The dynamic topology, resource constraints, and data heterogeneity inherent in the Internet of Vehicles (IoV) present fundamental challenges to the effective deployment of federated learning (FL) applications. Traditional FL strategies often suffer from suboptimal model performance and excessive communication overhead under such conditions. Existing solutions primarily focus on static resource allocation and overlook the compounded effects of high mobility, diverse device capabilities, and time-varying data quality. Moreover, current incentive mechanisms lack adaptability to dynamic resource-benefit trade-offs, making it challenging to sustain efficient participation from vehicle clients. To address these issues, we propose NBCI-FL, an incentive framework that redefines vehicular collaboration as a multi-objective coalition game. It introduces a mobility-aware coalition-formation mechanism based on heterogeneous coalition games, along with a three-dimensional evaluation-based client-selection mechanism to construct efficient and stable learning clusters. Furthermore, we propose a two-stage Nash bargaining game that dynamically balances the fairness of data contributions with the optimization of resource utilization efficiency. Theoretical analysis proves the existence and effectiveness of the Nash bargaining equilibrium under vehicular dynamic conditions. Extensive simulations on real-world datasets demonstrate that our proposed NBCI-FL substantially outperforms state-of-the-art traditional FL baselines by maintaining high global model accuracy, improving communication efficiency, enhancing network stability, and ensuring fair and rational utility allocation among all participants.

Federated Learning (FL) enables collaborative model training across distributed clients without requiring the exchange of raw data. However, existing One-Shot FL (OSFL) methods, designed for communication efficiency by reducing fed-erated rounds to one, suffer substantial performance degradation when faced with highly non-IID data across clients, primarily due to critical distribution shifts: label shift, feature shift, and concept shift. In this paper, we introduce POSFed, a new personalized three-stage approach, to systematically address these fundamen-tal limitations: (1) Each client locally generates robust and label-agnostic synthetic datasets via self-supervising learning, ensuring essential knowledge is captured despite local distribution shifts; (2) The server aggregates all synthetic datasets to train a global feature extractor, capturing generalizable and transferable rep-resentations across heterogeneous client data; and (3) Each client efficiently adapts the feature extractor by learning a personalized classification head on its own data, enabling effective local customization and mitigating both feature and concept shifts. Extensive experiments across multiple benchmarks demonstrate that POSFed significantly outperforms state-of-the-art methods, achieving performance comparable to multi-round personalized approaches while using only one communication round. By ensuring both superior personalization and practical communication efficiency, POSFed establishes a feasible paradigm for FL under more realistic and heterogeneous conditions. Code is available at https://github.com/I643204431IPOSFed.

In monitoring station observation, for the best accuracy of rumor source detection, it is important to deploy monitors appropriately into the network. There are, however, a very limited number of studies on the monitoring station selection. This article will study the problem of detecting a single rumormonger based on an observation of selected infection monitoring stations in a complete snapshot taken at some time in an online social network (OSN) following the independent cascade (IC) model. To deploy monitoring stations into the observed network, we propose an influence-distance-based$k$-station selection method where the influence distance is a conceptual measurement that estimates the probability that a rumor-infected node can influence its uninfected neighbors. Accordingly, a greedy algorithm is developed to find the best$k$monitoring stations among all rumor-infected nodes with a 2-approximation. Based on the infection path, which is most likely toward the$k$infection monitoring stations, we derive that an estimator for the “most like” rumor source under the IC model is the Jordan infection center in a graph. Our theoretical analysis is presented in the article. The effectiveness of our method is verified through experiments over both synthetic and real-world datasets. As shown in the results, our$k$-station selection method outperforms off-the-shelf methods in most cases in the network under the IC model.

Mobile Crowdsourcing (MCS) is a novel distributed computing paradigm that recruits skilled workers to perform location-dependent tasks. A number of mature incentive mechanisms have been proposed to address the worker recruitment problem in MCS systems. However, most of them assume that there is a large enough worker pool and a sufficient number of users can be selected. This may be impossible in large-scale crowdsourcing environments. To address this challenge, we consider the MCS system defined on a location-aware social network provided by a social platform. In this system, we can recruit a small number of seed workers from the existing worker pool to spread the information of multiple tasks in the social network, thus attracting more users to perform tasks. In this paper, we propose a Multi-Task Diffusion Maximization (MT-DM) problem that aims to maximize the total utility of performing multiple crowdsourcing tasks under the budget. To accommodate multiple tasks diffusion over a social network, we create a multi-task diffusion model, and based on this model, we design an auction-based incentive mechanism, MT-DM-L. To deal with the high complexity of computing the multi-task diffusion, we adopt Multi-Task Reverse Reachable (MT-RR) sets to approximate the utility of information diffusion efficiently. Through both complete theoretical analysis and extensive simulations by using real-world datasets, we validate that our estimation for the spread of multi-task diffusion is accurate and the proposed mechanism achieves individual rationality, truthfulness, computational efficiency, and$(1-1/\sqrt{e}-\varepsilon )$approximation with at least$1-\delta$probability.

