This article studies the generalized Nash equilibrium (GNE) seeking problem of second-integrator multiplayer systems. In particular, each player is endowed with an individual payoff function with respect to collective decision variables, and simultaneously, a coupling inequality constraint and a set constraint are imposed to each player. The players communicate with their local neighbors over a directed topology. To begin with, a distributed-observer-based seeking strategy is synthesized by leveraging a proper composite variable. It is first demonstrated using nonsmooth analysis that the established distributed observer enables each player to accurately estimate the decision variables of others in terms of a strongly connected topology condition. Upon this basis, all the decision variables are then shown to converge to the expected GNE asymptotically borrowing from convex theory. In addition, three extension results are also given under the built GNE seeking framework. First, under the postulation that the velocity information is unavailable, a velocity-free distributed GNE seeking strategy is synthesized for second-integrator systems by implementing a proper auxiliary dynamics. Second, we consider nonlinear Euler-Lagrange systems with unknown inertia parameters and synthesize an improved distributed GNE seeking strategy resorting to an adaptation technique. Third, we focus on integrator chain systems and synthesize a modified distributed GNE seeking strategy using a new composite variable based on a proper coordinate transformation. For three extension cases, we all show in detail the achievement of the GNE seeking objective. Finally, a practical example is simulated to confirm the built GNE seeking results.

Federated learning is a new distributed machine learning framework, where numerous heterogeneous clients collaboratively train a model without sharing training data. In this work, we consider a practical and ubiquitous issue when deploying federated learning in mobile environments: intermittent client availability, where the set of eligible clients may change during the training process. Such intermittent client availability would seriously deteriorate the performance of the classical federated averaging algorithm (FedAvg). Thus, we propose a simple distributed nonconvex optimization algorithm, called federated latest averaging (FedLaAvg), which leverages the latest gradients of all clients, even when the clients are not available, to jointly update the global model in each iteration. Our theoretical analysis shows that FedLaAvg achieves guaranteed convergence and a sublinear speedup with respect to the total number of clients. We implement FedLaAvg along with several baselines and evaluate them over the benchmarking MNIST and Sentiment140 data sets. The evaluation results demonstrate that FedLaAvg achieves more stable training than FedAvg in both convex and nonconvex settings and reaches a sublinear speedup. Source code and online supplement are available at the IJOC GitHub site ( http://dx.doi.org/10.1287/ijoc.2022.0057.cd , https://github.com/INFORMSJoC/2022.0057 ). History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Leaning. Funding: This work was supported by the National Key R&D Program of China [Grant 2022ZD0119100], the National Natural Science Foundation of China (NSFC) [Grants 61972252, 61972254, 62072303, 62025204, 62132018, 62202296, and 62202297], the Alibaba Innovation Research (AIR) Program, and the Tencent Rhino Bird Key Research Project. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0057 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0057 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

The two-user Gaussian broadcast wiretap channel with common message and feedback (GBC-WTC-CM-F) is revisited. Traditionally, achievable secrecy rate of this model is achieved by combining Marton’s coding scheme for the two-user broadcast channel (BC) and the secret-key based feedback scheme, where both of the two feedback links are used to transmit secret keys shared between the transceivers. Recently, it has been shown that for the Gaussian wiretap channel with feedback, the Schalkwijk-Kailath (SK) feedback scheme achieves its secrecy capacity. Then it is natural to ask: can we do better when applying the SK-type scheme to the GBC-WTC-CM-F? In this paper, we answer this question by proposing two kinds of SK-type schemes. Specifically, first, we propose a hybrid scheme where one feedback link is used to transmit a secret key, and the other one is used for SK-type coding. We show that this hybrid scheme may perform better than the existing one in some cases. Next, we show that Ozarow’s extended SK scheme for the two-user Gaussian BC with feedback, where both feedback links are used for SK-type coding, is self-secure (satisfying perfect weak secrecy constraint by itself) and may perform the best. We further show that Ozarow’s scheme is in fact a secure finite blocklength coding scheme, and extend it to the static fading SISO and SIMO cases. Finally, the results of this paper are further explained by numerical examples.

Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization. However, the label matrix is generally a full-rank or approximate full-rank matrix, making the low-rank factorization inappropriate. Besides, in the latent space, the label correlations will become implicit. To this end, we propose a simple yet effective method to depict the high-order label correlations explicitly, and at the same time maintain the high-rank of the label matrix. Moreover, we estimate the label correlations and infer model parameters simultaneously via the local geometric structure of the input to achieve mutual enhancement. Comparative studies over twelve benchmark data sets validate the effectiveness of the proposed algorithm in multi-label classification. The exploited high-order label correlations are consistent with common sense empirically.Our code is publicly available athttps://github.com/Chongjie-Si/HOMI.

To meet the requirements of high accuracy and low cost of target classification in modern warfare, and lay the foundation for target threat assessment, the article proposes a human-machine agent for target classification based on active reinforcement learning (TCARL_H-M), inferring when to introduce human experience guidance for model and how to autonomously classify detected targets into predefined categories with equipment information. To simulate different levels of human guidance, we set up two modes for the model: the easier-to-obtain but low-value-type cues simulated by Mode 1 and the labor-intensive but high-value class labels simulated by Mode 2. In addition, to analyze the respective roles of human experience guidance and machine data learning in target classification tasks, the article proposes a machine-based learner (TCARL_M) with zero human participation and a human-based interventionist with full human guidance (TCARL_H). Finally, based on the simulation data from a wargame, we carried out performance evaluation and application analysis for the proposed models in terms of target prediction and target classification, respectively, and the obtained results demonstrate that TCARL_H-M can not only greatly save labor costs, but achieve more competitive classification accuracy compared with our TCARL_M, TCARL_H, a purely supervised model-long short-term memory network (LSTM), a classic active learning algorithm-Query By Committee (QBC), and the common active learning model-uncertainty sampling (Uncertainty).

Federated learning (FL) is an emerging distributed machine learning (ML) framework that operates under privacy and communication constraints. To mitigate the data heterogeneity underlying FL, clustered FL (CFL) was proposed to learn customized models for different client groups. However, due to the lack of effective client selection strategies, the CFL process is relatively slow, and the model performance is also limited in the presence of nonindependent and identically distributed (non-IID) client data. In this work, for the first time, we propose selecting participating clients for each cluster with active learning (AL) and call our method active client selection for CFL (ACFL). More specifically, in each ACFL round, each cluster filters out a small set of clients, which are the most informative clients according to some AL metrics [e.g., uncertainty sampling, query-by-committee (QBC), loss], and aggregates only its model updates to update the cluster-specific model. We empirically evaluate our ACFL approach on the public MNIST, CIFAR-10, and LEAF synthetic datasets with class-imbalanced settings. Compared with several FL and CFL baselines, the results reveal that ACFL can dramatically speed up the learning process while requiring less client participation and significantly improving model accuracy with a relatively low communication overhead.

Meta learning is a promising paradigm to enable skill transfer across tasks. Most previous methods employ the empirical risk minimization principle in optimization. However, the resulting worst fast adaptation to a subset of tasks can be catastrophic in risk-sensitive scenarios. To robustify fast adaptation, this paper optimizes meta learning pipelines from a distributionally robust perspective and meta trains models with the measure of tail task risk. We take the two-stage strategy as heuristics to solve the robust meta learning problem, controlling the worst fast adaptation cases at a certain probabilistic level. Experimental results show that our simple method can improve the robustness of meta learning to task distributions and reduce the conditional expectation of the worst fast adaptation risk.

Ultra-reliable low-latency communication (URLLC) and reconfigurable intelligent surface (RIS) aided communication are two key technologies in future wireless communications. However, secure URLLC over RIS-adied communication channels receives little attention in the literature. In this paper, we propose finite blocklength (FBL) coding schemes for RIS aided SISO/SIMO/MIMO systems in the presence of an eavesdropper (no direct link between the transceiver), which are based on an existing coding scheme for the point-to-point white Gaussian channel with noiseless feedback. Then, we show that the proposed schemes are self-secure when the blocklengths are larger than certain thresholds. Finally, numerical results show that for given decoding error probability and secrecy level, the required coding blocklengths of our proposed schemes are extremely short, and the secrecy capacities of the RIS-aided systems without channel feedback are significantly enhanced by our feedback schemes.

