Large Language Models (LLMs) have demonstrated remarkable generalization capabilities, but aligning their outputs with human preferences typically requires expensive supervised fine-tuning. Recent test-time methods leverage textual feedback to overcome this, but they often critique and revise a single candidate response, lacking a principled mechanism to systematically analyze, weigh, and synthesize the strengths of multiple promising candidates. Such a mechanism is crucial because different responses may excel in distinct aspects (e.g., clarity, factual accuracy, or tone), and combining their best elements may produce a far superior outcome. This paper proposes the Textual Self-Attention Network (TSAN), a new paradigm for test-time preference optimization that requires no parameter updates. TSAN emulates self-attention entirely in natural language to overcome this gap: it analyzes multiple candidates by formatting them into textual keys and values, weighs their relevance using an LLM-based attention module, and synthesizes their strengths into a new, preference-aligned response under the guidance of the learned textual attention. This entire process operates in a textual gradient space, enabling iterative and interpretable optimization. Empirical evaluations demonstrate that with just three test-time iterations on a base SFT model, TSAN outperforms supervised models like Llama-3.1-70B-Instruct and surpasses the current state-of-the-art test-time alignment method by effectively leveraging multiple candidate solutions.

Multiplex graphs are widely used to model multi-relational complex systems and play an important role in various real-world scenarios, such as financial systems and social networks. Hence, detecting anomalous samples in multiplex graph becomes crucial to ensure cybersecurity and stability. Although existing homogeneous graph anomaly detection (GAD) methods can be applied to deal with multiplex graphs, they still face two major challenges: 1) Due to the multiplicity and complexity of relations in multiplex graphs, homogeneous GAD models fail to effectively capture anomalous behaviors that correlate with diverse relational patterns. 2) In real-world applications, malicious entities usually disguise themselves through various camouflage strategies, making it difficult to capture subtle anomalous features via single-relation analysis. To address these challenges, we propose a novel unsupervised anomaly detection method for multiplex graphs based on Similarity-constrained Fusion Graph Autoencoder (SFGA). In SFGA, we design a multiplex graph autoencoder and introduced a cross-plex attention module at the model bottleneck to achieve comprehensive modeling of cross-relation anomaly patterns. Then, a similarity balancing strategy is proposed to constrain node representations at the bottleneck from both local and global perspectives, enhancing the discriminative power against camouflaged anomalies of autoencoder and enabling more effective identification of anomalous nodes with overlapping or deceptive patterns. Extensive experiments are conducted on both synthetic and real-world datasets at varying scales, and the results demonstrate that our proposed method outperforms state-of-the-art approaches by a large margin.

Representation learning on continuous-time dynamic graphs (CTDGs) is critical for modeling evolving network behaviors. However, existing methods often fail to capture both temporal dynamics and structural nuances effectively. Since the community is well-known for manifesting the mesoscopic structure of graphs, we propose community-enhanced temporal walks (CTWalks), a novel framework that explicitly leverages community structures to enhance representation learning on CTDGs. CTWalks integrate three key innovations: 1) a community-guided temporal walk sampling strategy that captures intra and intercommunity interactions to mitigate locality bias, with theoretical guarantees; 2) a community-aware anonymization process that embeds contextual community labels for robust node representations; and 3) a neural ordinary differential equations-based encoding mechanism that models continuous temporal dynamics, including community information with high fidelity. Furthermore, we establish a theoretical connection between CTWalks and matrix factorization, revealing the principled foundation. Extensive experiments on six benchmark datasets, including the large-scale tgbl-comment dataset with approximately one million nodes, demonstrate that CTWalks significantly outperform ten state-of-the-art methods in temporal link prediction, achieving substantial improvements in Area Under the receiver operating characteristic Curve (AUC) and average precision (AP) scores across diverse settings. This work advances dynamic graph learning by bridging community-aware structural insights with continuous-time modeling, enabling more accurate and adaptable representations for real-world networks. Our implementation is publicly available at https://github.com/leonyuhe/CTWalks.

Time series forecasting (TSF) plays a pivotal role in decision-making and risk mitigation by predicting future values from historical observations. Despite significant improvements in forecasting accuracy, existing TSF models face two critical challenges: increasing computational complexity hinders deployment on resource-constrained platforms, and vulnerability to random failures compromises prediction stability. To address these issues, we propose M3NAS-TSF, a multimodal multiobjective neural architecture search framework that automates the design of lightweight and failure-resilient TSF models. Specifically, to address computational complexity, we introduce a modular time series super-net that defines a flexible and compact search space, enabling the discovery of architectures with reduced model size. To enhance failure resilience, we develop a multimodal multiobjective neural architecture search algorithm that promotes architectural diversity through an architecture-aware niching strategy and an architectural diversity distance metric, ensuring a broad set of robust candidate models. We also propose a node distribution heatmap and a structural entropy index to assess architectural diversity without ground-truth Pareto sets. Extensive experiments on 40 forecasting cases demonstrate that M3NAS-TSF outperforms six representative baselines, achieving superior forecasting accuracy (the maximum reduction in the RMSE reached 14.50%) with a smaller model size while maintaining greater architectural diversity for failure resilience.

Solving multimodal optimization problems (MMOPs) is a challenging task which needs locating multiple global optimal solutions simultaneously with high accuracy. Current popular niching-based evolutionary algorithms (EAs) for solving MMOPs usually divide the population into several separate species to search for different optimal solutions. However, achieving effective information exchange between species to enhance the performance of overall algorithm remains a challenge in current niching-based EAs, which will directly affect the efficiency of the multimodal optimization algorithm. In this paper, the process of the different species locating peaks in MMOPs is regarded as an evolutionary multitask (EMT) optimization problem and an EMT framework with bi-knowledge transfer for MMOPs is proposed. An explicit knowledge transfer (E-KT) strategy is designed to transfer the optimal individual of the species with the fastest convergence speed to other species, thereby facilitating the acceleration their convergence. Moreover, in order to further improve the information exchange between species, a species center-based implicit knowledge transfer (I-SCKT) strategy is designed to improve the diversity of the population. The performance of MTBKTMMOP is tested on the widely used CEC’2013 benchmark and five practical flexible job shop problems. The experimental results of MTBKTMMOP are compared with 9 state-of-the-art MMOPs algorithms and show that our MTBKTMMOP is superior to all of them. Besides, the experimental results also show that the MTBKTMMOP achieves breakthroughs in handling with a large number of optimal solutions or high-dimensional MMOPs, which provides a new and effective method for dealing with MMOPs.

