated.

Time-domain algorithms have special advantages for bistatic forward-looking synthetic aperture radar (BFSAR) applications with complex geometric configuration. In this paper, a improved fast time-domain algorithm based on orthogonal elliptical polar (OEP) coordinate is proposed for BFSAR imaging, which has prominently reduced burden in computation. In addition, the non-systematic range cell migration (NsRCM) is also analyzed and corrected in the motion compensation (MOCO) process. Simulation experiments are presented and analyzed to validate the superiority of the proposed algorithm.

The classical solution to an underdetermined system of linear equations mainly has two opposite directions, which lead to either a large ℓ2-norm sparse solution or a non-sparse minimum ℓ2-norm solution. In this paper, we systematically show that by modifying the well-known basic matching pursuit algorithm originally proposed to identify the sparse solution, an alternative solution between the two classical ones could be obtained. The modified algorithm, termed as random matching pursuit (RMP), is then used to create a novel image watermarking framework. Compared to conventional systems, the security is substantially improved by the use of random over-complete dictionaries and the order parameter of RMP. Capacity can also be increased thanks to the transform with over-complete dictionaries that could expand signal dimension. Meanwhile, imperceptibility and robustness properties of the proposed design framework are not compromised. The classical spread spectrum and improved spread spectrum techniques are applied to the proposed framework for practical implementations. The novelty and effectiveness of the proposed systems are supported by rigorous performance analysis and experimental results using an image data set. This paper reveals the potential of using over-complete dictionaries in multimedia watermarking systems, which theoretically leads to the exploration of alternative candidates among the infinite solutions to underdetermined linear systems other than minimum ℓ2-norm and sparse ones.

Matrix factorization has been widely adopted for recommendation by learning latent embeddings of users and items from observed user-item interaction data. However, previous methods usually assume the learned embeddings are static or homogeneously evolving with the same diffusion rate. This is not valid in most scenarios, where users’ preferences and item attributes heterogeneously drift over time. To remedy this issue, we have proposed a novel dynamic matrix factorization model, named Dynamic Bayesian Logistic Matrix Factorization (DBLMF), which aims to learn heterogeneous user and item embeddings that are drifting with inconsistent diffusion rates. More specifically, DBLMF extends logistic matrix factorization to model the probability a user would like to interact with an item at a given timestamp, and a diffusion process to connect latent embeddings over time. In addition, an efficient Bayesian inference algorithm has also been proposed to make DBLMF scalable on large datasets. The effectiveness of the proposed method has been demonstrated by extensive experiments on real datasets, compared with the state-of-the-art methods.

In this letter, a new spectrum-oriented fast factorized backprojection (FFBP) algorithm is proposed for synthetic aperture radar (SAR) imaging on a maneuvering platform. Specifically, an analytical SAR image spectrum is derived in a novel quasi-polar coordinate system based on the FFBP, which makes it easy to incorporate with an autocalibration process for both systematic and nonsystematic errors. Different from the conventional FFBP algorithms developed in polar grid, the proposed algorithm devised in quasi-polar gird conducts the motion-induced phase error as a space-invariant component, which will definitely facilitate the phase autofocusing process during the FFBP recursions. Subsequently, a phase autofocusing process is incorporated in the resultant SAR image formation algorithm. Simulations and discussions are presented to show the focusing quality improvement made by the proposed algorithm.

Because of flexible geometric configuration and trajectory designation, time-domain algorithms become popular for unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) applications. In this paper, a new quasi-polar-coordinate-based fast factorized back-projection (FFBP) algorithm combined with data-driven motion compensation is proposed for miniature UAV-SAR imaging. By utilizing wavenumber decomposition, the analytical spectrum of a quasi-polar grid image is obtained, where the phase errors arising from the trajectory deviations can be conveniently investigated and the phase autofocusing can be compatibly incorporated. Different from the conventional FFBP based on a polar coordinate system, the proposed algorithm operates in a quasi-polar coordinate system, where the phase errors become spacial invariant and can be accurately estimated and easily compensated. Moreover, the relationship between phase errors and nonsystematic range cell migration (NsRCM) is revealed according to the analytical image spectrum, based on which the NsRCM correction is developed to further improve the image focusing quality for high-resolution SAR applications. Promising experimental results from the raw data experiments of miniature UAV-SAR test bed are presented and analyzed to validate the advantages of the proposed algorithm.

Recently, compressive sensing theory has been successfully applied in inverse synthetic aperture radar (ISAR) imaging. However, the issue of maneuvering target imaging from compressive sampling data has not been sufficiently addressed because it is difficult to jointly deal with both sparse imaging and motion compensation under compressive sampling. In this paper, we develop a novel algorithm of high-resolution ISAR imaging for maneuvering targets from compressive sampling data. In this algorithm, a non-uniform scaled Fourier dictionary is constructed to represent the maneuverability. A hierarchical statistical model is utilized to encode the sparsity of ISAR image. Then, ISAR imaging joint with motion estimation is solved by using a parametric sparse Bayesian leaning (P-SBL) method, including sparse imaging and dictionary learning. Finally, experiments are performed to confirm the effectiveness of the proposed method by using the simulated and measured data.