Influence Maximization (IM) is a well-known topic in mobile networks and social computing that aims to find a small subset of users that maximize the influence spread through an online information cascade. Recently, some cautious researchers have paid attention to the diversity of information dissemination, especially community-aware diversity, and formulated the diversified IM problem. Diversity is ubiquitous in many real-world applications, but these applications are all based on a given community structure. In social networks, we can form heterogeneous community structures for the same group of users according to different metrics. Therefore, how to quantify diversity based on multiple community structures is an interesting question. In this paper, we propose a Composite Community-Aware Diversified IM (CC-DIM) problem, which aims to select a seed set to maximize the influence spread and the composite diversity over all possible community structures under consideration. To address the NP-hardness of the CC-DIM problem, we adopt the technique of reverse influence sampling and design a random Generalized Reverse Reachable (G-RR) set to estimate the objective function. The composition of a random G-RR set is much more complex than the RR set used for the IM problem, which will lead to the inefficiency of traditional sampling-based approximation algorithms. Because of this, we further propose a two-stage algorithm, Generalized HIST (G-HIST). It can not only return a$(1-1/e-\varepsilon)$approximate solution with at least$(1-\delta)$probability but also improve the efficiency of sampling and ease the difficulty of searching by significantly reducing the average size of G-RR sets. Finally, we evaluate our proposed G-HIST on real datasets against existing algorithms. The experimental results show the effectiveness of our proposed algorithm and its superiority over other baseline algorithms.

In practical recommendation scenarios, the types of user behaviors are usually diverse (e.g., click, add-to-cart, purchase), and different types of user behaviors can provide different aspects of user preference information. However, most existing methods only consider a single type of user behavior for modeling, which is not sufficient to fully learn complex user preferences. Besides multiple behavior types, the heterogeneous preference strength of users for items under the same behavior is also a factor that is often overlooked by most methods. Moreover, different types of behaviors may be correlated due to various factors, inadequate exploration of the implicit relationships between different types of behaviors may lead to the loss of potential information across behaviors. To solve the above problems, we propose a novel multi-behavior model with relation-aware graph attention network (RGAN), which is built on a graph-based neural architecture to explore high-order user-item relations. Specifically, we design a relation-aware attention propagation layer and an inter-behavior dependency encoder to capture heterogeneous collaborative signals from type-specific and inter-type behavior relations, respectively. During behavior integration, our proposed model automatically learns which types of behaviors are more important for assisting target behavior prediction. Extensive experiments conducted on three real-world datasets demonstrate that the RGAN model consistently outper-forms many state-of-the-art baselines, in terms of HR@n and NDCG@n.

With the growing popularity of artificial intelligence in drug discovery, many deep-learning technologies have been used to automatically predict unknown drug-target interactions (DTIs). A unique challenge in using these technologies to predict DTI is fully exploiting the knowledge diversity across different interaction types, such as drug-drug, drug-target, drug-enzyme, drug-path, and drug-structure types. Unfortunately, existing methods tend to learn the specifical knowledge on each interaction type and they usually ignore the knowledge diversity across different interaction types. Therefore, we propose a multitype perception method (MPM) for DTI prediction by exploiting knowledge diversity across different link types. The method consists of two main components: a type perceptor and a multitype predictor. The type perceptor learns distinguished edge representations by retaining the specifical features across different interaction types; this maximizes the prediction performance for each interaction type. The multitype predictor calculates the type similarity between the type perceptor and predicted interactions, and the domain gate module is reconstructed to assign an adaptive weight to each type perceptor. Extensive experiments demonstrate that our proposed MPM outperforms the state-of-the-art methods in DTI prediction.