In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle unoriented edges or latent assumptions violation suffered by conventional methods, researchers formulated a reinforcement learning (RL) procedure for causal discovery and equipped a REINFORCE algorithm to search for the best rewarded directed acyclic graph. The two keys to the overall performance of the procedure are the robustness of RL methods and the efficient encoding of variables. However, on the one hand, REINFORCE is prone to local convergence and unstable performance during training. Neither trust region policy optimization, being computationally expensive, nor proximal policy optimization (PPO), suffering from aggregate constraint deviation, is a decent alternative for combinatory optimization problems with considerable individual subactions. We propose a trust region-navigated clipping policy optimization method for causal discovery that guarantees both better search efficiency and steadiness in policy optimization, in comparison with REINFORCE, PPO, and our prioritized sampling-guided REINFORCE implementation. On the other hand, to boost the efficient encoding of variables, we propose a refined graph attention encoder called SDGAT that can grasp more feature information without priori neighborhood information. With these improvements, the proposed method outperforms the former RL method in both synthetic and benchmark datasets in terms of output results and optimization robustness.

The incomplete and imperfect essence of the battlefield situation results in a challenge to the efficiency, stability, and reliability of traditional intention recognition methods. For this problem, we propose a deep learning architecture that consists of a contrastive predictive coding (CPC) model, a variable-length long short-term memory network (LSTM) model, and an attention weight allocator for online intention recognition with incomplete information in wargame (W-CPCLSTM). First, based on the typical characteristics of intelligence data, a CPC model is designed to capture more global structures from limited battlefield information. Then, a variable-length LSTM model is employed to classify the learned representations into predefined intention categories. Next, a weighted approach to the training attention of CPC and LSTM is introduced to allow for the stability of the model. Finally, performance evaluation and application analysis of the proposed model for the online intention recognition task were carried out based on four different degrees of detection information and a perfect situation of ideal conditions in a wargame. Besides, we explored the effect of different lengths of intelligence data on recognition performance and gave application examples of the proposed model to a wargame platform. The simulation results demonstrate that our method not only contributes to the growth of recognition stability, but it also improves recognition accuracy by 7%-11%, 3%-7%, 3%-13%, and 3%-7%, the recognition speed by 6- 32× , 4- 18× , 13-* × , and 1- 6× compared with the traditional LSTM, classical FCN, OctConv, and OctFCN models, respectively, which characterizes it as a promising reference tool for command decision-making.

Sequences play an important role in many engineering applications. Searching sequences with desired properties has long been an intriguing but also challenging research topic. This article proposes a novel method, called HpGAN, to search desired sequences algorithmically using generative adversarial networks (GANs). HpGAN is based on the idea of zero-sum game to train a generative model, which can generate sequences with characteristics similar to the training sequences. In HpGAN, we design the Hopfield network as an encoder to avoid the limitations of GAN in generating discrete data. Compared with traditional sequence construction by algebraic tools, HpGAN is particularly suitable for complex problems which are intractable by mathematical analysis. We demonstrate the search capabilities of HpGAN in two applications: 1) HpGAN successfully found many different mutually orthogonal complementary sequence sets (MOCSSs) and optimal odd-length binary Z-complementary pairs (OB-ZCPs) which are not part of the training set. In the literature, both MOCSSs and OB-ZCPs have found wide applications in wireless communications and 2) HpGAN found new sequences which achieve a four-times increase of signal-to-interference ratio-benchmarked against the well-known Legendre sequences-of a mismatched filter (MMF) estimator in pulse compression radar systems. These sequences outperform those found by AlphaSeq.

This article focuses on solving the problem of vibration attenuation of an Euler–Bernoulli beam system considering imprecise system parameters, asymmetric input saturation, and external period disturbance. By employing the backstepping technique, a kind of boundary control scheme composed of parameter adaptive laws and iterative learning terms is recommended to attenuate vibration for the flexible beam system. And a functional auxiliary system is devised to make up for the influence of input nonlinearity on the system. With the presented control scheme, the well-posedness of the beam system is proved via semigroup theory and the output signal is guaranteed bounded with the aid of rigorous Lyapunov analysis. Eventually, a simulation experiment is available in the MATLAB to expatiate on the suggested controllers’ availability and simulation diagrams also highlight that the boundary controller based on parameter adaptive law with iteration term shows better control performance than that without iteration terms.

