Decentralized content sharing at the network edge provides a promising way to reduce backhaul traffic and improve local service responsiveness. However, in practical device-todevice environments, edge devices are usually owned by independent users and may not be willing to cache or deliver content without proper incentives. This creates a gap between systemlevel content distribution efficiency and individual device-level benefits. In this paper, we investigate an incentive-aware content sharing framework for edge communities. The basic idea is to separate slowly changing community organization from rapidly changing content deployment decisions. Specifically, edge devices are first organized into relatively stable communities according to long-term relationships such as proximity, interaction patterns, and caching capability. Then, within each community, content providers and selected caching devices interact through a pricingbased decision process, where content freshness, relevance, and popularity are considered when determining deployment preferences. Preliminary simulation results indicate that the proposed design has the potential to improve content deployment efficiency and provider-side utility while encouraging distributed caching behavior. This study provides an initial step toward sustainable and incentive-compatible content sharing in decentralized edge computing systems.

Federated learning (FL) enables collaborative model training without sharing raw data in edge environments, but is constrained by limited communication bandwidth and heterogeneous client data distributions. Prototype-based FL mitigates this issue by exchanging class-wise feature prototypes instead of full model parameters; however, existing methods still suffer from suboptimal generalization under severe communication constraints. In this paper, we propose RefProtoFL, a communication-efficient FL framework that integrates External-Referenced Prototype Alignment (ERPA) for representation consistency with Adaptive Probabilistic Update Dropping (APUD) for communication efficiency. Specifically, we decompose the model into a private backbone and a lightweight shared adapter, and restrict federated communication to the adapter parameters only. To further reduce uplink cost, APUD performs magnitude-aware Top-K sparsification, transmitting only the most significant adapter updates for server-side aggregation. To address representation inconsistency across heterogeneous clients, ERPA leverages a small server-held public dataset to construct external reference prototypes that serve as shared semantic anchors. For classes covered by public data, clients directly align local representations to public-induced prototypes, whereas for uncovered classes, alignment relies on server-aggregated global reference prototypes via weighted averaging. Extensive experiments on standard benchmarks demonstrate that RefProtoFL attains higher classification accuracy than state-of-the-art prototype-based FL baselines.

Service-driven compositions or mashups have successfully alleviated the invocation constraints associated with specific domains, leading to an increased frequency of service evolution. Current approaches struggle to recommend services absent in the training data due to the dynamics of evolving services and cannot automatically compose services according to the recommendations. To tackle these problems, this paper proposes a Large Language Models (LLMs)-based Service Process Automation framework named LaSPA. Firstly, LaSPA includes a system that can handle the evolution of software services, involving adaptively adding and deleting services. When user requirements arise, LaSPA retrieves the Top-k services by assessing the similarities between the requirements and available services in the repository. Then, LaSPA transforms the service recommendations into multiple-choice questions for accurate recommendations that rely on the semantic understanding of services with the help of LLMs. Finally, LaSPA utilizes the reasoning ability of LLMs to orchestrate the recommended services for the service process automation. Our observations suggest that LaSPA outperforms baseline methods. Compared to the recommendations approach, LaSPA can more easily cope with the evolution of services. The evolution experiment results indicate a 35.9

Context: Recent years have witnessed a prevailing trend of developing applications using microservice architectures. Microservice systems typically involve multiple containers that share resources on a single physical host, thereby complicating the interdependencies among microservices. This complexity significantly hinders the identification of root causes of performance issues. Objective: Performance issues can manifest in various forms. Existing approaches often overlook other potential failure indicators, such as process anomalies that are discernible in audit logs. This paper aims to refine the granularity of root cause analysis to the process level. Methods: This paper proposes a novel approach called MHP-RCA (Multivariate Hawkes Process-based Root Cause Analysis), which integrates diverse data types, including metrics and audit logs, to localize the root cause in microservice systems. MHP-RCA generates anomalous events from the observable data, then leverages the multivariate Hawkes process to construct causal graphs for effective root cause identification. Results: Extensive experiments, involving the injection of various anomalies into four widely used open-source benchmarks, demonstrate that MHP-RCA surpasses multiple baseline methods in most cases. Compared to the best-performing baseline approach, MHP-RCA achieves an average overall improvement of 2.5% in AC@1 and 3.7% in AC@5. Conclusion: The proposed method MHP-RCA, which considers audit logs and metrics, can localize the root cause of microservice anomalies at the process level.