In the current era of globalization, with increasing vessel cargo and limited port resources, the operational efficiency of container terminals is of paramount importance. Berth allocation and quay crane allocation problems (BACAPs) emerge as pivotal focal points, especially in large-scale container terminals. Although preventive maintenance for quay cranes is crucial for reducing equipment failures and widely implemented in real-world operations, it is often overlooked in existing studies. Lately, few methods are proposed considering maintenance activities. However, their performance are unsatisfied in terms of large-scale problems and hard to meet the requirement of efficiency. To deal with this challenge, in this paper, we present a mixed integer bi-objective optimization model and further propose a novel algorithm to address the large-scale BACAP with quay crane maintenance activities. This model aims to minimize vessel turnaround durations and the penalty of unscheduled maintenance. Meanwhile, based on NSGA-II, the model called RTAA utilizes a novel decoding method withRecurrentTemporal berthAllocation and quay craneAssignment, which can greatly reduce the probability of generating infeasible solutions in a heuristic way. Moreover, the island model is involved to improve the efficiency and parallelism of the model and enhance the diversity of the Pareto-front solutions. Compared to the existing methods in both small and large instances, the RTAA demonstrates its efficacy in discovering superior and more diverse solutions. In particular, for large-scale problems involving 100 vessels, as well as more berths and quay cranes, our model still delivers superior performance with a significant reduction in computation time. Additionally, our approach shows excellent scalability, as it can be easily adapted to scenarios that do not consider maintenance activities.

In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types—such as homogeneous and heterogeneous graphs—simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we introduce AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.

In the field of single objective optimization algorithms, learned evolutionary algorithms have achieved success in obtaining better performance than human-designed strategies. However, these learnable evolutionary algorithms are only applicable to single-objective optimization and cannot be applied to multi-objective optimization problems. In this study, we parameterize the mutation and crossover operators using the multi-head self-attention and the selection operator using a lightweight multilayer perceptron. We utilize the evolution strategy to train their parameters across multiple multi-objective optimization problems, resulting in the development of the Meta-Learned Multi-Objective Genetic Algorithm (Meta-MOGA). We compare Meta-MOGA with other multi-objective evolutionary algorithms on various test problems and evaluate its performance on untrained MOPs. The results demonstrate that our Meta-MOGA exhibits potential and generalizability.

Currently, visual single-object tracking methods utilize online template updates to combine temporal information. However, these methods rely on confidence scores to evaluate the reliability of the current template, which may result in a template not being updated for an extended period. Moreover, advanced trackers select bounding boxes based solely on the similarity between the template and the search area, which can lead to tracking drift when encountering deformable or similar targets. To alleviate these limitations, we propose a Spatio Temporal Prompt Tracker (STPTrack), which utilizes the prior information about small changes of object state between successive frames. Different from previous tracking methods that mainly rely on templates and similarity scores, STPTrack transfers the object position and shape information of the previous frame to the current frame as continuous spatio temporal prompt for the first time, and realizes the efficient fusion of spatio temporal information through the prompt encoder and the fusion decoder module. Specifically, it encodes the bounding box coordinates or mask information of the previous frame and the response points of the current frame as prompt features, and then combines prompt tokens with search tokens through the fusion decoder to provide the potential location of the object for the search feature map. Our STPTrack sets a new state-of-the-art performance on six tracking benchmark datasets.

The integrated circuit for 3D chip placement has attracted much attention in recent years, but its complex netlist structure poses significant challenges in optimizing 3D chip placement. However, the current algorithms for 3D chip placement have not considered further optimizing the placement, and existing location-based coding strategies have failed to effectively guide the optimization of standard cell placement. Therefore, a multi-objective optimization method with a mixedcoding strategy (MOMC3D) is proposed for standard cells in 3D chip placement, focusing on the adjustment of standard cell positions. The proposed MOMC3D algorithm includes the following three contributions. Firstly, a cell-netlist mixed-coding (CNMC) strategy to code the information of standard cells and netlist separately is designed to represent placement information of the current chip. Secondly, a max-min net length exchange (MMNE) crossover strategy and a large net boundary reduction (LNBR) mutation strategy are designed to reduce the halfperimeter wire length (HPWL). Thirdly, the 3D chip placement optimization is modeled as a multi-objective optimization problem, using an improved non-dominated sorting genetic algorithm II (NSGA-II) multi-objective evolutionary framework to iterate the HPWL and the number of terminals. Compared to existing location-based coding strategies, the CNMC strategy achieved a 9.54% reduction in HPWL and a 17.18% reduction in the number of terminals in the legally compliant placement of ICCAD 2023 contest case 2. Furthermore, compared to other existing multi-objective optimization algorithms and reinforcement learning algorithms, the MOMC3D algorithm reduced the HPWL and the number of terminals by 11.59% and 8.41%, respectively.

The search for multiple optimal solutions in the traveling salesman problem (TSP), as a challenging multimodal optimization problem in the combinatorial domain, has received increasing attention in recent years. Nevertheless, the multisolution TSP (MSTSP) still remains extremely difficult for larger-scale TSP instances. In this article, we propose a niching Lin-Kernighan–Helsgaun (LKH)-based ant colony system (ACS), named nLKH-ACS, taking advantage of LKH’s ability to solve large-scale TSPs, ACS’s search efficiency, and the niching technique for diversity preservation. Specifically, first, to address multisolution problems, we design a niching LKH (nLKH) strategy to generate diverse cost-efficient spanning trees, and adopt the$\alpha $-nearness on each tree to obtain a diverse candidate edge set. The nLKH strategy enhances the ACS by improving pheromone initialization, solution construction, and local search operation using spanning trees and candidate edge sets, thereby strengthening the search capability and diversity. Then, to balance convergence and diversity, an adaptive Gaussian strategy is utilized to update the pheromone matrix. Furthermore, we design an indicator to measure the geometric diversity between pairs of solutions in the MSTSP solution set. The comprehensive experiments on MSTSPs and TSPLIB are conducted to validate the performance of the proposed nLKH-ACS. The experimental results demonstrate the powerful solving capability and excellent diversity of the proposed nLKH-ACS, particularly in finding various optimal solutions in larger-scale TSP instances.