Label-specific features serve as an effective strategy to learn from multi-label data with tailored features accounting for the distinct discriminative properties of each class label. Existing prototype-based label-specific feature transformation approaches work in a three-stage framework, where prototype acquisition, label-specific feature generation and classification model induction are performed independently. Intuitively, this separate framework is suboptimal due to its decoupling nature. In this paper, we make a first attempt towards a unified framework for prototype-based label-specific feature transformation, where the prototypes and the label-specific features are directly optimized for classification. To instantiate it, we propose modelling the prototypes probabilistically by the normalizing flows, which possess adaptive prototypical complexity to fully capture the underlying properties of each class label and allow for scalable stochastic optimization. Then, a label correlation regularized probabilistic latent metric space is constructed via jointly learning the prototypes and the metric-based label-specific features for classification. Comprehensive experiments on 14 benchmark data sets show that our approach outperforms the state-of-the-art counterparts.

Binary neural networks (BNNs) constrain weights and activations to +1 or -1 with limited storage and computational cost, which is hardware-friendly for portable devices. Recently, BNNs have achieved remarkable progress and been adopted into various fields. However, the performance of BNNs is sensitive to activation distribution. The existing BNNs utilized the Sign function with predefined or learned static thresholds to binarize activations. This process limits representation capacity of BNNs since different samples may adapt to unequal thresholds. To address this problem, we propose a dynamic BNN (DyBNN) incorporating dynamic learnable channel-wise thresholds of Sign function and shift parameters of PReLU. The method aggregates the global information into the hyper function and effectively increases the feature expression ability. The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs. The DyBNN based on two backbones of ReActNet (MobileNetV1 and ResNet18) achieve 71.2% and 67.4% top1-accuracy on ImageNet dataset, outperforming baselines by a large margin (i.e., 1.8% and 1.5% respectively).

We focus on federated learning in practical recommender systems and natural language processing scenarios. The global model for federated optimization typically contains a large and sparse embedding layer, while each client’s local data tend to interact with part of features, updating only a small submodel with the feature-related embedding vectors. We identify a new and important issue that distinct data features normally involve different numbers of clients, generating the differentiation of hot and cold features. We further reveal that the classical federated averaging algorithm (FedAvg) or its variants, which randomly selects clients to participate and uniformly averages their submodel updates, will be severely slowed down, because different parameters of the global model are optimized at different speeds. More specifically, the model parameters related to hot (resp., cold) features will be updated quickly (resp., slowly). We thus propose federated submodel averaging (FedSubAvg), which introduces the number of feature-related clients as the metric of feature heat to correct the aggregation of submodel updates. We prove that due to the dispersion of feature heat, the global objective is ill-conditioned, and FedSubAvg works as a suitable diagonal preconditioner. We also rigorously analyze FedSubAvg’s convergence rate to stationary points. We finally evaluate FedSubAvg over several public and industrial datasets. The evaluation results demonstrate that FedSubAvg significantly outperforms FedAvg and its variants.

Human–computer interaction cognitive behavior (HCICB) modeling faces four deficiencies: 1) lack of a standard framework model; 2) large simulation error; 3) single simulation dimension; and 4) lack of a simulation software. To solve these deficiencies, we have carried out work in four aspects. First, we construct an HCICB model with the user, system device, and environment as the core elements, which provides a unified framework for the subsequent HCICB modeling in the Military Internet of Things (MIoT) command and control (C2) system. Second, we correct visual and motion parameters in the adaptive control of thought rational module of the Cogtool model by the commander in the loop (CIL) experiment. Third, we construct a mental workload (MW) prediction model of the MIoT C2 system based on improved visual auditory cognitive psychomotor, which realizes fast, high-precision, and quantitative MW prediction. It is added as a simulation dimension for the HCICB. Fourth, we develop MwCogtool, an HCICB prediction software that can rapidly simulate typical tasks at the design and usage stages of the MIoT C2 system, and also can output six parameters, including task completion time (TCT), MW, eye movement prepare time, eye movement execution time, motion time, and cognitive time in the whole process quickly and visually. In addition, we select 20 real users and 9 typical tasks of the MIoT C2 system to carry out the CIL verification experiment. Compared with Cogtool, MwCogtool reduces the maximum simulation error in TCT of the C2 system from 45.00% to 5.58%. The consistency of simulation results with real user data reaches 0.99. The results of the MW prediction model can significantly and negatively predict the change of real users’ eye movement, and can accurately predict the trend of MW change. Simultaneously, we build a fitting model between the mean MW prediction value and eye movement parameters.

