Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To address this gap, we propose a Simultaneous Learning Knowledge Distillation (SLKD) framework tailored for model compression in image restoration tasks. SLKD employs a dual-teacher, single-student architecture with two distinct learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL), simultaneously. In DRL, the student encoder learns from Teacher A to focus on removing degradation factors, guided by a novel BRISQUE extractor. In IRL, the student decoder learns from Teacher B to reconstruct clean images, with the assistance of a proposed PIQE extractor. These strategies enable the student to learn from degraded and clean images simultaneously, ensuring high-quality compression of image restoration models. Experimental results across five datasets and three tasks demonstrate that SLKD achieves substantial reductions in FLOPs and parameters, exceeding 80%, while maintaining strong image restoration performance.

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity—manifested in elevated FLOPs and parameter counts—limits their application in real-world scenarios. Existing knowledge distillation methods in image restoration typically employ lightweight student models that directly mimic the intermediate features and reconstruction results of the teacher, overlooking the implicit attention relationships between them. To address this, we propose a Soft Knowledge Distillation (SKD) strategy that incorporates a Multi-dimensional Cross-net Attention (MCA) mechanism for compressing image restoration models. This mechanism facilitates interaction between the student and teacher across both channel and spatial dimensions, enabling the student to implicitly learn the attention matrices. Additionally, we employ a Gaussian kernel function to measure the distance between student and teacher features in kernel space, ensuring stable and efficient feature learning. To further enhance the quality of reconstructed images, we replace the commonly used L1 or KL divergence loss with a contrastive learning loss at the image level. Experiments on three tasks—image deraining, deblurring, and denoising—demonstrate that our SKD strategy significantly reduces computational complexity while maintaining strong image restoration capabilities.

Images captured in outdoor scenes are often simultaneously affected by multiple degradation factors, making robust image restoration critical. To address this challenge, we introduce RMTD (Robust Multi-Type Degradation Dataset), the first comprehensive large-scale dataset specifically designed for outdoor image restoration under diverse degradation conditions. RMTD spans 10 outdoor scene categories and incorporates 8 common degradation types, reflecting real-world challenges. The dataset features 48,000 synthetic multi-degraded images paired with high-quality ground truth, making it the largest benchmark for multi-degraded image restoration. Additionally, 200 real-world multi-degraded images offer authentic test cases for evaluating model robustness under outdoor conditions. To support downstream applications, RMTD provides annotations for over 3,000 objects across 10 categories, facilitating evaluations for tasks such as object detection. Experiments on synthetic and real multi-degraded images demonstrate that models trained on RMTD achieve improvements of 1.31 in PSNR and 0.835 in BRISQUE over existing datasets, proving its robustness as a benchmark for advancing image restoration research. RMTD is available at: https://github.com/ICME25/RMTD.

The prompt-based method has been proven effective in improving the performance of pre-trained language models (PLMs) on sentence-level few-shot tasks. However, when applying prompting to token-level tasks such as Named Entity Recognition (NER), specific templates need to be designed, and all possible segments of the input text need to be enumerated. These methods have high computational complexity in both training and inference processes, making them difficult to apply in real-world scenarios. To address these issues, we redefine the NER task as a Machine Reading Comprehension (MRC) task and incorporate prompting into the MRC framework. Specifically, we sequentially insert boundary markers for various entity types into the templates and use these markers as anchors during the inference process to differentiate entity types. In contrast to the traditional multi-turn question-answering extraction in the MRC framework, our method can extract all spans of entity types in one round. Furthermore, we propose word-based template and example-based template that enhance the MRC framework's perception of entity start and end positions while significantly reducing the manual effort required for template design. It is worth noting that in cross-domain scenarios, PMRC does not require redesigning the model architecture and can continue training by simply replacing the templates to recognize entity types in the target domain. Experimental results demonstrate that our approach outperforms state-of-the-art models in low-resource settings, achieving an average performance improvement of +5.2% in settings where access to source domain data is limited. Particularly, on the ATIS dataset with a large number of entity types and 10-shot setting, PMRC achieves a performance improvement of +15.7%. Moreover, our method achieves a decoding speed 40.56 times faster than the template-based cloze-style approach.

Restoring real-world images suffering from complex degradations like haze, rain, and blur is a significant challenge. Existing models face difficulties when applied to these real-world images, mainly due to the domain gap between synthetically generated and authentic degradations. In this paper, we propose SDA-Net, a well-designed Semi-supervised Domain Adaptation Network that can effectively restore real-world images. Our method combines the advantages of two foundation models. The supervised knowledge transfer model helps a student network learn from diverse restoration networks, while the unsupervised domain adaptation models guide the student network to generalize from synthetic scenes to real-world scenes. Furthermore, we propose a grained-friendly contrastive learning loss to force our models to retain background details and clear representation. Extensive experiments demonstrate that our SDA-Net outperforms state-of-the-art algorithms on three common real-world datasets with various degradations, achieving a significant improvement of 2.7 scores on BRISQUE and 11.6 scores on PIQE.

