This article investigates the mean-square output consensus problem for heterogeneous linear multiagent systems (MASs) over random packet loss channels. Agent heterogeneity is reflected in possibly different state dimensions and dynamic parameters. In addition to heterogeneity, a major challenge arises from relaxing the commonly adopted independent and identically distributed (i.i.d.) assumption on packet losses. To capture temporal correlations that are prevalent in practice, packet losses are modeled by a discrete-time Markov process. Since existing consensus controllers designed for i.i.d. losses may fail under Markovian packet losses, novel dedicated control schemes are developed. Two packet loss scenarios are considered: identical and nonidentical packet losses. For identical packet losses, where all channels drop packets simultaneously, both analytical and numerical consensus conditions are derived to guarantee consensus of the distributed observers. The analytical condition reveals the interplay among packet loss rate, communication topology, and system dynamics, while the numerical conditions are more computationally tractable. An output-regulation-based controller is then designed to achieve mean-square output consensus. For the more general case of nonidentical packet losses, edge Laplacian theory is employed to decouple packet loss processes from the communication topology, leading to consensus conditions for the distributed observers, as well as corresponding controllers that guarantee mean-square output consensus. Finally, numerical simulations are utilized to validate the results.

The influence maximization problem seeks to identify a set of influential users in a social network to maximize the spread of information. While prior research has focused extensively on improving computational efficiency, it has largely overlooked fairness in information dissemination across different social groups. A widely adopted fairness criterion is the maximin objective, which aims to maximize the minimum influence received by any group. However, under this objective, the fairness-aware influence maximization problem is NP-hard even to approximate well. In this work, we consider randomized seed selection strategies for fairness-aware influence maximization to address this challenge. We introduce a noise-based smoothing technique to tackle the non-smoothness of the objective function and develop an approximate solution based on the stochastic Frank–Wolfe algorithm. For efficient and theoretically grounded gradient estimation, we leverage the reverse influence sampling method, which enables provable gradient approximation. To obtain a discrete solution, we apply swap rounding to the fractional output, resulting in a randomized seed set that achieves a \((1-1/e,2\epsilon)\) -approximation for monotone functions and a \((1/e,2\epsilon)\) -approximation for non-monotone functions, with probability at least \(1-\delta\) , where \(\epsilon\) and \(\delta\) are user-defined accuracy parameters. Although accurate gradient estimation typically requires a large number of samples and may incur a high computational cost, we further derive upper and lower bounds on the gradient estimates and demonstrate that under certain conditions, using fewer samples still preserves the theoretical approximation guarantee. We validate our approach on six real-world social network datasets, and the results demonstrate that our algorithm effectively balances fairness and influence spread while maintaining strong performance.

Summary In the article, we devise streaming algorithms for maximization of a monotone submodular function subject to a cardinality constraint on the integer lattice. Based on the observation that lattice submodularity is not equivalent to diminishing return submodularity on the integer lattice but rather a weaker condition, we propose a one‐pass streaming algorithm with a modified binary search as subroutine of each step. Finally, we show that the algorithm is with approximation ratio , memory complexity , and per‐element query complexity .

Bundle recommendation is an emerging research direction in the recommender system with the focus on recommending customized bundles of items for users. Although Graph Neural Networks (GNNs) have been applied to this problem and achieved superior performance, existing methods underexplore the graph-level GNN methods, which exhibit great potential in traditional recommender system. Furthermore, they usually lack the transferability from one domain with sufficient supervision to another domain which might suffer from the label scarcity issue. In this work, we propose a subgraph-based Graph Neural Network model, SuGeR, for bundle recommendation to handle these limitations. SuGeR generates heterogeneous subgraphs around the user-bundle pairs and then maps those subgraphs to the users' preference predictions via neural relational graph propagation. Experimental results show that SUGER significantly outperforms the state-of-the-art baselines in the basic and the transfer bundle recommendation tasks by up to 77.17% by [email protected] The source code is available at: https://github.com/Zhang-Zhenning/SUGER.

In multichannel high-resolution and wide-swath (HRWS) synthetic aperture radar (SAR) ground moving target indication (GMTI) systems, Doppler centroid (DC) is an essential parameter for spectrum reconstruction and image focusing. However, the conventional DC estimator faces many problems in moving target with multichannel SAR system, such as nonuniform data in azimuth, subsignal usage, and channel mismatch. To estimate the DC of moving target, the modified cross-correlation coefficient (MCCC) method for multichannel SAR system is proposed in this letter, which is especially suitable for nonuniform and undersampled data. Simulations with real spaceborne data demonstrate the effectiveness of this method.

Control framework design is critical to future SDN/NFV-enabled satellite network. However, the current multi-layer constellation based solutions have drawbacks in terms of availability, latency, openness, etc. The key contribution in this work is the study of an efficient control framework, which logically consists of two parts: entity part and overlay part. The entity part is a novel heterogeneous single-layer LEO satellite network, while the overlay part implements a virtualized overlay network. We have implemented a lightweight prototype of our framework and compared it with a GEO satellite based solution (i.e. OpenSAN). We demonstrate proof-of-concept that our framework performs better than OpenSAN with respect to control latency and avoids potential system bottleneck.

The proposed MSN architecture is intended to directly address the challenge of mobility, which refers to the motion of users as well as the dynamics of the satellite constellation. A virtual access point layer consisting of fixed virtual satellite network attachment points is superimposed over the physical topology in order to hide the mobility of satellites from the mobile endpoints. Then the MSN enhances endpoint mobility by a clean separation of identity and logical network location through an identity-to-location resolution service, and taking full advantage of the user's geographical location information. Moreover, a SDN based implementation is presented to further illustrate the proposal.