Accurate stock prediction is a pressing challenge in quantitative finance, where complex temporal and cross-sectional dynamics defy traditional models. Although deep learning-based methods have made significant progress, most of them focus on individual stock trajectories, neglecting directional causality in stock interactions. Fuzzy cognitive maps (FCMs) are good at modeling the directional causality. Therefore, we design a new type of FCM with each concept node having a fuzzy state vector instead of just a fuzzy state value to more stereoscopic manifest the factors affecting a stock, like firm size, book-to-market value, and market risk emphasized by the famous Fama-French multifactor model. A genetic algorithm with a specially designed objective function is used to learn the new FCMs. Furthermore, the new FCMs are combined with a double-level attention mechanism and graph neural networks (GNNs) for z-score forecasting, named CausalSeqGNN. To balance scalability and adaptability, a dual-phase alternating learning architecture is designed in CausalSeqGNN, where the double-level attention mechanism fuses eight-day price sequences with news-derived sentiment scores updated daily, and the causal matrix capturing asymmetric stock interdependencies obtained by FCM learning updated quarterly since companies generally release their financial reports on a quarterly basis. Successfully synergizing Fama-French-driven causality with temporal dynamics, CausalSeqGNN achieves superior mean squared error and investment performance on US and Chinese market dataset, outperforming state-of-the-art baselines. This hybrid framework offers transformative potential for real-time trading, redefining stock forecasting with unparalleled precision and scalability.

The significance of maritime transportation highlights the need to enhance the efficiency of container terminals. This study addresses a challenge within maritime transportation, specifically the continuous berth allocation and time-variant quay crane assignment problem (C/T-V BACAP). We formulate a comprehensive mathematical model of C/T-V BACAP. To solve the problem, we propose an effective memetic algorithm with a heuristic decoding method, named HMA, which comprises three essential components: a three-stage heuristic decoding method, a clustering-based evolutionary strategy, and a target-guided local search operator. The three-stage heuristic decoding method guarantees solution feasibility and high quality through the entire optimization, allowing the following strategies to fully utilize their search capabilities. The clustering-based evolutionary strategy refines the search space and diversifies the promising candidates. Meanwhile, the target-guided local search operator rapidly optimizes the allocation for the challenging vessel. The experimental results demonstrate that the proposed algorithm delivers excellent performance, especially in handling large-scale instances (up to 60 vessels). Our proposed method outperforms the state-of-the-art BACAP algorithms by an average margin of 150% in terms of berth offset and waiting time in most problem instances.

In real-world scenarios, most complex systems can be generally modelled as homogenous or heterogenous networks. Therefore, downstream tasks (e.g., node/graph classification, node clustering) based on these two types of graphs become ubiquitous and have drawn considerable attentions in recent years. Existing literatures on node classification mainly focuses on either homogeneous or heterogeneous graphs, while research on effectively carrying out node classification tasks on both types of graphs simultaneously still under-exploited. To fill this gap, we propose a universal Graph Neural Network architecture based on Subgraph and Subhypergraph (SS-GNN) with feature-enhanced strategy for node embedding on both homogeneous and heterogeneous graphs. Through construction of subgraph and subhypergraph with same-class nodes, our model can simultaneously deal with homogeneous and heterogeneous graphs. Graph attention modules are especially designed to embed subgraphs of same-class nodes to learn the internal topological structure and local community structure within the original graph. Additionally, to capture high-order features of graph and enhance the embedding representations of nodes, we also utilize hypergraph attention modules to embed subhypergraphs of same-class nodes. Unlike other approaches that rely on pre-defined meta-paths, our model can be readily applied to most real-world applications without requiring any domain knowledge. Finally, we conduct extensive experiments on three homogeneous and three heterogeneous real-world graphs to demonstrate the effectiveness of SS-GNN. The experimental results for node classification and clustering tasks not only show the superior performance of our proposed model compared to state-of-the-art, but also demonstrate its potentially good interpretability for graph analysis. This work may provide some enlightening insights to the study on universality of graph foundation model.

Graphs are widely used to model networks in real-world applications, with heterogeneous graph neural networks gaining increasing attention in recent years. Existing methods generally rely on first-order or high-order neighbors to capture semantic relationships, where metapath-based approaches are the most popular ones. However, existing metapath-based models not only require predefined metapaths based on prior knowledge, but also lack the consideration of metapath sequence modeling. Additionally, labeled data are scarce in massive graph data, and existing self-supervised or semisupervised models heavily rely on data enhancement strategies and complex frameworks. To address these limitations, we propose a self-supervised heterogeneous graph attention model (HGAM) based on adaptable step-size metapaths. Our model requires no prior knowledge to select the type of metapath and can adaptively capture the specific step-size metapath with high importance. The adaptable step-size metapaths module not only considers the attention weight in different step sizes, but also pays attention to the changing trend of attention, which expands the receptive field of the model and integrates global information preferably. To alleviate labeled data scarcity, our model employs a dual contrastive learning strategy. HGAM learns global representations by contrasting a high-order meta-graph against nodes, while preserving local structure through a cross-view comparison of first-order and high-order semantics. Extensive experiments on three different types of tasks, including node classification, clustering, and link prediction, are conducted on real-world datasets. Experimental results demonstrate that HGAM achieves superior performance compared to state-of-the-art methods.