Image enhancement methods leveraging learning-based approaches have demonstrated impressive results when trained on synthetic degraded-clear image pairs. However, when deployed in real-world scenarios, such models often suffer significant performance degradation due to the inherent domain gap between synthetic and real degradations. To bridge this gap, we propose a novel Two-stage Contrastive Domain Adaptation image Enhancement (TCDAE) framework consisting of two key strategies: (1) Synthetic-to-Real Domain Transfer Learning (S2R-DTL) that effectively translates images from the synthetic degraded domain to the real degraded domain, aligning the domains at the pixel level, and (2) Degraded-to-Clear Domain Transfer Learning (D2C-DTL) that further adapts the enhancement model from the synthetic to the real domain by translating images from the real degraded domain to the real clean domain in both supervised and unsupervised branches. A unique aspect of our approach is the integration of a Domain Noise Contrastive Estimation (DoNCE) loss in both learning strategies. This specialized loss formulation enables TCDAE to robustly translate images across domains, even in scenarios lacking strong positive examples. Consequently, our framework can generate enhanced images with natural, realistic appearances akin to real clear images. Comprehensive experiments on real-world degraded scenes across diverse tasks, including dehazing, deraining, and deblurring, demonstrate the superiority of TCDAE over state-of-the-art methods, achieving improved visual quality, quantitative metrics, and downstream task performance.

In this paper, we propose a simple and general lightweight approach named AL-RE2 for text matching models, and conduct experiments on three well-studied benchmark datasets across tasks of natural language inference and paraphrase identification. Firstly, we explore the feasibility of dimensional compression of word embedding vectors using principal component analysis, and then analyze the impact of the information retained in different dimensions on model accuracy. Considering the balance between compression efficiency and information loss, we choose 128 dimensions to represent each word and make the model params 1.6M. Finally, the feasibility of applying depthwise separable convolution instead of standard convolution in the field of text matching is analyzed in detail. The experimental results show that our model’s inference speed is at least 1.5 times faster and it has 42.76% fewer parameters compared to similarly performing models, while its accuracy on the SciTail dataset of is state-of-the-art among all lightweight models.

Currently, single image deraining lacks paired rain/clean images in real world and most studies use synthetic data. Real rain image deraining is still a challenge. To solve this problem, we propose a semi-supervised image deraining network using Swin Transformer, which can both use features of synthetic data and real data to get a better result. Specifically, the network is divided into supervised branch and unsupervised branch. Supervised and unsupervised branches are trained using synthetic data and real data, respectively. The network architecture is based on Swin Transformer, which adds a self-supervised memory module between encoder and decoder to store rain information. In the unsupervised branch, contrastive loss is added to ensure restored real rain image in features space is close to clear image, away from real rain image. In addition, we propose a real rain dataset RealRain11k. Experiments show our method has better result in real rain image deraining. The source code and RealRain11k are available at https://github.com/imissrc/Semi-SwinDerain.

Abstract Named entity recognition (NER) is a fundamental task for natural language processing, which aims to detect mentions of real-world entities from text and classifying them into predefined types. Recently, research on overlapped and discontinuous named entity recognition has received increasing attention. However, we note that few studies have considered both overlapped and discontinuous entities. In this paper, we proposed a novel sequence-to-sequence model that is capable of recognizing both overlapped and discontinuous entities based on machine reading comprehension. The model utilizes machine reading comprehension formulation to encode significant inferior information about the entity category. Then input sequence passes through a question-answering model to predict the mention relevance of the given source sentences to the query. Finally, we incorporate the mention relevance into the BART-based generation model. We conducted experiments on three type of NER datasets to show the generality of our model. The experimental results demonstrate that our model beats almost all the current top-performing baselines achieves a vast amount of performance boost over current SOTA models on overlapped and discontinuous NER datasets.

Aspect-based sentiment analysis aims to determine the sentiment of a specific aspect in the sentence. Most of the previous studies employ attention-based RNN models to capture aspect-dependent features in sentences or model Inter-Aspect Relation (IAR). However, RNN is difficult to parallelize when calculating all the elements in a sequence, and the word-level weight in attention mechanisms may introduce noise. Besides, we observe that the IAR contains inter-aspect syntactic relation and inter-aspect semantic relation, while the latter is overlooked in past IAR modeling studies. In this paper, we propose a new architecture that employs the multi-head attention mechanism to implement the parallel computation of sequence elements and introduce less noise than traditional attention mechanisms and model both relations in IAR. The experimental results on different types of data show that our model consistently outperforms state-of-the-art methods.

