Algorithmic trading relies on machine learning models to make trading decisions. Despite strong in-sample performance, these models often degrade when confronted with evolving real-world market regimes, which can shift dramatically due to macroeconomic changes—e.g., monetary policy updates or unanticipated fluctuations in participant behavior. We identify two core challenges that perpetuate this mismatch: (1) insufficient robustness in existing policy against uncertainties in high-level market fluctuations, and (2) the absence of a realistic and diverse simulation environment for training, leading to policy overfitting. To address these issues, we propose a Bayesian Robust Framework that systematically integrates a macro-conditioned generative model with robust policy learning. On the data side, to generate realistic and diverse data, we propose a macro-conditioned GAN-based generator that leverages macroeconomic indicators as primary control variables, synthesizing data with faithful temporal, cross-instrument, and macro correlations. On the policy side, to learn robust policy against market fluctuations, we cast the trading process as a two-player zero-sum Bayesian Markov game, wherein an adversarial agent simulates shifting regimes by perturbing macroeconomic indicators in the macro-conditioned generator, while the trading agent—guided by a quantile belief network—maintains and updates its belief over hidden market states. The trading agent seeks a Robust Perfect Bayesian Equilibrium via Bayesian neural fictitious self-play, stabilizing learning under adversarial market perturbations. Extensive experiments on 9 financial instruments demonstrate that our framework outperforms 9 state-of-the-art baselines. In extreme events like the COVID pandemic, our method shows improved profitability and risk management, offering a reliable solution for trading under uncertain and rapidly shifting market dynamics.

Neural architecture search-based multi-modal classification (NAS-MMC) aims to automatically find optimal network structures for improving the multi-modal classification performance. However, most current NAS-MMC methods are quite time-consuming during the training process. In this paper, we propose a knowledge sharing-based neural architecture search (KS-NAS) method for multi-modal classification. The KS-NAS optimizes the search process by introducing a dynamically updated knowledge base to reduce the consumption of computational resource. Specifically, during the deep evolutionary search, individuals in the initial population acquire initial parameters from a knowledge base, and then undergo training and optimization until convergence is reached, avoiding the need for training from scratch. The knowledge base is dynamically updated by aggregating the parameters of high-quality individuals trained within the population, thus progressively improving the quality of the knowledge base. As the population evolves, the knowledge base continues to optimize, ensuring that subsequent individuals can obtain higher-quality initialization parameters, which significantly accelerates the training speed of the population. Experimental results show that the KS-NAS method achieves state-of-the-art results in terms of classification performance and training efficiency across multiple popular multi-modal tasks.

Summary Matrix factorization (MF)‐based recommender systems (RSs) as black‐box models fail to provide explanations for the recommended items. While some models attain a degree of explainability by integrating neighborhood algorithms, which compute explainability based on the preferences of proximate users, they overlook the contribution of the subjective preferences of the target user to enhancing model explainability, resulting in suboptimal model explainability. To address this problem, an explainable RS directed by reconstructed explanatory factors and multi‐modal matrix factorization (ERS‐REFMMF) is proposed. By integrating users' subjective sentiment and preference features into the rating matrix to form a multi‐modal matrix, ERS‐REFMMF utilizes the Funk‐singular value decomposition method at the foundational layer to decompose the multi‐modal matrix and generate a candidate item set. At the upper layer, explainability is constructed based on the target user's subjective preferences and latent features derived from MF, and the final recommended list is optimized for accuracy, diversity, novelty, and explainability through multi‐objective optimization algorithms. ERS‐REFMMF models around users' explicit preferences and latent associations, reconstructs explainability with hybrid factors, and enhances overall performance through a many‐objective optimization algorithm. Experimental results on real datasets demonstrate that the proposed model is competitive in both phases compared to existing recommendation methods.

Summary With the rising adoption of the Internet of Things (IoT) across a variety of industries, malware is increasingly targeting the large number of IoT devices that lack adequate protection. Malware hunting is challenging in the IoT due to the variety of instruction set architectures of devices, as shown by the differences in the relevant characteristics of malware on different platforms. There are also serious concerns about resource utilization and privacy leaks in the development of conventional detection models. This study suggests a novel federated malware detection framework based on many‐objective optimization (FMDMO) for the IoT to overcome the problems. First, the framework provides a cross‐platform compatible basis with the federated mechanism as the backbone, while avoiding raw data sharing to improve privacy protection. Second, an intelligent optimization‐based client selection method is designed for four objectives: learning performance, architectural selection deviation, time consumption, and training stability, which leads malware detection to retain a high degree of cross‐architectural generalization while enhancing training efficiency. Based on a large IoT malware dataset we constructed, containing 62,515 malware samples across seven typical architectures, the FMDMO is evaluated comprehensively in three scenarios. The experimental results demonstrate the FMDMO substantially enhances the model's cross‐platform detection performance while preserving effective training and flexibility.

