Local smoothness is a widely used prior in hyperspectral image (HSI) denoising tasks. The current work mainly realizes the representation of this prior through total variation (TV) regularization. However, the TV regularization applies a uniform penalty to each entry in the image, unable to effectively balance noise removal and texture preservation. Aiming at this problem: 1) We propose a novel regularization for HSI denoising called Spatial-Spectral Texture-Preserved Total Variation (SSTPTV). This naturally expresses the physical phenomenon of the difference in sparsity between textured regions and smooth regions. Specifically, the regularization relaxes the sparsity penalty in textured regions by a weight learning strategy and sparsity measurement method for gradient maps, thereby preserving the spatial-spectral textures of HSIs. 2) An HSI denoising model based on the SSTPTV regularization constraint is given. We propose a tensor alternating subspace representation method that can capture the overall spatial texture features across all bands and the overall spectral texture features across all spectral curves. By applying the SSTPTV regularization constraint to these subspaces, the spatial-spectral texture structures are effectively preserved. An efficient ADMM-based algorithm for solving the model is designed. The simulated and real noise removal experiments of HSI prove that the proposed method has significant superiority and can serve as a framework to optimize other TV-based denoising methods. The code is available at https://github.com/zth-code/SSTPTV.

The quality of augmented data directly affects the performance of contrastive learning. Low-quality augmentation offers limited benefits for model optimization. Existing contrastive learning-based sequential recommendation works primarily utilize heuristic data augmentation methods, which often exhibit excessive randomness and struggle to generate positive samples that align with users' true intentions.

Tensor completion aims to recover original data from its degraded observations and has shown promise in processing incomplete hyperspectral images (HSIs). Many previous studies have indicated that global correlation and nonlocal self-similarity (NSS) are two important priors for tensor completion. Recently, tensor wheel (TW) decomposition has demonstrated excellent performance in the tensor completion problem. However, it overlooks NSS. To address this limitation, a novel nonlocal tensor wheel (NL-TW) decomposition-based method is presented for tensor completion, which leverages both of the aforementioned priors. The method consists of two main steps. In the first step, we introduce TW decomposition to the entire degraded tensor to generate an initial completion result. In the second step, similar patches in the initial completion result are first stacked into NSS groups, and TW decomposition is then applied to each grouped tensor to obtain the final completion result. In addition, the NL-TW decomposition-based tensor completion method is solved by a proximal alternating minimization (PAM)-based optimization algorithm, which has a theoretical convergence guarantee. Extensive experiments on three real datasets with different sampling rates (SRs) demonstrate the effectiveness of the proposed NL-TW method compared to other methods.

Robust tensor completion of hyperspectral image (HSI) is a challenging task in the field of remote sensing. Recently, nuclear norm minimization-based methods have made certain progress in robust tensor completion. However, the tensor nuclear norm applies the same constraint to all singular values, resulting in insufficient capturing power for the global structure of the HSI. In addition, as a convex surrogate of global low-rankness, tensor nuclear norm minimization leads to an overall low-rank approximation that cannot capture the details of the HSI. In this letter, we propose the spatial-spectral constrained deep low-rank tensor factorization (SDLTF). More precisely, the low-rank tensor factorization is used to dynamically assign penalty weights, aiming to preserve the main information and maintain the global structure of the HSI. The spatial-spectral constrained unsupervised deep prior is applied within a deep convolutional neural network to capture spatial-spectral correlations and local details of the HSI. We develop an efficient algorithm to tackle the corresponding model based on the ADMM. Extensive experiments demonstrate that our model has superior performance compared with several state-of-the-art methods.

