Federated Learning (FL) has become a prominent framework for maintaining privacy in recommender systems by enabling decentralized model training. Despite its benefits, traditional Federated Recommender Systems (FRSs)—often relying on collaborative filtering or generative models such as Variational Autoencoders (VAEs)—face limitations in capturing complex user-item interactions, resulting in suboptimal performance. Recent advancements in diffusion-based models, exemplified by L-DiffRec, have demonstrated superior capability in modeling intricate patterns. However, these models encounter significant challenges in federated settings, including data heterogeneity and slow convergence. To address these limitations, this paper introduces FedDiffRec, a novel federated framework that employs a module-wise training strategy and utilize a pseudo-interaction pretraining. Specifically, the VAE module is first trained locally, followed by fine-tuning with a diffusion module. Additionally, a pseudo-interaction pretraining mechanism is proposed to address challenges related to model initialization and convergence. Experimental results show that FedDiffRec enhances the stability and performance of diffusion-based models in federated environments, effectively bridging the performance gap between advanced diffusion-based approaches and traditional FRSs.

Federated recommender systems are used to address privacy issues in recommendations. Among them, FedVAE extends the representative non-linear recommendation method MultVAE. However, the bottleneck of FedVAE lies in its communication load during training, as the parameter volume of its first and last layers is correlated with the number of items. This leads to significant communication cost during the model's transmission phases (distribution and upload), making FedVAE's implementation extremely challenging. To address these challenges, we propose an Efficient Federated Variational AutoEncoder for collaborative filtering, EFVAE, which core is the Federated Collaborative Importance Sampling (FCIS) method. FCIS reduces communication costs through a client-to-server collaborative sampling mechanism and provides satisfactory recommendation performance through dynamic multi-stage approximation of the decoding distribution. Extensive experiments and analyses on real-world datasets confirm that EFVAE significantly reduces communication costs by up to 94.51% while maintaining the recommendation performance. Moreover, its recommendation performance is better on sparse datasets, with improvements reaching up to 13.79%.

Federated multimedia recommendation remains unexplored due to the high dimensionality of multimedia context, which limits the federated optimization on resource-constrained user devices. To address this issue, we propose a resource-efficient and secure federated learning framework for multimedia recommendation. Instead of training the entire model, we split the multimodal learning model to the powerful server, and the client trains the lightweight collaborative filtering model. Only the local model and item representations are transferred between the server and clients. We also propose an inter-client convolution strategy that utilizes secure multi-party computation to guarantee user privacy while alleviating heterogeneity among clients. We conduct evaluations on three datasets and demonstrate that our proposed method effectively exploits the modality features of items to improve performance while significantly reducing the communication and computation cost for clients.

Influence maximization, which aims to find a small number of influencers in a social network to maximize the influence spread under a certain propagation model, has attracted substantial attention due to its widespread applications, such as viral marketing and social advertising. However, most of the former studies focus primarily on maximizing the influence spread of a single product, which is not very common in actual marketing campaigns. In this article, we study a novel compatible influence maximization problem for two considered products, which involves more complex product adoption decisions of users in many realistic settings. The problem is NP-hard, and the objective function no longer exhibits monotonicity and submodularity. We propose an adapted greedy algorithm to solve the problem effectively. Due to its poor computational efficiency in the seed selection, we further propose a fast greedy algorithm that integrates several effective optimization strategies without compromising the accuracy and devise an efficient heuristic algorithm to approximate the influence spread calculation. Extensive experiments over real-world social networks of different sizes demonstrate the effectiveness and efficiency of the proposed methods.

User relationship prediction in the transaction of Blockchain is to predict whether a transaction will occur between two users in the future, which can be abstracted into the link prediction problem. The link prediction can be categorized into the positive one and the negative one. However, the existing negative link prediction algorithms mainly consider the number of negative user interactions and lack the full use of emotion characteristics in user interactions. To solve this problem, this paper proposes a negative link prediction algorithm based on the sentiment analysis and balance theory. Firstly, the user interaction matrix is constructed based on calculating the intensity of emotion polarity for social network texts, and a reliability weight matrix (noted as RW‐matrix) is constructed based on the user interaction matrix to measure the reliability of negative links. Secondly, with the RW‐matrix, a negative link prediction algorithm is proposed based on the structural balance theory by constructing negative link sample sets and extracting sample features. To evaluate the performance of the negative link prediction algorithm proposed, the variable management method is used to analyze the influence of negative sample control error and other parameters on the accuracy of it. Compared with the existing prediction benchmark algorithms, the experimental results demonstrate that the proposed negative link prediction algorithm can improve the accuracy of prediction significantly and deliver good performances.