Interactive Recommendation (IR) has attracted considerable attention in recent years. IR agents commonly utilize Deep Reinforcement Learning (DRL) to capture users' unique dynamic interests and demands. However, it's challenging to train DRL agents in online recommender systems due to the large action space and the sample inefficiency problem. We discover that the principle of tackling this challenge is to integrate neighborhood collaborative information into the representation. To implement this idea and address the challenge, we propose CPIR (Contrastive Paradigm for Representation Learning in Interactive Recommendation), which comprises three Contrastive Learning (CL) approaches, a data sampling mechanism, and an agent training mechanism. The CL methods start from the perspectives of sequence alignment, interest partial order, and interest community collaborative filtering separately. The recommender agent can optimize itself more efficiently on top of the extracted representations. The data sampling and agent training mechanism ensure the stability and consistency of the multi-task training in IR. Moreover, we have explained the effectiveness of the CPIR both theoretically and experimentally. Extensive experiments conducted on Virtual-Taobao and ML-1M have demonstrated superior improvements in sample efficiency during the training of the DRL-based IR agent.

In online social networks, trust relationships between users play a vital role in connecting like-minded friends and identifying trustworthy information. However, conventional approaches, mainly utilizing graph attention networks, often regard trust interactions as static and neglect their dynamic nature. Such a limitation undermines the precision of modeling trust dynamics and obstructs the comprehension of how trust evolves within online social networks. To address this challenge, we propose TrustFormer, a novel collaborative approach that integrates time-dependent trust interactions and explicitly predicts dynamic trust relationships. Specifically, TrustFormer first embeds an evolving topology from trust interactions to capture latent temporal features. It then applies time encoding within a multi-head attention network, quantifying the significance of time-sensitive topological features. Further, TrustFormer employs bidirectional interaction transferring to formalize shared trust topological features. Finally, pairwise trust relationships are evaluated using these topological features. Supported by extensive experiments on two real-world datasets, our approach demonstrates significant improvements in trust dynamics modeling, outperforming state-of-the-art methods in accuracy.

Recommending developers suitable for Pull Requests (PRs) review holds paramount importance in facilitating evolution and knowledge sharing on GitHub. Current researches primarily focus on modeling developer expertise or developer-PR interactions using historical review data. However, these approaches lack consideration for integrating domain-specific PRs and temporal changes into developer recommendations, which results in sub-optimal performance. To address these problems, we introduce a time-aware developer recommendation approach based on multi-feature fusion, called TFRec. We utilize the BERT model, trained via contrastive learning, to embed textual PR information (e.g., title and description), facilitating efficient semantic learning and generalization improvement. Additionally, we employ high-order propagation and embedding to fuse the semantic and structure features of historical data and capture potential collaborative relationships from developer-PR interactions. Furthermore, a time-aware attention is introduced to encode the temporal features into the propagation and embedding process. Extensive experiments on a dataset of 65k PRs from 10 GitHub open-source projects demonstrate the superior performance of our proposed method compared to state-of-the-art approaches.

Self-organization scheduling is a critic must to support the wide use of autonomous aerial vehicles (AAVs) in many scenarios, where frequent changes of network topology caused by high mobility of both AAVs and mobile devices (MDs) lead to great challenges. We propose a self-organization scheduling architecture of dynamic AAV-MD networks containing three sub-problems, respectively for AAVs' flight route planning, dynamic network topology control and task offloading decision. Three-layered hierarchical reinforcement learning (HRL) is adopted to solve the corresponding sub-problems. In particular, the idea of 'learn a priori in advance' is proposed, where one layer is used to learn the current network topology as a prior and feed it to the other two layers as a constraint. Unlike the traditional way of allowing each AAV or MD to select a coalition without any constraint, our method simplifies scheduling by learning a topology related rule for coalition formation without degrading system performance. More importantly, the proposed three-layer deep hierarchical learning framework is organized with two layers working in parallel and nesting with the other one. Simulation results show that our approach has good convergence performance, and can efficiently cope with high mobility of MDs, but without the need of frequent and large-scale AAV position adjustments.