Sequential recommendation has attracted a lot of attention from both academia and industry, however the privacy risks associated with gathering and transferring users’ personal interaction data are often underestimated or ignored. Existing privacy-preserving studies are mainly applied to traditional collaborative filtering or matrix factorization rather than sequential recommendation. Moreover, these studies are mostly based on differential privacy or federated learning, which often lead to significant performance degradation, or have high requirements for communication. In this work, we address privacy-preserving from a different perspective. Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence. Even if the target interaction sequence is obtained by attackers, it is difficult to discern which ones are the actual user interaction records. To achieve this goal, we introduce a novel sequential recommender system called CoLlaborative-cOnfusion seqUential recommenDer (CLOUD) , which incorporates a collaborative confusion mechanism to modify the raw interaction sequences before conducting recommendation. Specifically, CLOUD first calculates the similarity between the target interaction sequence and other neighbor sequences to find similar sequences. Then, CLOUD considers the shared representation of the target sequence and similar sequences to determine the operation to be performed: keep, delete, or insert. A copy mechanism is designed to make items from similar sequences have a higher probability to be inserted into the target sequence. Finally, the modified sequence is used to train the recommender and predict the next item. We conduct extensive experiments on three benchmark datasets. The experimental results show that CLOUD achieves a maximum modification rate of 66.57% on interaction sequences and obtains over 99% recommendation accuracy compared to the state-of-the-art sequential recommendation methods. This proves that CLOUD can effectively protect user privacy at minimal recommendation performance cost, which provides a new solution for privacy-preserving for sequential recommendation. Our implementation is available at https://github.com/weiwang0927/CLOUD .

Social recommendation improved the quality and efficiency of recommendation but increased the risk of privacy leakage, especially with the introduction of social networks. Consequently, the social recommendation considering user privacy has drawn tremendous attention from academia to industry. Nevertheless, most of the existing work regards the recommender systems as static, ignoring the diffusion of social influence over time. In this article, we propose a secure and efficient framework, temporal privacy-preserving social recommendation model (PrivTSR), to capture the changes of user preference for items and item types with time. PrivTSR first utilizes differential privacy to encrypt the data owned by the data owner. Then, inspired by the long short-term memory (LSTM), at each time step the initial user embedding and the initial item embedding are generated via DeepWalk as new ratings of users for items emerges in the user–item-type graph. The initial user-preference embedding is generated randomly at the first time step, and it is equivalent to the updated embedding of the previous time step for the later time steps. Most importantly, on the social graph, PrivTSR updates the user embedding and the user-preference embedding with graph attention convolutional network and graph attention diffused network, which aggregates (diffuses) social influence from (to) neighbors in depth and breadth. On the user–item-type graph, the user embedding and the item embedding are updated by aggregating the embedding of users and items in the six paths. Final, taking into account the users’ preference for items and item types, PrivTSR predicts the ratings of users to the items for the next time step. The extensive experiments are conducted on two real-world datasets, which demonstrated the superiority of our model over several competitive baselines.

In recent years, semantic change detection (SCD) has emerged as a pivotal field within the remote sensing (RS) research community, underscored by its essential contribution to various Earth observation undertakings. Conventional SCD methodologies typically adopt a multitask network architecture, fusing a binary change detection (BCD) sub-task with dual semantic segmentation (SS) sub-tasks. These strategies frequently rely on the encoder’s low-resolution yet semantically dense features, derived from multiple down-sampling stages, as the inputs for the decoding heads. Departing from this traditional path and targeting the nuanced characteristics of the multisubtasks, this study pioneers a novel methodology that harnesses the potential of the encoding phase’s high-resolution features. By integrating HRNet as the encoder structure, we introduce the BT-HRSCD framework, featuring two simple and effective modules. The first, bidirectional shallow and deep features aggregation module (BiFAM), seeks to imbue features with richer semantic insights through bidirectional feature fusion that spans from shallow-to-deep as well as deep-to-shallow layers. The second module, high-resolution difference extraction (HRDE), utilizes the encoder’s highest spatial resolution features, evaluating their differences to enhance the precision in identifying change areas. BiFAM is devised to boost the SS sub-tasks’ effectiveness, whereas HRDE aims to elevate the accuracy of the BCD sub-task. Experimental results reveal that our method outperforms state-of-the-art performances relative to previous SCD efforts. Our source code is released athttps://github.com/iridescent524/BT-HRSCD.

