Federated learning is a distributed machine-learning technique that allows multiple clients to collaboratively train a model without sharing their local raw data. In existing federated learning solutions, one-shot federated learning is a promising yet challenging direction. It involves model training with just one round of communication between clients and the server, reducing communication overheads and security risks. However, most existing methods still face several challenges. First, generating additional data for training prolongs the model training time. Second, the traditional single model cannot handle data heterogeneity in real world scenarios. To address these issues, this article proposes a personalized federated learning method called FedOM under the one-communication premise. Considering the high data heterogeneity, FedOM abandons the traditional single global model architecture and generates multiple group models to overcome the generalization limitations of a single model. Additionally, based on FedOM, this study proposes FedOMF, a personalized method with a fine-tuning module. Experiments on public datasets show that in highly heterogeneous data scenarios, the proposed methods outperform baseline methods, demonstrating superior performance and great practical potential.

Existing decision-making models are generally based on the classical normative paradigm, which seldom considers the limited cognitive and environmental resources of humans when making decisions in real environments. We draw on the theory of Artificial General Intelligence technology, Non-Axiomatic Reasoning System and heuristic-primed decision-making processes of psychology to propose a heuristic-primed decision-making model under the assumption of bounded resources. Firstly, we propose a spreading activation belief network based on experience-grounded semantics, which takes concepts as nodes and semantic relevance as edges, and changes the weights of logical reasoning links according to the evidence presented using multiple inferences rules so as to achieve the self-organization of its network topology. Next, multiple dynamically changing and conflicting goals are represented by a Non-Axiomatic Logic statement with two-dimensional desire-values. Finally, a controlled concurrent heuristic algorithm that can dynamically allocate limited computational resources and perform multiple inferences is proposed.

In the field of flexible electronics, traditional composite copper foils generally suffer from weak interfacial adhesion between the copper layer and polymer substrate, poor corrosion resistance, insufficient surface uniformity, and limited functional adaptability. To address these issues, Cu/Cu-CeO₂ composite coatings were deposited on polyimide (PI) substrates via PVD magnetron sputtering using argon as the working gas, aiming to enhance the comprehensive properties of composite copper foils, including interfacial bonding strength and corrosion resistance. Initially, pure Cu coatings were deposited on polyimide (PI), polyethylene terephthalate (PET), and polypropylene (PP) substrates. The deposition parameters were optimized through orthogonal and single-factor experiments, and the optimal process combination was determined as follows: PI substrate, sputtering time of 20 min, sputtering power of 60 W, and argon flow rate of 90 sccm, which achieved a balance between mechanical and electrical properties. Subsequently, comparative studies of Ar plasma treatment (100 s, 200 s, 300 s, and 400 s) and NaOH chemical etching (0 mol/L, 1 mol/L, 2 mol/L, and 3 mol/L) were conducted on the three polymer substrates. Comprehensive analyses of water contact angle, surface energy, bonding strength, and surface roughness demonstrated that the PI substrate treated with Ar plasma for 300 s exhibited superior overall performance, with a water contact angle of 48.5°, surface energy of 61.78 × 10⁻³ J/m², bonding strength of 4.56 N, and surface roughness of 0.89 μm. On this basis, the performance of pure Cu coatings and Cu/Cu-CeO₂ composite coatings prepared under different CeO₂ sputtering powers (20 W, 30 W, 40 W, and 50 W) was further investigated. Combined analyses of SEM, EDS, and XPS characterizations, together with bonding strength, resistivity, electrochemical impedance spectroscopy, polarization curves, and corrosion morphology tests, revealed that the Cu/Cu-CeO₂ composite coating prepared at a sputtering power of 50 W exhibited superior overall performance in terms of interfacial bonding strength and corrosion resistance.

As people become increasingly reliant on the Internet, securely storing and publishing private data has become an important issue. In real life, the release of graph data can lead to privacy breaches, which is a highly challenging problem. Although current research has addressed the issue of identity disclosure, there are still two challenges: First, the privacy protection for large-scale datasets is not yet comprehensive; Second, it is difficult to simultaneously protect the privacy of nodes, edges, and attributes in social networks. To address these issues, this paper proposes a $(k,\ t)$-graph anonymity algorithm based on enhanced clustering. The algorithm uses $k$-means++ clustering for $k$-anonymity and $t$-closeness to improve $k$-anonymity. We evaluate the privacy and efficiency of this method on two datasets and achieved good results. This research is of great significance for addressing the problem of privacy breaches that may arise from the publication of graph data.

To address the challenges of formation maintenance, collision avoidance, and cooperative navigation for multi-agent systems in shared environments, a spatio-temporal trajectory optimization method under global structural constraints and A attention-enhanced graph neural network (AE-GNN)-based cooperative navigation strategy are proposed. First, a differentiable formation similarity metric based on graph Laplacian theory is constructed to characterize the intrinsic geometric structure of formations, which is invariant to translation, rotation, and scale transformations. Based on this metric, a distributed trajectory optimization framework is developed by jointly considering formation maintenance, obstacle avoidance, inter-agent collision avoidance, and trajectory smoothness. Furthermore, an adaptive formation constraint adjustment mechanism based on environmental passage margin is introduced, allowing agents to relax rigid formation constraints in narrow passages and gradually recover the desired formation after obstacle avoidance. To improve cooperative decision-making in densely cluttered environments, an AE-GNN navigation method is proposed, where an attention mechanism dynamically assigns higher weights to critical neighboring agents during feature aggregation, enhancing cooperative information interaction and collision avoidance capability. Simulation and physical experiments validate the effectiveness of both proposed methods. The trajectory optimization method achieves a success rate of 97.5% in dense-obstacle formation-navigation simulations, while AE-GNN demonstrates effective cooperative navigation and collision avoidance in multi-agent scenarios.