Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context algorithm have shown strong performance and efficiency. However, inappropriate preference representations and training with imbalanced reward scores limit the performance of such algorithms. In this work, we introduce ParetoHqD that addresses the above issues by representing human preferences as preference directions in the objective space and regarding data near the Pareto front as ''high-quality'' data. For each preference, ParetoHqD follows a two-stage supervised fine-tuning process, where each stage uses an individual Pareto high-quality training set that best matches its preference direction. The experimental results have demonstrated the superiority of ParetoHqD over five baselines on two multiobjective alignment tasks.

This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is composed of finite number of arms and plays. Each arm has a stochastic number of capacities, and each unit of capacity is associated with a reward function. Each play is associated with a priority weight. When multiple plays compete for the arm capacity, the arm capacity is allocated in a larger priority weight first manner. Instance independent and instance dependent regret lower bounds are proved, revealing the impact of model parameters on the hardness of learning the optimal allocation policy. When model parameters are given, we design an algorithm named MSB-PRS-OffOpt to locate the optimal play allocation policy with a polynomial computational complexity in the number of arms and plays. Utilizing MSB-PRS-OffOpt as a subroutine, an approximate upper confidence bound (UCB) based algorithm is designed, which has instance independent and instance dependent regret upper bounds matching the corresponding lower bound up to acceptable factors. To this end, we address nontrivial technical challenges arising from optimizing and learning under a special nonlinear combinatorial utility function induced by the prioritized resource sharing mechanism.

Recently, some studies have shown that the popular large-scale multiobjective optimization problem (LSMOP) test suite cannot fairly test the performance of algorithms due to the specificity of its Pareto solution set position. Specifically, some large-scale multiobjective evolutionary algorithms (LSMOEAs) have achieved completely opposite (poor) performance on the GLSMOP test suite (the LSMOP test suite with generic Pareto solution sets). Since many real-world LSMOPs are computationally expensive, several surrogate-assisted LSMOEAs are developed and their effectiveness is verified on the LSMOP test suite. Motivated by the above, we aim to study the performance of those surrogate-assisted LSMOEAs on the GLSMOP test suite in this work. Firstly, we elaborate on the existing surrogate-assisted LSMOEAs for solving the expensive LSMOPs from different perspectives. Secondly, the basic formulation of the GLSMOP test suite and its difference from the original LSMOP test suite are shown. Finally, the performance of six surrogate-assisted LSMOEAs on the GLSMOP test suite is systematically tested. According to the experimental results, we give the current best algorithmic structure for handling expensive LSMOPs: using a decomposition-based framework, using differential evolution to search the original decision space, and fitting a scalarization function with the surrogate model. The proposed algorithmic structure is simple but is expected to guide the design of effective surrogate-assisted LSMOEAs.

High-fidelity electromagnetic simulation-driven optimization are crucial in modern antenna design. However, many antenna optimization models involve multiple expensive constraints, which can be formulated as expensive constrained optimization problems (ECOPs). Currently, surrogate-assisted evolutionary algorithms are widely used to solve ECOPs. However, existing methods face significant challenges in addressing errors in constraint surrogate models and the strong conflicts among constraints and the objective, making it difficult to find feasible solutions with optimal objective value within a limited number of simulations. We propose a parallel surrogate-assisted multiple penalties search method for simulation-driven antenna design problems with expensive conflicting constrains. In the proposed method, a multi-penalty function search mechanism is designed, followed by an adaptive parallel sampling approach to collect multiple samples for the parallel simulation. The experimental results applied to the design of the three-layer filtering antenna demonstrate the effectiveness and great potential of the proposed method in addressing simulation-driven antenna design problems with expensive conflicting constrains.

Large-scale multiobjective binary optimization problems (MBOPs) often occur in real-world applications, where the function evaluation can only be performed through computationally expensive simulations, which renders standard exact and heuristic methods ineffective. Aggregation-based surrogate-assisted multiobjective evolutionary algorithms have been developed and shown to be promising for solving such problems. They define a set of uniformly distributed weight vectors as search directions, on which all search resources are placed to perform the evolution. However, the Pareto fronts of large-scale MBOPs are discrete and nonuniform. As a result, many weight vectors are useless, thus a lot of search resources are wasted. To address this challenge, we propose a surrogate-assisted neighborhood search (SANS) for expensive large-scale multiobjective binary optimization. SANS uses only a few weight vectors to save search resources while maintaining an adequate diversity. To further utilize the limited search resources, a Q-learning-based method is designed to dynamically allocate search resources to weight vectors. Furthermore, a surrogate-assisted variable neighborhood search is developed to speed up the search without getting trapped in a local optimum prematurely. To robustly and reliably predict the quality of the found solutions, global and local surrogate models are trained by different training samples and then work collaboratively. The experimental results have demonstrated the superiority of SANS over seven state-of-the-art algorithms on the MBOPs with up to 1000 decision variables using only 500 real solution evaluations.

