With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.

With the rapid development of ubiquitous networks and unmanned devices, air quality monitoring data is increasingly collected via wireless networks from sensors at multiple monitoring stations. However, the complexity of these data introduces significant challenges. Existing spatiotemporal methods for air quality prediction often struggle with issues such as inadequate handling of spatial relationships, difficulties in modeling long-term temporal dependencies, and limited generalization capabilities. To address these challenges, this paper proposes a novel spatiotemporal modeling approach—Spatiotemporal λ-Bernstein Graph Convolutional Network with Transformer for Multi-Site Air Quality Prediction (ST-BernT). This method constructs a graph structure based on spatiotemporal correlations, integrating a Gaussian-weighted adjacency matrix derived from geographic distances with an adjacency matrix capturing the temporal correlations of pollutant concentration time series, thereby precisely modeling spatial dependencies. Subsequently, a dynamic filter adjusted by λ-Bernstein polynomials is proposed to adaptively process spatiotemporal data characterized by the coexistence of low- and high-frequency components on the graph. Furthermore, a hierarchical generative transformer (GPHT) is introduced to enhance the model’s ability to capture long-term temporal patterns, such as periodicity and seasonality, while supporting parallel prediction across multiple sites, significantly improving computational efficiency and accuracy. Experimental results demonstrate that ST-BernT exhibits strong accuracy, adaptability, and generalization capability in multi-site air quality prediction tasks, particularly showing enhanced robustness in large-scale long-term forecasting scenarios.

API recommendation is a crucial task in code intelligence, aiming to suggest suitable APIs for programming queries. Recent efforts have integrated Large Language Models (LLMs) into this task. However, these methods overlook the compatibility between recommended APIs and fail to fully utilize the factual knowledge of APIs. Moreover, these prompting-only methods are limited by the insufficient domain-specific knowledge of LLMs. In this article, we propose a novel fine-tuning method, KDRAR, designed to leverage knowledge-driven reasoning with LLMs for compatible and interpretable API recommendation. To fully utilize the factual knowledge, we introduce a dual matching strategy that leverages both function descriptions and keyword matching to retrieve candidate APIs. To handle compatibility, we translate compatibility information into descriptive knowledge, which is integrated into the recommendation process. Furthermore, we adopt a distilled fine-tuning strategy: a student LLM is trained via distillation from a teacher LLM to perform step-by-step reasoning for enhanced recommendation and explanation. By considering both function matching and compatibility information, the knowledge-driven reasoning not only improves API recommendation accuracy but also provides reasonable explanations for the recommendations. Experimental results show that our method significantly outperforms baseline methods on API recommendation tasks across multiple API domains.

This is an erratum for the article “Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation” published in ACM Trans. Inf. Syst. 44, 1, Article 27 (December 2025), 30 pages.

The development of Internet of Vehicles (IoV) has produced a considerable amount of real-time traffic data. These traffic data constitute a kind of digital twin that connects the physical vehicles and their virtual representation via 5G communications. Generally, through analyzing the digital twin traffic data, traffic administrators can optimize traffic scheduling and alleviate traffic jams. However, the exceptions of IoV sensors inevitably raise an issue of traffic data sparsity and consequently influence scientific traffic scheduling decisions. Inspired by this drawback, in this article, a digital twin-assisted real-time traffic data prediction method is proposed by analyzing the traffic flow and velocity data monitored by IoV sensors and transmitted through 5G. At last, we conduct a set of experiments based on a traffic dataset collected by Nanjing city of China. Reported results show the feasibility of our proposal in smart traffic flow and velocity prediction that call for a quick response and high accuracy.