Modeling continuous-time dynamics constitutes a foundational challenge, and uncovering inter-component correlations within complex systems holds promise for enhancing the efficacy of dynamic modeling. The prevailing approach of integrating graph neural networks with ordinary differential equations has demonstrated promising performance. However, they disregard the crucial signed information potential on graphs, impeding their capacity to accurately capture real-world phenomena and leading to subpar outcomes. In response, we introduce a novel approach: a signed graph neural ordinary differential equation, adeptly addressing the limitations of miscapturing signed information. Our proposed solution boasts both flexibility and efficiency. To substantiate its effectiveness, we seamlessly integrate our devised strategies into three preeminent graph-based dynamic modeling frameworks: graph neural ordinary differential equations, graph neural controlled differential equations, and graph recurrent neural networks. Rigorous assessments encompass three intricate dynamic scenarios from physics and biology, as well as scrutiny across four authentic real-world traffic datasets. Remarkably outperforming the trio of baselines, empirical results underscore the substantial performance enhancements facilitated by our proposed approach. Our code can be found at https://github.com/beautyonce/SGODE.

RGBT tracking has been widely used in various fields such as robotics, surveillance processing, and autonomous driving. Existing RGBT trackers fully explore the spatial information between the template and the search region and locate the target based on the appearance matching results. However, these RGBT trackers have very limited exploitation of temporal information, either ignoring temporal information or exploiting it through online sampling and training. The former struggles to cope with the object state changes, while the latter neglects the correlation between spatial and temporal information. To alleviate these limitations, we propose a novel Temporal Adaptive RGBT Tracking framework, named as TATrack. TATrack has a spatio-temporal two-stream structure and captures temporal information by an online updated template, where the two-stream structure refers to the multi-modal feature extraction and cross-modal interaction for the initial template and the online update template respectively. TATrack contributes to comprehensively exploit spatio-temporal information and multi-modal information for target localization. In addition, we design a spatio-temporal interaction (STI) mechanism that bridges two branches and enables cross-modal interaction to span longer time scales. Extensive experiments on three popular RGBT tracking benchmarks show that our method achieves state-of-the-art performance, while running at real-time speed.

Current video anomaly detection (VAD) approaches with weak supervisions are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to de-tect unseen anomalies given seen anomalies and normal videos. However, such a setting focuses on predicting frame anomaly scores, having no ability to recognize the specific categories of anomalies, despite the fact that this ability is essential for building more informed video surveillance systems. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pretrained large models to detect and cate-gorize seen and unseen anomalies. To this end, we propose a model that decouples OVVAD into two mutually comple-mentary tasks - class-agnostic detection and class-specific classification - and jointly optimizes both tasks. Particu-larly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task. These semantic knowledge and synthesis anomalies substantially extend our model's capability in detecting and categorizing a variety of seen and unseen anomalies. Exten-sive experiments on three widely-used benchmarks demonstrate our model achieves state-of-the-art performance on OVVAD task.

Weakly supervised video anomaly detection (WSVAD) is a challenging task. Generating fine-grained pseudo-labels based on weak-label and then self-training a classifier is currently a promising solution. However, since the existing methods use only RGB visual modality and the utilization of category text information is neglected, thus limiting the generation of more accurate pseudo-labels and affecting the performance of self-training. Inspired by the manual labeling process based on the event description, in this paper, we propose a novel pseudo-label generation and self-training framework based on Text Prompt with Normality Guidance (TPWNG) for WSVAD. Our idea is to transfer the rich language-visual knowledge of the contrastive language-image pre-training (CLIP) model for aligning the video event description text and corresponding video frames to generate pseudo-labels. Specifically, We first fine-tune the CLIP for domain adaptation by designing two ranking losses and a distributional inconsistency loss. Further, we propose a learnable text prompt mechanism with the assist of a normality visual prompt to further improve the matching accuracy of video event description text and video frames. Then, we design a pseudo-label generation module based on the normality guidance to infer reliable frame-level pseudo-labels. Finally, we introduce a temporal context self-adaptive learning module to learn the temporal dependencies of different video events more flexibly and accurately. Extensive experiments show that our method achieves state-of-the-art performance on two benchmark datasets, UCF-Crime and XD-Violence, demonstrating the effectiveness of our proposed method.

Recent research shows that deep neural networks make wrong predictions when faced with adversarial examples with small perturbations added. In the setting of white-box attack, it is easy to generate adversarial samples with high attack success rate through gradients. But in reality, gradients are usually unavailable. At present, most black-box attack achieves the purpose of the attack by adding small perturbations, the intensity of the perturbation and the attack success rate are a kind of trade off. However, the noise added by most methods is meaningless. This paper introduces a novel adversarial attack algorithm called Pixel Logo Attack (PLA), which rationalizes noise by arranging pixel patterns into a logo-style, thereby presenting itself as an identity for protecting copyright information. Unlike most existing methods, this method can completely expose the added noise to the user without arousing user suspicion, and does not affect the usage of image. We use the differential evolution(DE) to search for suitable pixel positions and RGB values, and compare the performance of PLA with the state-of-the-art adversarial attack algorithms on the CIFAR-10 and ImageNet datasets. Experimental results show that PLA has good performance in solving black-box adversarial attack problems, especially non-targeted attack.

Class-imbalanced node classification tasks are prevalent in real-world scenarios. Due to the uneven distribution of nodes across different classes, learning high-quality node representations remains a challenging endeavor. The engineering of loss functions has shown promising potential in addressing this issue. It involves the meticulous design of loss functions, utilizing information about the quantities of nodes in different categories and the network’s topology to learn unbiased node representations. However, the design of these loss functions heavily relies on human expert knowledge and exhibits limited adaptability to specific target tasks. In this paper, we introduce a high-performance, flexible, and generalizable automated loss function search framework to tackle this challenge. Across 15 combinations of graph neural networks and datasets, our framework achieves a significant improvement in performance compared to state-of-the-art methods. Additionally, we observe that homophily in graph-structured data significantly contributes to the transferability of the proposed framework.

Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal adjustments to the optimizer. It is crucial to ensure reliable and robust performance in various applications. Current optimizers often struggle with zero-shot optimization and require intricate hyperparameter tuning to adapt to new tasks. To address this, we propose a Pretrained Optimization Model (POM) that leverages knowledge gained from optimizing diverse tasks, offering efficient solutions to zero-shot optimization through direct application or fine-tuning with few-shot samples. Evaluation on the BBOB benchmark and two robot control tasks demonstrates that POM outperforms state-of-the-art black-box optimization methods, especially for high-dimensional tasks. Fine-tuning POM with a small number of samples and budget yields significant performance improvements. Moreover, POM demonstrates robust generalization across diverse task distributions, dimensions, population sizes, and optimization horizons. For code implementation, see https://github.com/ninja-wm/POM/.

In the realm of daily services, the deployment of deep neural networks underscores the paramount importance of their reliability. However, the vulnerability of these networks to adversarial attacks, primarily evasion-based, poses a concerning threat to their functionality. Common methods for enhancing robustness involve heavy adversarial training or leveraging learned knowledge from clean data, both necessitating substantial computational resources. This inherent time-intensive nature severely limits the agility of large foundational models to swiftly counter adversarial perturbations. To address this challenge, this paper focuses on the \textbf{Ra}pid \textbf{P}lug-\textbf{i}n \textbf{D}efender (\textbf{RaPiD}) problem, aiming to rapidly counter adversarial perturbations without altering the deployed model. Drawing inspiration from the generalization and the universal computation ability of pre-trained transformer models, we propose a novel method termed \textbf{CeTaD} (\textbf{C}onsidering Pr\textbf{e}-trained \textbf{T}ransformers \textbf{a}s \textbf{D}efenders) for RaPiD, optimized for efficient computation. \textbf{CeTaD} strategically fine-tunes the normalization layer parameters within the defender using a limited set of clean and adversarial examples. Our evaluation centers on assessing \textbf{CeTaD}'s effectiveness, transferability, and the impact of different components in scenarios involving one-shot adversarial examples. The proposed method is capable of rapidly adapting to various attacks and different application scenarios without altering the target model and clean training data. We also explore the influence of varying training data conditions on \textbf{CeTaD}'s performance. Notably, \textbf{CeTaD} exhibits adaptability across differentiable service models and proves the potential of continuous learning.

Fuzzy cognitive map (FCM) has been successfully applied to time series prediction due to its powerful dynamic system modeling and inference ability. Although many FCM-based methods have been proposed, their performance is far from satisfactory. The existing FCM-based methods have two limitations: First, the feature extraction of some methods is unreasonable and even leads to overfitting. Second, most methods ignore the local temporal features of time series. In this work, we propose a novel framework for time series prediction based on long short-term memory (LSTM) and high-order FCMs (HFCM) with an attention mechanism, termed LSTM-HFCM AM . To overcome the first limitation, different from other FCM-based methods that use Autoencoder to forcibly decompose each point of the time series into multiple points to represent the original sequences, we use a sliding window to preprocess the original time series and use the Encoder-Decoder framework to represent the sequences. This way makes the model has better generalization and interpretability. Then, HFCM is used to predict representations of sequences due to its powerful causal inference ability. Finally, self-attention is applied to restore the predicted sliding window data with focus, effectively improving the performance. To overcome the second limitation, we use the LSTM to learn the temporal features of time series fragments, thereby learning the local features of the whole time series. We validate the performance of LSTM-HFCM AM on twelve benchmark datasets. Compared with current methods, LSTM-HFCM AM has a maximum improvement of 51.02%. The experimental results demonstrate the effectiveness of LSTM-HFCM AM and overcome the above limitations.

Transformer has shown its great strength in visual object tracking due to its effective attention mechanism , but most prevailing transformer-based trackers only explore temporal information frame by frame, thus overlooking the rich context information inherent in videos. To alleviate this problem, we propose a transformer-based tracker via learning immediate appearance change information in videos, called IAC-tracker. The proposed tracker enhances the perception of the immediate motion state to improve the performance of single target tracking . IAC-tracker contains three key components: a spatial information extractor (SIE) with a superior attention mechanism to progressively extract spatial information, a temporal information extractor (TIE) with a designed temporal attention mechanism to progressively learn target immediate appearance change, and a novel spatial–temporal context enhanced fusion module integrating the information from SIE and TIE to prepare for the final prediction head. Comparison experiments with state-of-the-art trackers on six challenging datasets demonstrate the superior performance of IAC-tracker with real-time running speed.

Network structure evolves with time in the real world, and the discovery of changing communities in dynamic networks is an important research topic that poses challenging tasks. Most existing methods assume that no significant change occurs; namely, the difference between adjacent snapshots is slight. However, great change exists in the real world usually. The great change in the network will result in the community detection algorithms are difficulty obtaining valuable information from the previous snapshot, leading to negative transfer for the next time steps. This article focuses on dynamic community detection with substantial changes by integrating higher order knowledge from the previous snapshots to aid the subsequent snapshots. Moreover, to improve search efficiency, a higher order knowledge transfer strategy is designed to determine first-order and higher order knowledge by detecting the similarity of the adjacency matrix of snapshots. In this way, our proposal can keep the advantages of previous community detection results and transfer them to the next task. We conduct the experiments on four real-world networks, including the networks with great or minor changes. Experimental results in the low-similarity datasets demonstrate that higher order knowledge is more valuable than first-order knowledge when the network changes significantly and keeps the advantage even if handling the high-similarity datasets. Our proposal can also guide other dynamic optimization problems with great changes.