Recently, Semantic Change Detection (SCD) has gained growing attention from the Remote Sensing (RS) research community due to its critical role in Earth observation applications. Typical approaches tackle the task using a multi-task network, comprising one Change Detection (CD) sub-task and two Semantic Segmentation (SS) sub-tasks. Although these approaches have achieved good performance, one crucial question persists: What is the effective way to handle the feature interactions across SCD sub-tasks? To address this issue, this paper first offers an overview of existing SCD networks and compares them from a perspective view of Multi-Task Learning (MTL). Following that, we select an architecture combining a two-branch encoder and a three-branch decoder as the baseline due to its compatibility with MTL. Then, one simple yet very effective module, decoder feature interaction across sub-tasks (DFIT), is introduced. DFIT seeks to enhance the CD decoding feature by leveraging the feature differences between two SS decoding branches on a layer-wise basis. Additionally, the feature aggregation module (FAM) is designed further to enhance the network performance in cooperation with DFIT. FAM aims to produce more representative shared information across the SS and CD sub-tasks by merging the outputs from the final three encoder layers. Combining DFIT and FAM, the proposed network exploiting Decoder-Focused MTL (DEFO-MTLSCD) presents more representative information by capitalizing on both CD and SS losses back-propagations across all coding paths and achieves better performance. Experimental results reveal that our method outperforms state-of-the-art performances relative to previous SCD efforts. Our source code is released at https://github.com/byyztgxz/Decoder_Fusion.

Hyperspectral image (HSI) inpainting is a fundamental task in remote sensing image processing, which is helpful for subsequent applications such as classification and unmixing. Recently, tensor-train decomposition (TTD)-based low-rank methods have achieved great success in image inpainting because of the balanced tensor unfolding and the use of tensor augmentation (TA). However, the TTD algorithm only performs TA on the third mode, and cannot effectively mine the spectral domain information of HSIs. Aiming at this problem, this article extends TA to each mode of the tensor and proposes a full-mode-augmentation TT decomposition (FTTD). More precisely, the HSI is cast along each mode to get a 3-D$N$th-order tensor sequence, and all the tensors in the sequence are performed TTD to get$3N$factor tensors that model the correlation on various modes. Then, the full-mode-augmentation tensor unfolding method is given by performing TT unfolding on each$N$th-order tensor. We implement FTTD by minimizing the rank of the unfolding matrix and thus provide the tensor completion framework based on full-mode-augmentation tensor-train rank minimization. Finally, using the framework, we optimize the current two classical iterative algorithms nuclear norm minimization and parallel matrix decomposition. These two algorithms utilize the unfolding matrices in the framework to effectively mine spatial and spectral information, thereby making the restored tensor more approximate to the original HSI. Experiments on various HSIs have shown that the proposed method outperforms compared methods in terms of visual and quantitative measures.

Traffic flow forecasting is challenging due to the intricate spatio-temporal correlations in traffic patterns. Previous works captured spatial dependencies based on graph neural networks and used fixed graph construction methods to characterize spatial relationships, which limits the ability of models to capture dynamic and long-range spatial dependencies. Meanwhile, prior studies did not consider the issue of a large number of redundant parameters in traffic prediction models, which not only increases the storage cost of the model but also reduces its generalization ability. To address the above challenges, we propose a Dynamic Spatial Transformer for Traffic Forecasting with Low-Rank Tensor Compression (DSFormer-LRTC). Specifically, we constructed a global spatial Transformer to capture remote spatial dependencies, and a distance-based mask matrix is used in local spatial Transformer to enhance the adjacent spatial influence. To reduce the complexity of the model, the model adopts a design that separates temporal and spatial. Meanwhile, we introduce low-rank tensor decomposition to reconstruct the parameter matrix in Transformer module to compress the proposed model. Experimental results show that DSFormer-LRTC achieves state-of-the-art performance on four real-world datasets. The experimental analysis of attention matrix also proves that the model can learn dynamic and distant spatial features. Finally, the compressed model parameters reduce the original parameter size by two-thirds, while significantly outperforming the baseline model in terms of computational efficiency.

In this paper, we focus on the problem of context-aware recommendation using tensor factorization. Traditional tensor-based models in context-aware recommendation scenario only consider user-item-context interactions. In this paper, we argue that rating can't be totally explained by the interactions and the rating also influenced by the combined impact of overall mean, user bias, item bias and context bias. Based on this hypothesis, we propose a novel context-aware recommendation model named Bias Tensor Factorization, which take all this factors into account. Additionally, traditional context-aware recommenders with tensor factorization still have three main drawbacks: (1) the model complexity of those models increase exponentially with the number of context features, (2) those models can only handle context features with categorical values and (3) the models fail to select effective features from available context features. To address those problems, we propose a context features auto-encoding algorithm based on regression tree which can both handle numerical features and select effective features. Then we integrate this algorithm with Bias Tensor Factorization. Experiments on a real world contextual dataset and Movielens show that our proposed algorithms outperform the state-of-art context-aware recommendation algorithms, namely tensor factorization and factorization machine.