Monitoring aerosols over the oceans is critical for understanding Earth’s climate and air quality. Although polarization can substantially reduce uncertainty in aerosol retrievals, current algorithms rely mainly on multi-view polarimeters, and no dedicated algorithm is available for single-view polarimeters over the ocean. Here, we present the first ocean algorithm for a spaceborne single-view polarimeter, demonstrated with the Particulate Observing Scanning Polarimeter (POSP) onboard the GF-5(02) satellite. Our algorithm combines multi-spectral polarization with machine-learning-accelerated radiative transfer calculation and seasonally clustered global aerosol models. Validation with AErosol RObotic NETwork (AERONET) and Maritime Aerosol Network (MAN) data demonstrates high accuracy, with RMSEs of 0.061, 0.479, and 0.037 for AOD550, AE670-870, and SSA550using AERONET, and 0.030 and 0.259 for AOD550and AE670-870using MAN, respectively. Comparison with retrievals from the Generalized Retrieval of Atmosphere and Surface Properties (GRASP) algorithm confirms that our algorithm performs comparably to GRASP products. These results underscore the necessity and feasibility of developing specialized aerosol retrieval algorithms for single-view polarimeters, and pave the way for global aerosol over the ocean monitoring.

Reposting plays an essential role in boosting visibility on online social networks (OSNs). In this paper, we study the problem of designing “reposting service” in an OSN to incentivize “transactions” between requesters (users who seek to enhance visibility) and suppliers (users who are willing to repost if certain incentives are given), and maximize the welfare increase accumulated through a given time horizon. We formulate a mathematical model for reposting which captures various factors like click-through rates (CTRs), requesters’ valuations and suppliers’ costs. We formulate the problem of maximizing the welfare increase via judiciously assigning suppliers to requesters from two aspects: (a) “user-centric” and (b) “platform-centric”. The user-centric aspect deals with situations where requesters and suppliers collaborate and share valuations and costs. To address the challenge of unknown CTRs, we propose an online learning protocol and achieve a sub-linear regret. The platform-centric aspect corresponds to the scenario where users keep their valuations or costs private. To address the challenges of unknown CTRs, valuations and costs, we design an “explore-then-commit” online protocol. We prove the truthfulness of the proposed online protocol, and we also prove that this protocol has a sub-linear regret. Lastly, we conduct extensive experiments on six public datasets to evaluate the effectiveness and scalability of the proposed protocols.

In recent years, the research on large-scale mul-tiobjective optimization has attracted much attention. Many competitive large-scale multiobjective evolutionary algorithms have been proposed. Usually, their performance is evaluated on the widely used large-scale multiobjective test suite (i.e. LSMOP test suite). Those algorithms often exhibit a strong convergence capability on the instances of LSMOP test suite. The purpose of this study is to show our concern that the development of algorithms may be over specialized for the LSMOP test suite. We first explain some issues in the original LSMOP test suite. Then, we propose a general LSMOP test suite (termed GLSMOP), in which the Pareto set has a more general structure in the decision space. Experimental results on two test suites suggest that the performance of some large-scale multiobjective evolutionary algorithms will be deteriorated rapidly by the change of Pareto set. It also reveals the good performance of MOEAID-DE on large-scale multiobjective optimization problems.

User-centric selection problems arise from mobile edge computing systems, ride-sharing applications, etc. Novel variants of the multi-play multi-armed bandit model are proposed to balance the exploration vs. exploitation tradeoff of user-centric selection problems. Two significant limitations of these variants are: (1) all plays must be assigned; (2) full feedback on the resource is required. This paper relaxes these two assumptions by assigning a subset of plays and capturing bandit feedback on the resource. We show that under this relaxation of assumptions, previous algorithms have a linear regret, i.e., failing to learn the optimal decision. We design a Thompson sampling type algorithm called USP-TS for this relaxation and prove it has a sub-linear regret. To attain a better exploration vs. exploitation tradeoff, we design a variant of the USP-TS called USP-TS-AER, which is tailored for the structure of bandit feedback on the resource. Extensive experiments validate the superior performance of USP-TS against various baselines and that USP-TS-AER can reduce the regret of USP-TS by as much as 50%.