Community partition is an important problem in many areas, such as biology networks and social networks. The objective of this problem is to analyze the relationships among data via the network topology. In this article, we consider the community partition problem under the independent cascade (IC) model in social networks. We formulate the problem as a combinatorial optimization problem that aims at partitioning a given social network into disjoint$m$communities. The objective is to maximize the sum of influence propagation of a social network through maximizing it within each community. The existing work shows that the influence maximization for community partition problem (IMCPP) is NP-hard. We first prove that the objective function of IMCPP under the IC model is neither submodular nor supermodular. Then, both supermodular upper bound and submodular lower bound are constructed and proved so that the sandwich framework can be applied. A continuous greedy algorithm and a discrete implementation are devised for upper and lower bound problems. The algorithm for both of the two problems gets a$1-1/e$approximation ratio. We also present a simple greedy algorithm to solve the original objective function and apply the sandwich approximation framework to it to guarantee a data-dependent approximation factor. Finally, our algorithms are evaluated on three real datasets, which clearly verifies the effectiveness of our method in the community partition problem, as well as the advantage of our method against the other methods.

Despite the massive surge of evolving social network analysis in popularity, existing research usually represent the observed social interactions among individuals as completely credible edges. However, due to information inaccuracy, individual non-response and dropout, and sampling biases in observations, the evolving noisy social network that coexists true edges and spurious edges is pervasive in actual applications, where the ignoration of credibility otherness of observed edges could lead to the wrong estimates of social properties and misleading conclusions. To discover credible edge information to shape correct social interactions among individuals, we propose a universal and explainable multiple-neighbor evolutional filtering method (MEFM) to evaluate how credible of observed edges to ‘truly’ exist in the evolving noisy social network.MEFMconsists of an evolutional extractor and a filtering evaluator. To resist the noisy disturbance, the evolutional extractor exploits the evolutional states of edges from the perspective of evolution mechanisms within multiple-neighbor ranges, which applies different link prediction algorithms to fit the evolution mechanism in the formation of each edge. Further, the filtering evaluator reconstructs Kalman filter to predict and refine the evolutional states of edges based on their evolving local structures. As a result,MEFMcombines the evolutional extractor and the filtering evaluator to analyze the evolutional fluctuations of the observed edges to evaluate their credibility. Extensive experiments on real-world datasets demonstrate that our proposedMEFMcan effectively and reasonably evaluate edge credibility in evolving noisy social networks.

As vehicles are becoming more and more intelligent, mobile data traffic in vehicular ad hoc network (VANET) has been increasing dramatically. This makes the communication capacity of VANET systems and the computing resources of vehicles insufficient. In the meantime, location-aware large-scale distributed services with very low latency and high reliability are demanded by most of the novel functions, such as accident alarming, and congestion warning, in the intelligent transportation system. To meet these claimed characteristics of VANET, we first present a novel architecture that integrates vehicular fog computing and vehicle-to-vehicle (V2V) communication technologies. Lower latency and higher quality services can be supplied to vehicles by nearby fog servers, which are virtualized from vehicles that locate close enough and communicate using the V2V link. However, like all collaborative systems, computing reliability is vital to collaborative VANET. In this article, we design a novel energy-efficient proactive replication mechanism. Follower vehicles calculate with a lazy rate act as backups of host vehicles to ensure the reliability of the system. Considering the time sensitivity of computing requirements in VANET, the upper bound on the total number of failures is proposed through theoretical analysis. Then, the lower bound on the lazy calculating rate of followers is derived by balancing the tradeoffs between delay and energy. A fast algorithm for searching this lower bound based on the discrete Newton method is also proposed. Results of numerical experiments show that our new mechanism is effective in energy saving and reliability enhancing.

In this paper, we study the channel assignment problem in cellular-VANET heterogeneous wireless networks. The D2D communication technology can be applied to VANET. Vehicular device-to-device (D2D) network as an underlying network to the cellular network can share the uplink channel resources of the cellular network. Interference as a critical element has an impact on the utilization in channel assignment. To minimize the interference when allocating channels, we present a novel channel assignment algorithm based on reuse distance. Essentially we have limited spectrum resources that can be shared by vehicular transmitters and cellular users in an area, to assign the minimal number of channels to vehicles in a prescribed area is our first concern. Since the interference between co-channel devices is related to their distance, we divide the area to small hexagon regions then use Region-based Channel Assignment Algorithm to assign different channel sets to each region. In this case, three sets of resources can fulfill the channel assignment requirements to all vehicles. We also prove the theoretical guarantee as approximation factor of 3 for the minimal channel assignment problem. To improve the system throughput with limited channel resources in the HetNets, we propose a Local Search Throughput Maximization algorithm to find the vehicular transmitters and cellular users combinations. We prove the optimal approximation factor is (1-ε) and the complexity of our algorithm in each small region. We show the effectiveness and efficiency of proposed algorithm in experiments.