Mining quantitative association rules is one of the most important tasks in data mining and exists in many real-world problems. Many researches have proved that particle swarm optimization(PSO) algorithm is suitable for quantitative association rule mining (ARM) and there are many successful cases in different fields. However, the method becomes inefficient even unavailable on huge datasets. This paper proposes a parallel PSO for quantitative association rule mining(PPQAR). The parallel algorithm designs two methods, particle-oriented and data-oriented parallelization, to fit different application scenarios. Experiments were conducted to evaluate these two methods. Results show that particle-oriented parallelization has a higher speedup, and data-oriented method is more general on large datasets.

Current recommender systems often take fusion factors into consideration to realize personalize point‐of‐interest (POI) recommendation. Historical behavior records and location factors are two kinds of significant features in most of recommendation scenarios. However, existing approaches usually use the Euclidean distance directly without considering the traffic factors. Moreover, the timing characteristics of users’ historical behaviors are not fully utilized. In this paper, we took the restaurant recommendation as an example and proposed a personalized POI recommender system integrating the user profile, restaurant characteristics, users’ historical behavior features, and subway network features. Specifically, the subway network features such as the number of passing stations, waiting time, and transfer times are extracted and a recurrent neural network model is employed to model user behaviors. Experiments were conducted on a real‐world dataset and results show that the proposed method significantly outperforms the baselines on two metrics.

With the rapidly growing number of Web services, how to identify high quality Web services becomes a hot research topic. User-side QoS evaluation on Web services is a key measurement to choose the optimal Web service from a set of Web services with similar functions. The user-side QoS data is acquired through the invocation of services from different locations. However, in real world, the QoS data of Web services is sparse and not timely. Though there are already a lot of research works on the sparsity and timeliness of QoS data respectively, it's still a lack of a prediction model which can combine both of these features. In order to solve this challenging problem, we put forward a novel model, called CAPred, to provide timely QoS prediction. Our model cut the historical QoS data into several time slices. Each time slice is a 2-dimension matrix. CAPred firstly processes every time slice to fill the empty part of the matrix, then utilizes all of the historical data to predict current QoS values of Web services. And at last we demonstrate two applications, those are recommendation and selection, which utilize the QoS prediction results of our model. The experimental results indicate the high feasibility and efficiency of our model.

Abstract Mashups, which use multiple sources to create a new service, emerged as an evolution of Web 2.0. However, scalable access control for mashups is difficult. To enable a mashup to gather data from legacy applications and services, users must obey as the mashup host orders. These orders are created without any standard or limits about the privacy protection. This authorization approach violated the principle of least privilege and leaves users vulnerable to misuse of their private information by malicious mashups. To overcome the limitations, we introduce the privacy‐preserving authorization method for mashups, which encapsulates the data of backend services with different private sensitivity degrees before the authorization process executes. We also give the data–user relationship model to make standard for backend services when defining private sensitivity degrees of users' data. In this progress, standard encapsulation file and authorization file are created successively. In the end, the authorization steps, which could be set stored for regular use of the mashups, are created based on the authorization mechanism and authorization file. The proposed method mainly focuses on the users and backend services, which are the real data owners. Through this method, users have the ability to observe and control the data involved in the mashup, and the backend services can take the responsibility of their users' private information protecting. In the end of the paper, the application example and a series of experimental study are given to demonstrate the feasibility and efficiency of this method. Copyright © 2015 John Wiley & Sons, Ltd.

In the Web services environment, RBAC (role-based access control) model is widely accepted as an efficient approach to manage the access control. By defining the authorization relationship between subject roles and object roles in the RBAC, authorization policies are utilized to simplify the authorization management on different Web services. But the scalability and complexity of composite Web services may cause authorization policy conflict. A new authorization policy added to the system may conflict with existing ones and result in authorization chaos and authorization leaking. And when implemented in the composite Web services, policy conflict detection would be of high cost with manually checking. That makes automatic policy conflict detection important to ensure the security of authorizations in the composited Web services. This paper analyzes the features of the authorization policy in the CWS-RBAC (RBAC for composite Web services) and presents methods of detecting policy conflict including subject role propagation conflict, object role composition conflict and context conflict. The experiment designed is to validate the efficiency of each conflict detection method.

In recent years, RESTful Web services have been rapidly developed and deployed, because of the advantages of lightweight, flexibility and extensibility, etc. However, most RESTful services are described in heterogeneous and ordinary HTML pages, which makes them really difficult to be identified and crawled automatically from the Internet. In this paper we propose a hybrid classifier framework called co-NV for automatic identification of RESTful services on the Web. In our framework, web pages are analyzed and filtered according to the contents and structure characteristics of HTML documents, with Naïve Bayes classifier and Vector Space Model (VSM) respectively. Experiments with real RESTful services prove that our framework works effectively with high precision and recall rate, and is very practical.