In order to make better use of massive network comment data for decision-making support of customers and merchants in the big data era, this paper proposes two unsupervised optimized LDA (Latent Dirichlet Allocation) models, namely, SLDA (SentiWordNet WordNet-Latent Dirichlet Allocation) and HME-LDA (Hierarchical Clustering MaxEnt-Latent Dirichlet Allocation), for aspect-based opinion mining. One scheme of each of two optimized models, which both use seed words as topic words and construct the inverted index, is designed to enhance the readability of experiment results. Meanwhile, based on the LDA topic model, we introduce new indicator variables to refine the classification of topics and try to classify the opinion target words and the sentiment opinion words by two different schemes. For better classification effect, the similarity between words and seed words is calculated in two ways to offset the fixed parameters in the standard LDA. In addition, based on the SemEval2016ABSA data set and the Yelp data set, we design comparative experiments with training sets of different sizes and different seed words, which prove that the SLDA and the HME-LDA have better performance on the accuracy, recall value, and harmonic value with unannotated training sets.

As an effective method for detecting the schedulability of real-time tasks on multiprocessor platforms, Response time analysis (RTA) has been deeply researched in recent decades. Most of the existing RTA methods are designed for tasks that can be preempted at any time. However, in some real-time systems, a task may have some fixed preemption points (FPPs) that divide its execution into a series of non-preemptive regions (NPRs). In such environments, the task can only be preempted at its FPPs, which makes existing RTA methods for arbitrary preemption tasks not applicable. In this article, we study the schedulability analysis on tasks with FPPs under both global fixed-priority (G-FP) scheduling and global earliest deadline first (G-EDF) scheduling. First, based on the idea of limiting the time interval between two consecutive executions of an NPR, a novel RTA method for tasks with FPPs under G-FP scheduling is proposed. Second, we propose an effective RTA method for tasks with FPPs under G-EDF scheduling. Finally, extensive simulations are conducted and the results validate the effectiveness of the proposed methods.

As a crucial task in heterogeneous distributed systems, DAG-scheduling models a scheduling application with a set of distributed tasks by a Direct Acyclic Graph (DAG). The goal is to assign tasks to different processors so that the whole application can finish as soon as possible. Task Duplication-Based (TDB) scheme is an important technique addressing this problem. The main idea is to duplicate tasks on multiple machines so that the results of the duplicated tasks are available on multiple machines to trade computation time for communication time. Existing TDB algorithms enumerate and test all possible duplication candidates, and only keep the candidates that can improve the overall scheduling. We observe that while a duplication candidate is ineffective at the moment, after other duplications have been applied, this ineffective duplication candidate can become effective, which in turn can cause other ineffective duplications to become effective. We call this phenomenon the chain reaction of task duplication. We propose a novel Task Duplication based Clustering Algorithm (TDCA) to improve the schedule performance by utilizing duplication task more thoroughly. TDCA improves parameter calculation, task duplication, and task merging. The analysis and experiments are based on randomly generated graphs with various characteristics, including DAG depth and width, communication-computing cost ration, and variant computation power of processors. Our results demonstrate that the TDCA algorithm is very competitive. It improves the schedule makespan of task duplication-based algorithms for heterogeneous systems for various communication-computing cost ratios.

This paper presents a direct digital frequency synthesizer (DDFS) for high speed application based on multichannel structure. This DDFS has phase resolution of 32 bits and magnitude resolution of 12 bits. In order to ensure the high speed and high resolution at the same time, the multi-channel sampling technique is used and a 12 bits linear DAC is implemented. The chip is fabricated in TSMC 130nm CMOS technology with active area of 0.89mm×0.98mm and total power consumption of 300mW at a single 1.2V supply voltage. The maximum operating speed is up to 2.0GHz at room temperature.