Fuzzy cognitive maps (FCMs) play a significant role in inferring causal relationships and modeling complex systems. In recent years, numerous FCM-based causal discovery methods have emerged for diverse causal inference scenarios. However, determining the causal relations that best represent the ground truth in a novel scenario remains a challenge, resulting in an abundant but noisy set of candidate causal relations. Addressing this challenge, we introduce a parameter-free model grounded in Bayesian and fuzzy theory to estimate the accurate causal relations of the real system from candidate causal relation datasets. We initially fuzzify the edge weights within candidate FCMs into distinct causal states. Assuming a probabilistic data model linking observed data (causal relations in candidate FCMs) to true causality, we employ Bayesian methods to transform model parameter solving into a maximum posterior probability estimation task. This approach yields an accurate probabilistic data model, facilitating precise estimation of genuine causality from datasets containing multiple candidate relations. This model aims to derive accurate causal relations from datasets populated with multiple candidate relations. Our method validated on 15 diverse causal datasets, constructed from real and synthetic gene regulatory data, exhibits superior accuracy in discerning causal relationships. These results also demonstrate the efficacy of our proposal: 1) stabilizing performance amidst noisy data; 2) resolving algorithmic diversity for precise causal inferences; 3) mitigating fluctuations from hyperparameters. The source code and dataset are available athttps://github.com/IngeTeng/Abundant-but-Noisy-FCMs.

Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies, which can be roughly interpreted as the binary or multiple event classification. However, such a setup that builds relationships between complicated anomalous events and single labels, e.g., "vandalism", is superficial, since single labels are deficient to characterize anomalous events. In reality, users tend to search a specific video rather than a series of approximate videos. Therefore, retrieving anomalous events using detailed descriptions is practical and positive but few researches focus on this. In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e.g., language descriptions and synchronous audios. Unlike the current video retrieval where videos are assumed to be temporally well-trimmed with short duration, VAR is devised to retrieve long untrimmed videos which may be partially relevant to the given query. To achieve this, we present two large-scale VAR benchmarks and design a model called Anomaly-Led Alignment Network (ALAN) for VAR. In ALAN, we propose an anomaly-led sampling to focus on key segments in long untrimmed videos. Then, we introduce an efficient pretext task to enhance semantic associations between video-text fine-grained representations. Besides, we leverage two complementary alignments to further match cross-modal contents. Experimental results on two benchmarks reveal the challenges of VAR task and also demonstrate the advantages of our tailored method. Captions are publicly released at https://github.com/Roc-Ng/VAR.

Conducting functional connectivity analysis on functional magnetic resonance imaging (fMRI) data presents a significant and intricate challenge. Contemporary studies typically analyze fMRI data by constructing high-order functional connectivity networks (FCNs) due to their strong interpretability. However, these approaches often overlook temporal information, resulting in suboptimal accuracy. Temporal information plays a vital role in reflecting changes in blood oxygenation level-dependent signals. To address this shortcoming, we have devised a framework for extracting temporal dependencies from fMRI data and inferring high-order functional connectivity among regions of interest (ROIs). Our approach postulates that the current state can be determined by the FCN and the state at the previous time, effectively capturing temporal dependencies. Furthermore, we enhance FCN by incorporating high-order features through hypergraph-based manifold regularization. Our algorithm involves causal modeling of the dynamic brain system, and the obtained directed FC reveals differences in the flow of information under different patterns. We have validated the significance of integrating temporal information into FCN using four real-world fMRI datasets. On average, our framework achieves 12% higher accuracy than non-temporal hypergraph-based and low-order FCNs, all while maintaining a short processing time. Notably, our framework successfully identifies the most discriminative ROIs, aligning with previous research, and thereby facilitating cognitive and behavioral studies.

We introduce GS-SFS, a method that utilizes a camera array with wide baselines for high-quality multiple human mesh reconstruction in large-scale sports scenes. Traditional human reconstruction methods in sports scenes, such as Shape-from-Silhouette (SFS), struggle with sparse camera setups and small human targets, making it challenging to obtain complete and accurate human representations. Despite advances in differentiable rendering, including 3D Gaussian Splatting (3DGS), which can produce photorealistic novel-view renderings with dense inputs, accurate depiction of surfaces and generation of detailed meshes is still challenging. Our approach uniquely combines 3DGS's view synthesis with an optimized SFS method, thereby significantly enhancing the quality of multiperson mesh reconstruction in large-scale sports scenes. Specifically, we introduce body shape priors, including the human surface point clouds extracted through SFS and human silhouettes, to constrain 3DGS to a more accurate representation of the human body only. Then, we develop an improved mesh reconstruction method based on SFS, mainly by adding additional viewpoints through 3DGS and obtaining a more accurate surface to achieve higher-quality reconstruction models. We implement a high-density scene resampling strategy based on spherical sampling of human bounding boxes and render new perspectives using 3D Gaussian Splatting to create precise and dense multi-view human silhouettes. During mesh reconstruction, we integrate the human body's 2D Signed Distance Function (SDF) into the computation of the SFS's implicit surface field, resulting in smoother and more accurate surfaces. Moreover, we enhance mesh texture mapping by blending original and rendered images with different weights, preserving high-quality textures while compensating for missing details. The experimental results from real basketball game scenarios demonstrate the significant improvements of our approach for multiple human body model reconstruction in complex sports settings.

A fuzzy cognitive map (FCM) is a simple but effective tool for modeling and predicting time series. This article focuses on the problem of multivariate time series prediction (TSP), which is essential and challenging in data mining. Although several FCM-based approaches have been designed to solve this problem, their feature extraction module designed for single mode falls short in capturing the nonlinear spatiotemporal dependencies among variates, thereby resulting in low prediction accuracy in forecasting multivariate time series, which shows that the single mode learning is not enough. Therefore, in this article, we propose a joint spatiotemporal feature learning framework for multivariate TSP, where a mix-resolution spatial module consisting of multiple sparse autoencoders (SAEs) is designed to extract the feature series with different spatial resolutions, and a mix-order spatiotemporal module concluding multiple high-order FCMs (HFCMs) is designed to model the spatiotemporal dynamics of these feature series. Finally, the outputs of the two modules are concatenated to predict future values. We refer to this framework as the spatiotemporal FCM (STFCM). Especially, an efficient learning algorithm is designed to update the integral weights of STFCM based on the batch gradient descent algorithm when it deems necessary. We validate the performance of the STFCM on four real-world datasets. Compared with the existing state-of-the-art (SOTA) methods, the experimental results not only show the advantages of the two designed modules in the STFCM but also show the excellent performance of the STFCM.