As privacy protection gains increasing importance, more models are being trained on edge devices and subsequently merged into the central server through Federated Learning (FL). However, current research overlooks the impact of network topology, physical distance, and data heterogeneity on edge devices, leading to issues such as increased latency and degraded model performance. To address these issues, we propose a new federated learning scheme on edge devices that called Federated Learning with Encrypted Data Sharing(FedEDS). FedEDS uses the client model and the model's stochastic layer to train the data encryptor. The data encryptor generates encrypted data and shares it with other clients. The client uses the corresponding client's stochastic layer and encrypted data to train and adjust the local model. FedEDS uses the client's local private data and encrypted shared data from other clients to train the model. This approach accelerates the convergence speed of federated learning training and mitigates the negative impact of data heterogeneity, making it suitable for application services deployed on edge devices requiring rapid convergence. Experiments results show the efficacy of FedEDS in promoting model performance.

Social recommendations play a crucial role in helping users filter information and discover potential requirements. However, existing works often ignore the effects of memory patterns and social inconsistency, which hide the recommendation for capturing evolving user interests. To overcome these problems, a model incorporating the Forgetting curve and Memory Replay for Evolving Socially-aware recommendation (FMRES) is proposed to navigate users’ fresh interests. Specifically, a cognitive-inspired Ebbinghaus curve is integrated with item attributes to consider users’ personalized interest forgetting and retention. Then, the memory replay mechanism is employed to revive forgotten yet valuable items, fostering user engagement and enhancing relevance in recommendations. By aggregating the neighbors’ social characters, consistent friends are sampled to identify meaningful and impactful relationships. Finally, temporal representations of users and items are incorporated to track the evolution of users’ interests by utilizing gated recurrent units. Extensive experiments on three datasets demonstrate that the proposed model consistently outperforms advanced baseline methods over various metrics.

With limited computing and communication resources, it is a big challenge for AAVs (Autonomous Aerial Vehicles) self-organization scheduling to achieve the minimum cost and offload delay at the same time, especially in a fully dynamic scenario with ground MDs (Mobile Devices). We propose a two-stage multi-objective self-organization scheduling architecture using deep reinforcement learning (DRL) to solve this problem, in which every single objective attainment is learned prior to learning multi-objective cooperation. In Stage 1, we decompose the original scheduling problem into two parts for achieving two objectives (minimizing energy consumption and minimizing offloading delay): training the AAV’s flight strategy to reduce energy consumption with the offloading policy fixed, and training the task offloading policy with the AAV’s flight strategy fixed. We derive a new multi-objective policy gradient with a credit function for fine-grained credit assignment. In Stage 2, we innovatively introduce a universal value approximator as a function to bridge policy and value functions across the sub-problems, where the parameters in the function are trained by actor-critic approach using the outputs of Stage 1 as its initial inputs. Our algorithm exactly explores how each sub-problem contributes to the overall objective, avoiding the penalty of random exploration when the other two sub-problems have been well rewarded, which can benefit the optimization process. Experimental results show that our approach has good convergence performance and can efficiently cope with large scale AAVs and MDs.

Traditional DRAM-based memory solutions face challenges, including high energy consumption and limited scalability. Non-Volatile Memory (NVM) offers low energy consumption and high scalability. However, security challenges, particularly data remanence vulnerabilities, persist. Prevalent methods such as the Bonsai Merkle Tree (BMT) are employed to ensure data security. However, the consistency requirements for integrity tree updates have led to performance issues. It is observed that compared to a secure NVM system without persistent secure metadata, the average overhead for updating and persisting the BMT root with persistent secure metadata is as high as 2.48 times. Therefore, this paper aims to mitigate these inefficiencies by leveraging the principle of memory access locality. We propose the Dynamic Construction and Adjustment of Skewed Bonsai Merkle Tree (DCAS-BMT). The DCAS-BMT is dynamically built and continuously adjusted at runtime according to access weights, ensuring frequently accessed memory blocks reside on shorter paths to the root node. This reduces the verification steps for frequently accessed memory blocks, thereby lowering the overall cost of memory authentication and updates. Experimental results using the USIMM memory simulator demonstrate that compared to the widely used BMT approach, the DCAS-BMT scheme shows a performance improvement of 34.1%.