Online backup service software provides automated, offsite, secure online data backup and recovery for remote computers. How to satisfy functional requirements and guarantee the fault tolerance of online backup service software is a difficult but crucial problem faced by software designers. In this paper, we investigate to incorporate the fault tolerant techniques in the system design, and propose a fault-tolerant online backup service model (FOBSM) to guide the development of online backup service system. The FOBSM comprises four components: backup client (BC), backup server (BS), storage server (SS), and online backup exception handler (OBEH). The first three components constitute three-party functional units, whereas OBEH serves as the centralized exception handling mechanism, which is devised to receive the external exceptions raised by the other entities, transform them into a global exception, and propagate it to the related entities to handle, so as to improve the fault tolerance of the software greatly. In order to provide precise and explicit idioms to system designers, we use Object-Z language to specify the FOBSM. Following the Object-Z reasoning rules, we reason about the fault tolerant properties of FOBSM and demonstrate that it can improve fault tolerance of the online backup service software effectively.

The conventional k-means clustering algorithm must know the number of clusters in advance and the clustering result is sensitive to the selection of the initial cluster centroids. The sensitivity may make the algorithm converge to the local optima. This paper proposes an improved k-means clustering algorithm based on quantum-inspired genetic algorithm (KMQGA). In KMQGA, Q-bit based representation is employed for exploration and exploitation in discrete 0-1 hyperspace by using rotation operation of quantum gate as well as three genetic algorithm operations (selection, crossover and mutation) of Q-bit. Without knowing the exact number of clusters beforehand, the KMQGA can get the optimal number of clusters as well as providing the optimal cluster centroids after several iterations of the four operations (selection, crossover, mutation, and rotation). The simulated datasets and the real datasets are used to validate KMQGA and to compare KMQGA with an improved k-means clustering algorithm based on the famous variable string length genetic algorithm (KMVGA) respectively. The experimental results show that KMQGA is promising and the effectiveness and the search quality of KMQGA is better than those of KMVGA.

This paper presents a 2GS/s 10-bit CMOS digital-to-analog converter (DAC). This DAC consists of a unit current-cell matrix for 6MSBs and another unit current-cell matrix for 4LSBs, trading off between the precision and size of the chip. The current mode logic (CML) is used to ensure high speed, and a double centro-symmetric current matrix is designed by the Q2random walk strategy in order to ensure the linearity of the DAC. The DAC occupies 2.2 times 2.2 mm2of die area, and consumes 790mw at a single 3.3V power supply

This paper proposes a novel heterogeneous software architecture FTA (fault tolerant architecture). FTA incorporates idealized fault tolerant component concept and coordinated error recovery mechanism in the early system design phase. It can be reused in the high level model design of specific mission critical distributed systems with reliability requirements. The formal model of FTA in the Object-Z language is presented to provide precise idioms to the system designers. Formal proof using the Object-Z reasoning rules are constructed to demonstrate the fault tolerant properties of FTA. By analyzing the customization process, we also present a FTA template, expressed in x-frames using XVCL (XML-based variant configuration language) methodology, to automate the customization process. We apply a sales control system case study to illustrate the customization of FTA.

This paper proposes a novel heterogeneous software architecture GFTSA (Generic Fault Tolerant Software Architecture) which can guide the development of safety critical distributed systems. GFTSA incorporates an idealized fault tolerant component concept, and coordinated error recovery mechanism in the early system design phase. It can be reused in the high level model design of specific safety critical distributed systems with reliability requirements. To provide precise common idioms & patterns for the system designers, formal language Object-Z is used to specify GFTSA. Formal proofs based on Object-Z reasoning rules are constructed to demonstrate that the proposed GFTSA model can preserve significant fault tolerant properties. The inheritance & instantiation mechanisms of Object-Z can contribute to the customization of the GFTSA formal model. By analyzing the customization process, we also present a template of GFTSA, expressed in x-frames using the XVCL (XML-based Variant Configuration Language) methodology to make the customization process more direct & automatic. We use an LDAS (Line Direction Agreement System) case study to illustrate that GFTSA can guide the development of specific safety critical distributed systems