Multimodal optimization problems (MMOPs) are one of the most challenging optimization problems in the real world, which need to locate multiple global optima with high accuracy, simultaneously. Although many niching techniques, such as crowding and species have been widely used for solving MMOPs, how to reduce the influence of introduced niching parameters and how to deal with the individuals trapped into local optima are still challenges for the existing multimodal algorithms. In this paper, a novel reachability-distance based differential evolution with individual transfer (RDDE-IT) is proposed to better deal with MMOPs, which includes the following three contributions. Firstly, a reachability-distance based prim (RDP) niching strategy without sensitive parameters is proposed to divide the population, which can adaptively adjust the number of niches as evolution progress. Secondly, an individual state-based mutation (ISM) strategy is proposed to help each individual select a suitable mutation operator. Thirdly, an adaptive individual transfer (AIT) strategy is proposed to deal with the individuals trapped into local optima and determines the probability of new individuals being generated within each niche. The performance of RDDE-IT is compared with 13 state-of-the-art algorithms on CEC'2013 and the experimental results show that RDDE-IT achieves significant advantages on high-dimension problems.

Matrix factorization (MF) is a fundamental model in data mining and machine learning, which finds wide applications in diverse application areas, including recommendation systems with user-item rating matrices, phenotype extraction from electronic health records, and spatial-temporal data analysis for check-in records. The "right to be forgotten" has become an indispensable privacy consideration due to the widely enforced data protection regulations, which allow personal users having contributed their data for model training to revoke their data through a data deletion request. Consequently, it gives rise to the emerging task of machine unlearning for the MF model, which removes the influence of the matrix rows/columns from the trained MF factors upon receiving the deletion requests from the data owners of these rows/columns. The central goal is to effectively remove the influence of the rows/columns to be forgotten, while avoiding the computationally prohibitive baseline approach of retraining from scratch. Existing machine unlearning methods are either designed for single-variable models and not compatible with MF that has two factors as coupled model variables, or require alternative updates that are not efficient enough. In this paper, we propose a closed-form machine unlearning method. In particular, we explicitly capture the implicit dependency between the two factors, which yields the total Hessian-based Newton step as the closed-form unlearning update. In addition, we further introduce a series of efficiency-enhancement strategies by exploiting the structural properties of the total Hessian. Extensive experiments on five real-world datasets from three application areas as well as synthetic datasets validate the efficiency, effectiveness, and utility of the proposed method.

Video anomaly detection (VAD) is a significant computer vision problem. Existing deep neural network (DNN) based VAD methods mostly follow the route of frame reconstruction or frame prediction. However, the lack of mining and learning of higher-level visual features and temporal context relationships in videos limits the further performance of these two approaches. Inspired by video codec theory, we introduce a brand-new VAD paradigm to break through these limitations: First, we propose a new task of video event restoration based on keyframes. Encouraging DNN to infer missing multiple frames based on video keyframes so as to restore a video event, which can more effectively motivate DNN to mine and learn potential higher-level visual features and comprehensive temporal context relationships in the video. To this end, we propose a novel U-shaped Swin Transformer Network with Dual Skip Connections (USTN-DSC) for video event restoration, where a cross-attention and a temporal upsampling residual skip connection are introduced to further assist in restoring complex static and dynamic motion object features in the video. In addition, we propose a simple and effective adjacent frame difference loss to constrain the motion consistency of the video sequence. Extensive experiments on benchmarks demonstrate that USTN-DSC outperforms most existing methods, validating the effectiveness of our method.

Currently, the problem of uncovering complex network structure and dynamics from time series is prominent in many fields. Despite the recent progress in this area, reconstructing large-scale networks from limited data remains a tough problem. Existing works treat connections of nodes as continuous values, leaving a challenge of setting a proper cut-off value to distinguish whether the connections exist or not. Besides, their performances on large-scale networks are far from satisfactory. Considering the reconstruction error and sparsity as two objectives, this article proposes a subspace learning-based evolutionary multiobjective network reconstruction algorithm, called SLEMO-NR, to solve the aforementioned problems. In the evolutionary process, we assume that binary-coded individuals obey the Bernoulli distribution and can use the probability and natural parameter as alternative representations. Moreover, our approach utilizes the logistic principal component analysis (LPCA) to learn a subspace containing the features of the network structure. The offspring solutions are generated in the learned subspace and then can be mapped back to the original space via LPCA. Benefitting from the alternative representations, a preference-based local search operator (PLSO) is proposed to concentrate on finding solutions approximate to the true sparsity. The experimental results on synthetic networks and six real-world networks demonstrate that, due to the well-learned network structure subspace and the preference-based strategy, our approach is effective in reconstructing large-scale networks compared to six existing methods.

Violence detection in videos is very promising in practical applications due to the emergence of massive videos in recent years. Most previous works define violence detection as a simple video classification task and use the single modality of small-scale datasets, e.g., visual signal. However, such solutions are undersupplied. To mitigate this problem, we study weakly supervised violence detection on the large-scale audio-visual violence data, and first introduce two complementary tasks, i.e., coarse-grained violent frame detection and fine-grained violent event detection, to advance the simple violence video classification to frame-level violent event localization, which aims to accurately locate the violent events on untrimmed videos. We then propose a novel network that takes as input audio-visual data and contains three parallel branches to capture different relationships among video snippets and further integrate features, where similarity branch and proximity branch capture long-range dependencies using similarity prior and proximity prior, respectively, and score branch dynamically captures the closeness of predicted score. In both coarse-grained and fine-grained tasks, our approach outperforms other state-of-the-art approaches on two public datasets. Moreover, experiment results also show the positive effect of audio-visual input and relationship modeling.