A key problem in traffic management is to schedule the movements of vehicles to reduce unnecessary costs; this issue has arisen in applications such as train schedule management, air-traffic control, and urban traffic management. This problem can be modeled as a job shop scheduling problem (JSSP), which is an important combinatorial optimization problem that is widely applied in real-world scenarios. However, designing good approximation algorithms for JSSPs often requires significant specialized knowledge and trial-and-error. In this paper, we present an end-to-end framework for solving JSSPs by using graph neural networks (GNNs) and deep Q-Learning. This single-policy model is suitable for solving instances that have similar sizes and is trained only by observing reward signals and following feasible rules. The trained model behaves like a constructive heuristic algorithm that incrementally constructs a solution, and each action is determined by the output of a GNN, which captures the current state of the partial solution. We test the proposed approach on JSSP instances with multiple sizes and demonstrate its competitive performance in all cases (after training). Our proposed framework also has the potential to be applied to other JSS subproblems.

Quasi-complementary sequence sets (QCSSs) can be seen as a generalized version of complete complementary codes (CCCs), which enables multicarrier communication systems to support more users. The contribution of this work is two-fold. First, we propose a systematic construction of Florentine rectangles. Secondly, we propose several sets of CCCs and QCSSs, using Florentine rectangles. The CCCs and QCSSs are constructed over$\mathbb {Z}_{N}$, where$N\geq 2$is any integer. The cross-correlation magnitude of any two of the constructed CCCs is upper bounded by$N$. By combining the proposed CCCs, we propose asymptotically optimal and near-optimal QCSSs with new parameters.

With the more extensive application of flexible robots, the expectation for flexible manipulators is also increasing rapidly. However, the fast convergence will cause the increase of vibration amplitude to some extent, and it is difficult to obtain vibration suppression and satisfactory transient performance at the same time. In order to deal with the problem, a fixed-time learning control method is proposed to realize the fast convergence. The constraint on system outputs, system uncertainty, and input saturation is addressed under the fixed-time convergence framework. A novel adaptive law for neural networks is integrated into the backstepping method, which enhances the learning rate of neural networks. The imposed constraint on the vibration amplitude is guaranteed by using the barrier Lyapunov function (BLF). Moreover, the chattering problem is addressed by approximating the sign function smoothly. In the end, some simulations have been carried out to show the effectiveness of the proposed method.

In this article, vibration abatement problems of a riser system with system uncertainty, input deadzone, and output constraint are considered. For obtaining better control precision, a boundary control law is constructed by employing the backstepping method and Lyapunov's theory. The output constraint is guaranteed by utilizing a barrier Lyapunov function. Adaptive neural networks are designed to cope with the uncertainty of the riser and compensate for the effect caused by the asymmetric deadzone nonlinearity. With the designed controller, the output constraint is satisfied, and the system stability is guaranteed through Lyapunov synthesis. In the end, numerical simulation results are provided to display the performance of the developed adaptive neural network boundary control law.

Human-robot co-transportation allows for a human and a robot to perform an object transportation task cooperatively on a shared environment. This range of applications raises a great number of theoretical and practical challenges arising mainly from the unknown human-robot interaction model as well as from the difficulty of accurately model the robot dynamics. In this article, an adaptive impedance controller for human-robot co-transportation is put forward in task space. Vision and force sensing are employed to obtain the human hand position, and to measure the interaction force between the human and the robot. Using the latest developments in nonlinear control theory, we propose a robot end-effector controller to track the motion of the human partner under actuators' input constraints, unknown initial conditions, and unknown robot dynamics. The proposed adaptive impedance control algorithm offers a safe interaction between the human and the robot and achieves a smooth control behavior along the different phases of the co-transportation task. Simulations and experiments are conducted to illustrate the performance of the proposed techniques in a co-transportation task.