As one of the cyber–physical–social systems that plays a key role in people's daily activities, a smart city is producing a considerable amount of industrial data associated with transportation, healthcare, business, social activities, and so on. Effectively and efficiently fusing and mining such data from multiple sources can contribute much to the development and improvements of various smart city applications. However, the industrial data collected from the smart city are often sensitive and contain partial user privacy such as spatial–temporal context information. Therefore, it is becoming a necessity to secure user privacy hidden in the smart city data before these data are integrated together for further mining, analyses, and prediction. However, due to the inherent tradeoff between data privacy and data availability, it is often a challenging task to protect users’ context privacy while guaranteeing accurate data analysis and prediction results after data fusion. Considering this challenge, a novel privacy-aware data fusion and prediction approach for the smart city industrial environment is put forward in this article, which is based on the classic locality-sensitive hashing technique. At last, our proposal is evaluated by a set of experiments based on a real-world dataset. Experimental results show better prediction performances of our approach compared to other competitive ones.

Cloud computing has promoted the success of big data applications such as medical data analyses. With the abundant resources provisioned by cloud platforms, the quality of service (QoS) of services that process big data could be boosted significantly. However, due to unstable network or fake advertisement, the QoS published by service providers is not always trusted. Therefore, it becomes a necessity to evaluate the service quality in a trustable way, based on the services' historical QoS records. However, the evaluation efficiency would be low and cannot meet users' quick response requirement, if all the records of a service are recruited for quality evaluation. Moreover, it may lead to `Lagging Effect' or low evaluation accuracy, if all the records are treated equally, as the invocation contexts of different records are not exactly the same. In view of these challenges, a novel approach named Partial Historical Records-based service evaluation approach (Partial-HR) is put forward in this paper. In Partial-HR, each historical QoS record is weighted based on its service invocation context. Afterwards, only partial important records are employed for quality evaluation. Finally, a group of experiments are deployed to validate the feasibility of our proposal, in terms of evaluation accuracy and efficiency.

In recent years, with the development of mobile devices, the location based services (LBSs) have become more and more prevailing and most applications installed on these devices call for location information. Yet, the untrusted LBS provider can collect this location information, which may potentially threaten users' location privacy. In view of this challenge, we propose a two-tier schema for the privacy preservation based on k-anonymity principle meanwhile reducing the cost for privacy protection. Concretely, we divide the users into groups in order to maximize the privacy level and in each group one proxy is selected to generate dummy locations and share the returned results from LBS provider; then, on each group, an auction mechanism is proposed to determine the payment of each user to the proxy as the compensation, which satisfies budget balance and incentive compatibility. To evaluate the performance of the proposed schema, a simulated experiment is conducted.

Recommending appropriate product items to the target user is becoming the key to ensure continuous success of E-commerce. Today, many E-commerce systems adopt various recommendation techniques, e.g., Collaborative Filtering (abbreviated as CF)-based technique, to realize product item recommendation. Overall, the present CF recommendation can perform very well, if the target user owns similar friends (user-based CF), or the product items purchased and preferred by target user own one or more similar product items (item-based CF). While due to the sparsity of big rating data in E-commerce, similar friends and similar product items may be both absent from the user-product purchase network, which lead to a big challenge to recommend appropriate product items to the target user. Considering the challenge, we put forward a Structural Balance Theory-based Recommendation (i.e., SBT-Rec) approach. In the concrete, (I) user-based recommendation: we look for target user's “enemy” (i.e., the users having opposite preference with target user); afterwards, we determine target user's “possible friends”, according to “enemy's enemy is a friend” rule of Structural Balance Theory, and recommend the product items preferred by “possible friends” of target user to the target user. (II) likewise, for the product items purchased and preferred by target user, we determine their “possibly similar product items” based on Structural Balance Theory and recommend them to the target user. At last, the feasibility of SBT-Rec is validated, through a set of experiments deployed on MovieLens-1M dataset.

Summary Because of the strong demands of physical resources of big data, it is an effective and efficient way to store and process big data in clouds, as cloud computing allows on‐demand resource provisioning. With the increasing requirements for the resources provisioned by cloud platforms, the Quality of Service (QoS) of cloud services for big data management is becoming significantly important. Big data has the character of sparseness, which leads to frequent data accessing and processing, and thereby causes huge amount of energy consumption. Energy cost plays a key role in determining the price of a service and should be treated as a first‐class citizen as other QoS metrics, because energy saving services can achieve cheaper service prices and environmentally friendly solutions. However, it is still a challenge to efficiently schedule Virtual Machines (VMs) for service QoS enhancement in an energy‐aware manner. In this paper, we propose an energy‐aware dynamic VM scheduling method for QoS enhancement in clouds over big data to address the above challenge. Specifically, the method consists of two main VM migration phases where computation tasks are migrated to servers with lower energy consumption or higher performance to reduce service prices and execution time. Extensive experimental evaluation demonstrates the effectiveness and efficiency of our method. Copyright © 2016 John Wiley & Sons, Ltd.