The emergence of the mobile edge computing paradigm enables the deployment of microservices on edge servers, which greatly improves the quality of services and reduces network transmission costs. However, due to limited computing and storage resources, an individual edge server can host only a limited number of microservice instances. Moreover, user mobility often results in uneven distribution of service requests in mobile edge computing systems. To this end, it is a key problem to dispatch microservice requests to appropriate edge servers to minimize the average service response time. Current solutions to this problem rely on centralized methods and suffer from serious problems of single point of failure, error-proneness, difficult expansion, low robustness, etc. To resolve these problems, this paper proposes a decentralized game-theoretic approach for dispatching microservice requests effectively and efficiently in mobile edge computing systems. Specifically, we formulate the request dispatching problem as a decentralized non-cooperative game and propose a decentralized request dispatching algorithm that can find the Nash equilibrium through finite iterations. We conduct a series of experiments to demonstrate that our approach beats benchmarking approaches with close-to-optimal performance and high efficiency measured by convergence time.

Traditional recommendation systems focus on maximizing user satisfaction by suggesting their favorite items. This user-centric approach may lead to unfair exposure distribution among the providers. On the contrary, a provider-centric design might become unfair to the users Therefore, this paper proposes a re-ranking model FairSort 1 to find a trade-off solution among user-side fairness, provider-side fairness, and personalized recommendations utility. Previous works habitually treat this issue as a knapsack problem, incorporating both-side fairness as constraints. In this paper, we adopt a novel perspective, treating each recommendation list as a runway rather than a knapsack. In this perspective, each item on the runway gains a velocity and runs within a specific time, achieving re-ranking for both-side fairness. Meanwhile, we ensure the Minimum Utility Guarantee for personalized recommendations by designing a Binary Search approach. This can provide more reliable recommendations compared to the conventional greedy strategy based on the knapsack problem. We further broaden the applicability of FairSort, designing two versions for online and offline recommendation scenarios. Theoretical analysis and extensive experiments on real-world datasets indicate that FairSort can ensure more reliable personalized recommendations while considering fairness for both the provider and user.

Service recommendations are crucial for developers to create mashups such as mobile applications, workflows, e-business solutions, etc. Existing methods based on collaborative filtering or content analysis are manual and cannot automatically acquire services that align with the requirements of mashup creation. A possible solution to automatically acquiring necessary services for mashups is the seq2seq (sequence to sequence) generation model, which has demonstrated promising performance in automatic text and program code generation. However, two main challenges must be tackled in service acquisition based on the seq2seq model. First, the seq2seq model can only acquire a set of services without inter-service dependencies, but such dependencies are crucial in the generation of sequences for services. Second, external knowledge must be leveraged to recommend services more accurately that fulfill developers' requirements, such as similar historical user requirements and combining mashup category information, due to the incomplete description of user requirements. To tackle these challenges, this paper proposes GSR ( G eneration of S ervice R ecommendations), an approach that can automatically acquire services based on user requirements. Specifically, GSR employs reinforcement learning to learn the inter-dependencies among services and integrate dependencies into service recommendations. To further improve the quality of the acquired services, GSR retrieves relevant user requirements based on BERT (Bidirectional Encoder Representation from Transformers) to help identify potential services. Experiment results conducted on real-world datasets show the superior performance of GSR. Compared with the existing recommendation approaches, the precision metric is increased by up to 1.99x, and the recall metric is increased by up to 12%.

With the rapid development of mobile communication and Internet of Things (IoT) technologies, smart mobile devices such as portable and sensor devices have been widely used in our daily lives. However, their compact size and limited energy capacity inherently hinder their ability to efficiently handle computation-intensive tasks within acceptable timeframes. To tackle this challenge, computation offloading has emerged as a pivotal solution. Computation offloading can significantly reduce the response time and energy consumption for mobile devices executing such tasks. However, it also bring some challenges, notably the risk of compromising user privacy. In this paper, we prioritize user privacy alongside considerations of service delay and energy consumption, and model the offloading decision problem as a multi-objective optimization problem. We employ an enhanced multi-objective bat algorithm to identify Pareto front solutions, balancing the diverse objectives effectively. Our experimental validation confirms the feasibility and efficacy of the proposed method, offering a promising avenue for addressing the complexities of computation offloading in mobile edge computing systems.