In this paper, the analytic expression of synthetic aperture radar (SAR) image spectrum in the polar grid system is derived based on the wavenumber analysis. By revealing the relationship between wavenumber variable and image spectrum in the polar system, we can better understand the mechanism of fast factorized BP (FFBP) processing. Moreover, the form of phase error in spectral domain can be possibly revealed which will facilitate motion compensation and autofocusing in FFBP processing. Simulation results are presented and analyzed to demonstrate the validity of the derived spectrum.

Forward velocity extraction is a very important process for obtaining a high-quality unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) image. Because of the constraints of low flying altitude and small platform size, the flight path of the UAV is easily disturbed by the atmospheric turbulence. The complex motion error of the UAV's flight path makes the forward velocity difficult to be extracted from raw SAR data. To address this problem, an adaptive notch filtering (ANF)-based approach for forward velocity extraction is proposed. Based on the kinetic characteristics of the UAV, the variation of Doppler centroid frequency is analyzed and exploited to remove most components of the cross-track acceleration in the low-frequency range. Then, by regarding the forward velocity component as a narrow-band component, ANF processing is employed to extract it from the estimated Doppler rate. Comparing with the methods reported in the literature, the ANF method can achieve higher accuracy and efficiency due to its excellent notching performance and strong suppression for narrow-band signals. Promising results from raw data experiments are presented to demonstrate the validity and superiority of the proposed method.

In this paper, a novel synthetic aperture radar (SAR) ground moving target imaging (GMTIm) algorithm is presented within a parametric and dynamic sparse Bayesian learning (SBL) framework. A new time-frequency representation, which is known as Lv's distribution (LVD), is employed on the moving targets to determine the parametric dictionary used in the SBL framework. To combat the inherent accuracy limitations of the LVD and extrinsic perturbation errors, a dynamical refinement process is further developed and incorporated into the SBL framework to obtain highly focused SAR image of multiple moving targets. An emerging inference technique, which is known as variational Bayesian expectation-maximization, is applied to achieve an efficient Bayesian inference for the focused SAR moving target image. A remarkable advantage of the proposed algorithm is to provide a fully posterior distribution (Bayesian inference) for the SAR moving target image, rather than a poor point estimate used in conventional methods. Because of utilizing high-order statistical information, the error propagation problem is desirably ameliorated in an iterative manner. The perturbations, known as the multiplicative phase error and additive clutter and noise, are both well adjusted for further improving the image quality. Experimental results by using simulated spotlight-SAR data and real Gotcha data have demonstrated the superiority of the proposed algorithm over other reported ones.

We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification. As visually similar pixels are indistinguishable from local context, we alleviate such ambiguity by introducing a global scene constraint. We estimate the global potential in a non-parametric framework. Furthermore, a large margin based CNN metric learning method is proposed for better global potential estimation. The final pixel class prediction is performed by integrating local and global beliefs. Even without any post-processing, we achieve state-of-the-art performance on SiftFlow and competitive results on Stanford Background benchmark.

This paper presents a new SAR ground moving target imaging (GMTIm) algorithm based on an unified framework of Keystone transformation (KT). To combat the inherent range-azimuth coupling, an tandem two-step strategy is designed, where the range decoupling is implemented by polar format algorithm (PFA) and the azimuth decoupling is finished by an novel time-frequency representation method that is Lv's distribution (LVD). We show, mathematically, that the azimuth resampling of PFA has inherently the same mechanism as the KT, and also, the LVD achieves the optimal performance when it is performed in accordance with the KT principle. Therefore, multiple moving targets can be imaged simultaneously. Focused targets' responses can be obtained in both range and azimuth dimensions. Isotropic point target simulation is designed, and experiments are carried out to validate our proposed SAR-GMTIm algorithm.

This paper considers the problem of estimating multiple frequency hopping signals with unknown hopping pattern. By segmenting the received signals into overlapped measurements and leveraging the property that frequency content at each time instant is intrinsically parsimonious, a sparsity-inspired high-resolution time-frequency representation (TFR) is developed to achieve robust estimation. Inspired by the sparse Bayesian learning algorithm, the problem is formulated hierarchically to induce sparsity. In addition to the sparsity, the hopping pattern is exploited via temporal-aware clustering by exerting a dependent Dirichlet process prior over the latent parametric space. The estimation accuracy of the parameters can be greatly improved by this particular information-sharing scheme and sharp boundary of the hopping time estimation is manifested. Moreover, the proposed algorithm is further extended to multi-channel cases, where task-relation is utilized to obtain robust clustering of the latent parameters for better estimation performance. Since the problem is formulated in a full Bayesian framework, labor-intensive parameter tuning process can be avoided. Another superiority of the approach is that high-resolution instantaneous frequency estimation can be directly obtained without further refinement of the TFR. Results of numerical experiments show that the proposed algorithm can achieve superior performance particularly in low signal-to-noise ratio scenarios compared with other recently reported ones.