Bacteriophages are the viruses that infect bacterial cells. They are the most diverse biological entities on earth and play important roles in microbiome. According to the phage lifestyle, phages can be divided into the virulent phages and the temperate phages. Classifying virulent and temperate phages is crucial for further understanding of the phage-host interactions. Although there are several methods designed for phage lifestyle classification, they merely either consider sequence features or gene features, leading to low accuracy. A new computational method, DeePhafier, is proposed to improve classification performance on phage lifestyle. Built by several multilayer self-attention neural networks, a global self-attention neural network, and being combined by protein features of the Position Specific Scoring Matrix matrix, DeePhafier improves the classification accuracy and outperforms two benchmark methods. The accuracy of DeePhafier on five-fold cross-validation is as high as 87.54% for sequences with length >2000bp.

When the elderly have a working memory burden, the cognitive burden can be transferred to mobile touch devices. However, the decline of physical function and cognitive ability affects the ability of the elderly to interact with mobile devices. Optimizing the interaction of mobile touch devices is one of the effective ways to reduce the cognitive burden of the elderly. This study intended to investigate the effects of the input and feedback methods on mobile touch devices on cognitive offloading behaviors in older adults. The experiment adopts a 3 × 3 within-subject design, and the independent variables include 3 input methods (mouse, direct touch, and stylus) and 3 feedback methods (visual feedback, auditory feedback, and combined audiovisual feedback). Thirty elderly participants were invited to complete a visual working memory test and subjective preference questionnaires. The results of the study show that (i) the input methods have a significant effect on the cognitive offloading of the elderly, who, under the stylus condition, have the most offloaded working memory and lower cognitive load; (ii) the feedback methods have a significant effect on the cognitive offloading of the elderly, among which they, under the combined visual and auditory feedback, offload working memory more frequently and have lower cognitive load; and (iii) in terms of subjective evaluation, both the input and feedback methods affect the satisfaction of the elderly: among the 3 input methods, the elderly displayed the highest satisfaction with the stylus, and among the 3 feedback methods, the elderly have the highest satisfaction with the combined audio-visual feedback. Studies have shown that the input and feedback methods of mobile touch devices are important factors affecting the cognitive offloading behavior and subjective evaluation of the elderly. The conclusions of this research provide an important reference for designing interactive methods suitable for the elderly.

Recently, a number of evolutionary algorithms (EAs) have been proposed for large-scale multiobjective optimization. Among them, due to the high efficiency, the problem reformulation-based large-scale multiobjective optimization framework (LSMOF) has shown to be promising. By associating the weight variables with a set of specific bi-directional vectors representing search directions, LSMOF reformulates the original large-scale multiobjective optimization problem (LSMOP) into a low-dimensional single-objective optimization problem (SOP). For the reformulated SOP, the weight variables are as the decision vector and the hypervolume is as the objective. In many recently proposed competitive EAs for large-scale multiobjective optimization, the promising search directions are also specified similar to the bi-directional vectors of LSMOF. The aim of this paper is to point out some challenges in the construction of bi-directional vectors in LSMOF. We first verify that the lower and upper boundary points from which the bi-directional vectors are generated are crucial to the good performance of LSMOF on the LSMOP test suite. Then, for demonstrating how LSMOF performs when the Pareto set (PS) is changed, a new test suite is designed. The experimental results show that the performance of LSMOF will deteriorate rapidly on the problems with the new PS.

Real-world industrial engineering optimization problems often have a large number of decision variables. Most existing large-scale evolutionary algorithms (EAs) need a large number of function evaluations to achieve high-quality solutions. However, the function evaluations can be computationally intensive for many of these problems, particularly, which makes large-scale expensive optimization challenging. To address this challenge, surrogate-assisted EAs based on the divide-and-conquer strategy have been proposed and shown to be promising. Following this line of research, we propose a surrogate-assisted differential evolution algorithm with adaptive multisubspace search for large-scale expensive optimization to take full advantage of the population and the surrogate mechanism. The proposed algorithm constructs multisubspace based on principal component analysis and random decision variable selection, and searches adaptively in the constructed subspaces with three search strategies. The experimental results on a set of large-scale expensive test problems have demonstrated its superiority over three state-of-the-art algorithms on the optimization problems with up to 1000 decision variables.