Stable operation of IoT systems in extreme environments is critical for infrastructures, including energy, aerospace, and healthcare. But resource-constrained devices are vulnerable to malware exploiting known weaknesses due to complex operating conditions and low-frequency device maintenance, and systems are at serious risk of failure or information leakage. However, automated security defense based on machine learning faces the challenges of low cross-architectural generalization and multidimensional data imbalance. We propose a many-objective-optimization-driven data balancing strategy for cross-architectural malware classification (MODSC) to address the above issues. MODSC constructs the optimization problem model for data balancing strategy search based on data set information, which focuses on rebalancing the data space in different dimensions, including category distribution and architectural distribution. The many-objective evolutionary algorithm (MaOEA-PBF), guided by the performance balance function, is then designed to solve the above model. The MODSC framework was tested on a group of IoT malware data sets with stepped imbalance rates containing six common architectures. The experimental results show that MODSC can both steadily and effectively improve cross-architectural generalization while maintaining a high level of confidence compared to popular data processing methods.

Summary With the rapid development of big data, the explosive growth of data promotes the progress of the Internet of Things (IoT). Because it is hard for traditional cloud computing to meet vast computing tasks, scholars propose mobile edge computing (MEC) for the IoT. However, the mobility of users results in the instability of MEC performance. Besides, the conflict of interest between users and service providers needs to be balanced. To solve these problems, this paper constructs a virtual machine migration model based on many‐objective optimization (MaOVMMM). In MaOVMMM, four objectives are considered simultaneously: communication expense, computing expense, delay, and energy consumption. A many‐objective evolutionary algorithm with double population confrontation (MaOEA‐DPC) is suggested to support the MaOVMMM that is proposed. First, the population confrontation strategy is designed to better simulate the relationship between users and service providers. Second, the dynamic probability integration selection strategy is used to ensure the evolution ability of the algorithm. Simulation results demonstrate the effectiveness and superiority of MaOEA‐DPC when compared with other algorithms. This proposed approach can provide a superior virtual machine migration scheme for decision‐makers.

Summary In many‐objective optimization algorithms, it is very important to maintain significant convergence and diversity of the population. And with the increasing demand in various fields, the optimization problem also becomes gradually complicated. Some existing many‐objective optimization algorithms are faced with challenges such as domination resistance and dimensional crisis. To solve these challenges, a many‐objective optimization algorithm based on dual criteria and mixed distribution correction strategy (MaOEA‐CSMDC) is proposed in this paper. To be specific, a matching selection strategy based on dual criteria combined by pareto domination strategy and achievement scalar function, which alleviates the domination resistance phenomenon and enhances the selection pressure of the algorithm. After that, an environment selection strategy based on equal probability mixed distribution correction is designed to better balance convergence and diversity. In this strategy, normal distribution, exponential distribution, and Cauchy distribution are introduced to adjust the weight of convergence and diversity in evolution by means of equal probability, so as to alleviate the problem that the conflict between them is intensified in the later stage of the algorithm. The experimental results show that, MaOEA‐CSMDC not only has advantages in convergence and diversity indicators, but also is more competitive in solving many‐objective optimization problems.

The rapid progress of artificial intelligence expands its wide applicability in Internet of Things (IoT). Meanwhile, data insufficient and data source privacy are key supply chain challenges facing IoT especially in the healthcare industry. To address this problem in healthcare IoT, in this article, we propose a skin cancer detection model based on federated learning integrated with deep generation model. First, we employ dual generative adversarial networks to address the problem of insufficient data. In addition, to improve the quality of generated images, we synchronously optimize the sharpness of images, Frechet inception distance, image diversity, and loss using knee point-driven evolutionary algorithm (KnEA). Then, we protect patient information privacy by training federated skin cancer framework. Finally, we employ the ISIC 2018 dataset to test the performance of the proposed training model under different situations, including using identically distributed data, nonidentically distributed data, a sparse convolutional neural network, and a fully connected convolutional neural network. The experiment results demonstrate that the accuracy and area under the curve reach 91% and 88%, respectively. This model can help resolve problems of insufficient data in smart medicine of IoT and protect the privacy of user data while also providing an excellent detection rate.

Summary At present, irrelevant or redundant features in network traffic data occupy a lot of storage and computing resources, reducing the accuracy of network anomaly detection. Aiming at this problem, a many‐objective feature selection model is proposed in this article. The model takes the number of selected feature, false alarm rate, detection rate, precision and accuracy as the optimization objectives, and characterizes the performance of the feature selection method from different perspectives. At the same time, a many‐objective integration optimization algorithm (IN‐MaOEA) is designed to solve this model. First, the algorithm will build the evolution strategy pool and the dominance strategy pool, then a random probability strategy selection mechanism is designed to improve the algorithm's convergence and diversity. At the same time, an anomaly detection simulation was performed using the NSL‐KDD dataset. Experimental results show that the IN‐MaOEA algorithm can effectively improve the performance of detection.