Compressive sensing (CS) based Inverse Synthetic Aperture Radar (ISAR) imaging exploits the sparsity of the target scene to achieve high resolution and effective denoising with limited measurements. This paper extends the CS based ISAR imaging to further include the continuity structure of the target scene within a Bayesian framework. A correlated prior is imposed to statistically encourage the continuity structures in both the cross-range and range domains of the target region and the Gibbs sampling strategy is used for Bayesian inference. Because the resulted method requires to recover the whole target scene at a time with heavy computational complexity, an approximate strategy is proposed to alleviate the computational burden. Experimental results demonstrate that the proposed algorithm can achieve substantial improvements in terms of preserving the weak scatterers and removing noise over other reported CS based ISAR imaging algorithms.

Motivated by the existing time-frequency peak filtering (TFPF) algorithm, herein a robust time-varying filtering (RTVF) algorithm is proposed for filtering and separating multicomponent frequency modulation (FM) signals. The performance of the TFPF based on windowed Wigner-Ville distribution is limited by the linear constraint on the waveform of the received signal. The proposed RTVF significantly improves the filtering performance with low complexity by applying a sinusoidal time-frequency distribution, which allows a sinusoidal constraint on the signal's waveform. The RTVF can successfully decompose a multicomponent signal into individual components based on an initial instantaneous frequency (IF) estimate of each component. Unlike existing time-varying filters, the RTVF is much less sensitive to the accuracy of the IF estimate, which can be gradually refined by performing an iterative RTVF procedure.

This letter addresses the recovery of hierarchical sparse signals in a Bayesian framework. Hierarchical sparse signals exhibit two levels of sparsity, i.e., block-sparsity among different blocks and internal sparsity within each individual block. As in sparse Bayesian learning, each component of the coefficient vector is firstly modeled as a Gaussian distributed variable with zero mean. To enforce the two-level hierarchical sparsity, the variance is further modeled by two classes of hidden variables controlling the block-sparsity and the internal sparsity, respectively. Finally, variational Bayesian inference is used to recover the coefficient vector from the noise corrupted data. Numerical simulation and experimental results show that the proposed method outperforms those recently reported recovery methods.

This paper presents a novel inverse synthetic aperture radar (ISAR) imaging method by exploiting the inherent continuity of the scatterers on the target scene to obtain enhanced target images within a Bayesian framework. A simplified radar system is utilized by transmitting the sparse probing frequency signal, where the ISAR imaging problem can be converted to deal with underdetermined linear inverse scattering. Following the Bayesian compressive sensing (BCS) theory, a hierarchical Bayesian prior is employed to model the scatterers in the range-Doppler plane. In contrast to the independent prior on each scatterer in the conventional BCS, a correlated prior is proposed to statistically encourage the continuity structure of the scatterers in the target region. To overcome the intractability of the posterior distribution, the Gibbs sampling strategy is used for Bayesian inference. The parameters of the signal model are inferred efficiently from samples obtained by the Gibbs sampler. Because the proposed method is a data-driven learning process, the tedious parameter tuning process required by the convex optimization-based approaches can be avoided. Both the synthetic and the experimental results demonstrate that the proposed algorithm can achieve substantial improvements in the scenarios of limited measurements and low signal-to-noise ratio compared with other reported algorithms for ISAR imaging problems.

For inverse synthetic aperture radar imagery, the inherent sparsity of the scatterers in the range-Doppler domain has been exploited to achieve a high-resolution range profile or Doppler spectrum. Prior to applying the sparse recovery technique, preprocessing procedures are performed for the minimization of the translational-motion-induced Doppler effects. Due to the imperfection of coarse motion compensation, the autofocus technique is further required to eliminate the residual phase errors. This paper considers the phase error correction problem in the context of the sparse signal recovery technique. In order to encode sparsity, a multitask Bayesian model is utilized to probabilistically formulate this problem in a hierarchical manner. In this novel method, a focused high-resolution radar image is obtained by estimating the sparse scattering coefficients and phase errors in individual and global stages, respectively, to statistically make use of the sparsity. The superiority of this algorithm is that the uncertainty information of the estimation can be properly incorporated to obtain enhanced estimation accuracy. Moreover, the proposed algorithm achieves guaranteed convergence and avoids a tedious parameter-tuning procedure. Experimental results based on synthetic and practical data have demonstrated that our method has a desirable denoising capability and can produce a relatively well-focused image of the target, particularly in low signal-to-noise ratio and high undersampling ratio scenarios, compared with other recently reported methods.

This letter considers the multiplicative perturbation problem in compressive sensing, which has become an increasingly important issue on obtaining robust performance for practical applications. The problem is formulated in a probabilistic model and an auto-calibration sparse Bayesian learning algorithm is proposed. In this algorithm, signal and perturbation are iteratively estimated to achieve sparsity by leveraging a variational Bayesian expectation maximization technique. Results from numerical experiments have demonstrated that the proposed algorithm has achieved improvements on the accuracy of signal reconstruction.