Local planning is one of the key technologies for mobile robots to achieve full autonomy and has been widely investigated. To evaluate mobile robot local planning approaches in a unified and comprehensive way, a mobile robot local planning benchmark called MRPB 1.0 is newly proposed in this paper. The benchmark facilitates both motion planning researchers who want to compare the performance of a new local planner relative to many other state-of-the-art approaches as well as end users in the mobile robotics industry who want to select a local planner that performs best on some problems of interest. We elaborately design various simulation scenarios to challenge the applicability of local planners, including large-scale, partially unknown, and dynamic complex environments. Furthermore, three types of principled evaluation metrics are carefully designed to quantitatively evaluate the performance of local planners, wherein the safety, efficiency, and smoothness of motions are comprehensively considered. We present the application of the proposed benchmark in two popular open-source local planners to show the practicality of the benchmark. In addition, some insights and guidelines about the design and selection of local planners are also provided. The benchmark website [1] contains all data of the designed simulation scenarios, detailed descriptions of these scenarios, and example code.

Since its inception in 2013, Golay complementary sequences with periodic zero autocorrelation zones (ZACZs) and cross-correlation zones (ZCCZs), or Golay-ZCZ (zero correlation zone) sequences have special importance in modern communication systems. Till date, all the proposed complementary sequences with periodic ZACZs and ZCCZs have lengths in the form$2^{m}$, where$m$is a natural number. In this paper, we extend such complementary sequences with large periodic ZACZs and ZCCZs to more flexible lengths in the form of non-power-of-two.

Reinforcement learning, as an effective method to solve complex sequential decision-making problems, plays an important role in areas such as intelligent decision-making and behavioral cognition. It is well known that the sample experience replay mechanism contributes to the development of current deep reinforcement learning by reusing past samples to improve the efficiency of samples. However, the existing priority experience replay mechanism changes the sample distribution in the sample set due to the higher sampling frequency assigned to a specific transition, and it cannot be applied to actor-critic and other on-policy reinforcement learning algorithm. To address this, we propose an adaptive factor based on TD-error, which further increases sample utilization by giving more attention weight to samples of larger TD-error, and embeds it flexibly into the original Deep Q Network and Advantage Actor-Critic algorithm to improve their performance. Then we carried out the performance evaluation for the proposed architecture in the context of CartPole-V1 and 6 environments of Atari game experiments, respectively, and the obtained results either on the conditions of fixed temperature or annealing temperature, when compared to those produced by the vanilla DQN and original A2C, highlight the advantages in cumulative rewards and climb speed of the improved algorithms.

Recently, mutually orthogonal complementary sequence sets (MOCSSs) have been found many important applications in communication systems, radar, etc. Most of the known constructions of MOCSSs are based on generalized Boolean functions (GBFs) and hence mostly have lengths of power-of-two. A few constructions of MOCSSs are also based on paraunitary (PU) matrices and hence mostly have power-of-an-integer lengths. The objective of this paper is to develop a general framework to construct more MOCSSs consisting of sequences with non-power-of-two lengths. The proposed framework is based on complete complementary codes and even-shift complementary sequence sets.

Grasping the dynamics of crime situation is a long standing but significant problem and plays an instructive role in the field of security and protection. Traditional methods approach the crime forecasting via stochastic equations based on physics or statistics, which may be interpretable but less efficient in real applications. Recently, some data-driven models, especially sequence generative networks, seem to be promising in capturing spatio-temporal dynamics with massive dataset available. In this paper, we process some regional crime dataset of recent fifteen years in the crime situation awareness graphs and learn latent representations with variational auto-encoder. And then Crime Generative Adversarial Network (Crime-GAN) is formulated as a new crime forecasting model for four types of crime, integrating sequence to sequence structure and Wasserstein adversarial loss. In comparison to other typical algorithms, such as Conv-RNN, Crime-GAN shows superior forecasting performance for multi-type crime in spatio-temporal scale.