Summary Traffic hotline discovery is necessary for rational and scientific urban transportation planning in the new living quarters and economic zones. Cloud of Things (CoT) is a newly emerging concept, involving with two advanced technologies, that is, Cloud Computing and Internet of Things (IoT). CoT provides promising opportunities for traffic hotline discovery. However, it is still a challenge to discover the traffic hotlines over CoT. In view of this challenge, a hotline discovery method over CoT by using big taxi GPS data is proposed in this paper. Specifically, a traffic hotline discovery principle is presented to provide a reference standard for the generalized traffic spots that need planning, and a corresponding hotline discovery method is proposed for traffic hotspot identification and hotline selection. To improve the scalability and efficiency of the proposed method in “Big Data” environment, the SAP HANA cloud is applied to implement the proposed method under two application scenarios. Finally, the experimental results demonstrate that the proposed method is both effective and efficient. Software—Practice and Experience. Copyright © 2016 John Wiley & Sons, Ltd.

With the prosperity of media streaming applications over the Internet in the past decades, multimedia data has sharply increased (categorized as multimedia big data), which exerts more pressure on the infrastructure, such as networking of the application provider. In order to move this hurdle, an increasing number of traditional media streaming applications have migrated from a private server cluster onto the cloud. With the elastic resource provisioning and centralized management of the cloud, the operational costs of media streaming application providers can decrease dramatically. However, to the best of our knowledge, existing migration solutions do not fully take viewer information such as hardware condition into consideration. In this article, we consider the deployment optimization problem named ODP by leveraging local memories at each viewer. Considering the NP-hardness of calculating the optimal solution, we turn to propose computationally tractable algorithms. Specifically, we unfold the original problem into two interactive subproblems: coarse-grained migration subproblem and fine-grained scheduling subproblem. Then, the corresponding offline approximation algorithms with performance guarantee and computational efficiency are given. The results of extensive evaluation show that compared with the baseline algorithm without leveraging local memories at viewers, our proposed algorithms and their online versions can decrease total bandwidth reservation and enhance the utilization of bandwidth reservation dramatically.

The influence of the uncertain or malicious service nodes on the Web service composition (WSC) performance is generally fatal in the Internet, so the problems of services selecting for WSC can not be completely solved by the perspective of performance. In the paper, the two-tier model of reputation computing, which describes the credibility evolution mechanism of the inter-entity relations in the course of services composition, has been proposed. A trust reputation computing mode is builded through interactive services composition submitted by the parties, then an intuitive reputation evaluation model is formed through the direct or indirect interaction between services entities. On that basis, the services scheduling algorithm based on trust reputation evolution model has been proposed, which can effectively inhibit the interference of fraudulent services entity and reduce the influence of low-quality services in WSC. Experimental results show that the method proposed in the paper is more superior in credibility and security, comparing to the traditional services scheduling methods.

In the Internet, there are a mass of malicious, fraudulent services in addition to the dynamics change and differences in service of quality. As a result, it is difficult for a client to fastly get high- quality services. In this paper, a service-composition framework based on the trust evolution and alliance has been proposed. It is different from traditional service workflow model. The trust relationship will be built after the trust evolution between services requester and provider. The trust services requester and provider are going to form an alliance through the relationship, so the malicious, fraudulent services will be excluded from the system and the service-composition will be carried out in a trust environment. On this basis, a strategy measuring the trust relationship among the services based on information entropy has been proposed, which can avoid the deficiencies of multi-dimensional trust indicators simply weighted in the previous studies. Theoretical analysis and experimental result show that the method proposed in this paper is more superior in credibility and security, comparing to the traditional services selection methods.