In industrial control systems (ICSs), intrusion detection is a vital task. Conventional intrusion detection systems (IDSs) rely on manually designed rules. These rules heavily depend on professional experience, thereby making it challenging to represent the increasingly complicated industrial control logic. Although deep learning-based approaches provide better accuracy than other methods, they can only provide alerts. However, they cannot provide administrators with detailed information. In this study, we propose the logic understanding IDS (LU-IDS), which is a rule-based IDS with in-depth understandings of industrial control logic. Our proposed LU-IDS uses a specially designed deep learning-based model to capture features automatically and carry out attack classification. More importantly, it analyzes the knowledge learned from the classification of attacks to understand the abnormal industrial control logic and generate rules. The experimental results indicate that our proposed LU-IDS demonstrates excellent performance on intrusion detection. The rules generated by our proposed LU-IDS can be used to successfully detect all types of attacks on two public datasets.

Abstract Owing to the development of industrial production, the hidden danger in industrial control systems (ICSs) has considerably increased, causing challenges in traditional safety defense methods. The combination of machine-learning or deep-learning algorithms and intrusion detection systems (IDSs) has become the mainstream method for solving this problem. However, these methods depend on a massive amount of high-quality attack traffic data, which cannot be obtained easily owing to the independence and unique characteristics of ICSs. In this study, we apply the reconstructed convolutional neural network and a data expansion algorithm named CenterBorderline_SMOTE (CB_SMOTE) to an IDS and propose data expansion intrusion detection system (DEIDS). The DEIDS is an end-to-end detection model that learns representative attack features from raw traffic and classifies them in a unified framework. Moreover, we adopt the classification activation map structure, which can deeply mine the potential characteristics of traffic and enhance the effectiveness of attack features. While enhancing the data quality, we introduce the designed CB_SMOTE algorithm into DEIDS to expand the data and solve the problem of insufficient attack data in the system. Our comprehensive experiments on different open datasets indicate that DEIDS achieves an excellent performance (97 $$\%$$ % detection accuracy) and outperforms the state-of-the-art methods. The experimental results also show that our method has high efficiency and high accuracy in processing ICSs datasets.

Summary The virtual resource allocation in cloud computing is becoming a critical issue. In order to meet the task requirements of different users, virtual machines need to be placed on physical machines through virtualization technology in the data center. However, in this process, the total load balance, energy consumption, and resource utilization of physical machines should be considered. Therefore, two models are established for two different optimization targets, respectively. The first model is built to minimize the degree of load imbalance. The second model is built to maximize the resource utilization and minimize the energy consumption. To gain better results of virtual machines placement, we propose a new algorithm called resampled binary particle swarm optimization (RBPSO). To enhance the global search ability of BPSO, we add the re‐sampling, mutation and small vibration process to it, named RBPSO, for the purpose of maintaining the diversity of the population, reducing redundant calculation and thereby improving the ability and efficiency of the algorithm. Then, the RBPSO is used to solve the deployment problem of virtual machines in cloud computing. The experiments show that the proposed model is reasonable and RBPSO performs better than BPSO and genetic algorithm (GA).

In this paper, we proposed a novel method to solve the coverage control problem of sensor networks in the Internet of Things (IoT). The coverage control is an important index to evaluate the performance of network services. Ensuring the quality of network services, it is mainly to maximize the coverage of the network and minimize the energy consumption at the same time for the purpose of extending the network life cycle effect. Because of the overlay redundancy, it adopts the sleeping scheduling mechanism of nodes. The optimal solution is obtained after utilizing the coverage rate and the node sleep rate as the optimization objective function. Particle swarm optimization (PSO) is a group intelligent optimization algorithm. In practical applications, PSO often convergence in the local optimal solution prematurely. In order to balance the global search ability and convergence speed of PSO, We have improved the PSO based on the resampling technique, named resampled PSO (RPSO). The RPSO can not only maintain the diversity of the population, which can avoid premature convergence of the algorithm to some extent, but also ensure that each particle is active, reducing the calculation of redundancy, thereby improving the efficiency of the algorithm. The experimental results show that the RPSO can deal with complex multipeak optimization problem efficiently and reliably. Then the RPSO is used to solve the coverage control problem of sensor networks in IoT and has a great performance.