The recommendation system recommends service providers on platforms according to their trust. However, the diversity of platforms and malicious attacks can affect the trust of service providers and lead to reliable services unavailable for users and partners. To address the issue, in this paper, we introduce the blockchain into service recommendation and propose a blockchain-based service recommendation and trust enhancement model. First, we propose platform heterogeneous factors to improve the accuracy of service recommendations. Second, we deploy the smart contracts on the blockchain, which implements trust aggregation that considers multiple recommendations for the same service provider and ultimately generates reliable recommendation results. Finally, we propose a trust enhancement algorithm in the smart contract, which can solve the trust unreliability problem caused by malicious attacks. Extensive experiments on case studies and real datasets. In comparison, our method outperforms the baseline methods by achieving a 22% reduction in RMSE and an 8% increase in coverage, thereby demonstrating the effectiveness and reliability of our method.

Multi-scale detection based on Feature Pyramid Networks (FPN) has been a popular approach in object detection to improve accuracy. However, using multi-layer features in the decoder of FPN methods entails performing many convolution operations on high-resolution feature maps, which consumes significant computational resources. In this paper, we propose a novel perspective for FPN in which we directly use fused single-layer features for regression and classification. Our proposed model, You Only Look One Hourglass (YOLOH), fuses multiple feature maps into one feature map in the encoder. We then use dense connections and dilated residual blocks to expand the receptive field of the fused feature map. This output not only contains information from all the feature maps, but also has a multi-scale receptive field for detection. The experimental results on the COCO dataset demonstrate that YOLOH achieves higher accuracy and better run-time performance than established detector baselines, for instance, it achieves an average precision (AP) of 50.2 on a standard 3× training schedule and achieves 40.3 AP at a speed of 32 FPS on the ResNet-50 model. We anticipate that YOLOH can serve as a reference for researchers to design real-time detection in future studies. Our code is available at https://github.com/wsb853529465/YOLOH-main.

Financial institutions may be subject to financial fraud by malicious users because of the large amount of transaction data and sensitive user information involved. Therefore, it is crucial to design a machine learning model that can detect abnormal data in financial institutions. However, with the development of the economy and technology, the massive amount of user-generated data is distributed among various financial institutions, and how to enable multiple financial institutions to collaborate on anomalous data detection has become a new challenge. In this paper, we propose a blockchain-based federated learning architecture to assist multiple financial institutions to collaborate on anomaly detection. First, anomaly detection models are trained locally without sharing local data, which effectively protects data privacy. Second, the architecture introduces a differential privacy algorithm to protect data security in communication. Finally, to avoid communication bottlenecks that threaten data security, the architecture employs the aperiodic aggregation algorithm in which clients collaborate to reduce communication costs. Experimentally, a large number of experiments are conducted using three datasets to evaluate the proposed architecture. The experimental results show that the architecture is effective in detecting anomalous data and reducing communication costs.

Federated Learning (FL) can train models in an edge environment without sending raw data. However, the performance is still constrained by data heterogeneity. To address the problems of data heterogeneity and resource scarcity in edge devices, we propose Federal Learning via Dynamic Aggregation (FedDA), which eliminates the influence of data heterogeneity and improves model accuracy. FedDA updates the impact of individual local models on the global model in real-time at different stages. It adjusts the local epoch in each round to prevent the device from dropping out while obtaining a more accurate local model. The core module is the model impact factor (MIF) that inscribes the aggregation weights to solve the impact of fixed weights on the aggregation model with improper extraction of local information. We conducted several experiments to evaluate the convergence speed using different algorithms on the MINIST. FedDA consistently outperforms the other six SOTA algorithms on MNIST, Cifar10, and Cifar100 datasets. In significant data heterogeneity, FedDA improves accuracy by up to 6% over the different algorithms and at least about 3%, especially in resource-scarce environments. To reach the specified accuracy, FedDA is 3 times faster than SCAFFOLD and at least 50% faster than other algorithms.