Spatiotemporal forecasting has been attracting tremendous interest in various fields, among which traffic flow prediction is a representative example. Existing methods typically deal with the complex spatial and temporal dependencies in traffic flow through graph neural networks (GNNs) and temporal neural networks (TNNs), respectively. However, these works still fall short due to: 1) deep GNNs have the over-smoothing problem that hinders the handling of higher-order spatial correlations; 2) TNNs have difficulty in extracting the temporal dependencies with different localities. To this end, this paper proposes Higher-Order Masked Graph Neural Networks (HOMGNNs) to model and predict the traffic flow data. Concretely, we design the spatial graph learning layer to adaptively characterize the dependency correlations of different orders, and the higher-order GNN (HOGNN) is further proposed to deal with these correlations. Furthermore, we define and construct a temporal graph to represent the temporal dynamics in traffic data. The masked GNN (MGNN) is further proposed to extract these dynamics based on the temporal graph. To validate the superiority of the proposed HOMGNNs, we conduct extensive experiments on METR-LA and PEMS-BAY datasets. Experimental results demonstrate the remarkable performance of our method compared with 11 state-of-the-art baselines.

The problem of reconstructing nonlinear and complex dynamical systems from available data or time series is prominent in many fields, including engineering, physical, computer, biological, and social sciences. Many methods have been proposed to address this problem and their performance is satisfactory. However, none of them can reconstruct network structure from large-scale real-time streaming data, which leads to the failure of real-time and online analysis or control of complex systems. In this article, to overcome the limitations of current methods, we first extend the network reconstruction problem (NRP) to online settings, and then develop a follow-the-regularized-leader (FTRL)-Proximal style method to address the online complex NRP; we refer to it as Online-NR. The performance of Online-NR is validated on synthetic evolutionary game network reconstruction datasets and eight real-world networks. The experimental results demonstrate that Online-NR can effectively solve the problem of online network reconstruction with large-scale real-time streaming data. Moreover, Online-NR outperforms or matches nine state-of-the-art network reconstruction methods.

Due to the multilayer nature of real-world systems, the problem of inferring multilayer network structures from nonlinear and complex dynamical systems is prominent in many fields, including engineering, biological, physical, and computer sciences. Many network reconstruction methods have been proposed to address this problem, but none of them consider the similarities among network reconstruction tasks at different component layers, which are inspired by topology correlations and dynamic couplings among different component layers. This article develops an evolutionary multitasking multilayer network reconstruction framework to make use of the correlations among different component layers to improve the reconstruction performance; we refer to this framework as EM2MNR. In EM2MNR, the multilayer network reconstruction problem is first established as a multitasking multilayer network reconstruction problem, where the goal of each task is to reconstruct the network structure of a component layer. In addition, multitasking multilayer network reconstruction problems are high dimensional, but existing evolutionary multitasking algorithms may have poor performance when dealing with optimization problems with a high-dimensional search space. Inspired by the sparsity of multilayer networks, EM2MNR employs the restricted Boltzmann machine to extract low effective features from the original decision space and then decides whether to conduct knowledge transfer on these features. To verify the performance of EM2MNR, this article also designs a test suite for multilayer network reconstruction problems. The experimental results demonstrate the significant improvement obtained by the proposed EM2MNR framework on 96 multilayer network reconstruction problems.

Evolutionary multitask optimization (EMTO) has recently attracted widespread attention in the evolutionary computation community, which solves two or more tasks simultaneously to improve the convergence characteristics of tasks when individually optimized. Effective knowledge between tasks is transferred by taking advantage of the parallelism of population-based search. Without any prior knowledge about tasks, it is a challenging problem of how to adaptively transfer effective knowledge between tasks and reduce the impact of negative transfer in EMTO. However, these two issues are rarely studied simultaneously in the existing literature. Besides, in complex many-task environments, the potential relationships among individuals from highly diverse populations associated with tasks directly determine the effectiveness of cross-task knowledge transfer. Keeping those in mind, we propose a multitask evolutionary algorithm based on anomaly detection (MTEA-AD). Specifically, each task is assigned a population and an anomaly detection model. Each anomaly detection model is used to learn the relationship among individuals between the current task and the other tasks online. Individuals that may carry negative knowledge are identified as outliers, and candidate transferred individuals identified by the anomaly detection model are selected to assist the current task, which may carry common knowledge across the current task and other tasks. Furthermore, to realize the adaptive control of the degree of knowledge transfer, the successfully transferred individuals that survive to the next generation through the elitism are used to update the anomaly detection parameter. The fair competition between offspring and candidate transferred individuals can effectively reduce the risk of negative transfer. Finally, the empirical studies on a series of synthetic benchmarks and a practical study are conducted to verify the effectiveness of MTEA-AD. The experimental results demonstrate that our proposal can adaptively adjust the degree of knowledge transfer through the anomaly detection model to achieve highly competitive performance compared to several state-of-the-art EMTO methods.

Wireless energy charging is considered as a very promising technology for prolonging sensor lifetime in Wireless Rechargeable Sensor Networks (WRSNs). However, most existing studies suffers from charging scalability and efficiency problems. Under such a background, a new one to many charging model, which allows multiple sensors to be charged simultaneously by a single mobile reader, is designed. A dynamic multiagent genetic algorithm with a virtual force operator combined with K-means clustering for WRSNs (D_VF_MAGA_WRSNs) is proposed to optimize the charging problem in this paper. Agents representing candidate solutions compete or cooperate with their neighbors, and can also use knowledge. Memetic algorithm is applied in the process of evolution to guide readers moving to the tags' clustering centers obtained by the K-means algorithm. Moreover, a special crossover operator is designed to dynamically adjust the number of reader charging positions in the network. To verify the effectiveness of D_VF_MAGA_WRSNs, various of experiments on different kinds of benchmarks are carried. Compared with other algorithms, our algorithm is illustrated to be superior for WRSNs in terms of total charging time, maximum charging load, charging efficiency, and total charging distance.

In real life, independent networks exist widely and their robustness has received significant attention. When an interdependent network faces attacks, the failure can propagate along inter-links to the whole network and the damage caused by malicious attacks is more serious. However, in terms of designing the robust inter-links of interdependent networks, most of the existing strategies target at random attacks and make little use of the inner structure of interdependent networks. In this paper, we propose a specific memetic algorithm (MA) for optimizing the inter-links to enhance the robustness of interdependent networks against malicious attacks, termed as MA-RINint. Moreover, we design an effective crossover operator based on retaining the inter-links of adjacent nodes and a local search operator according to the degree of nodes. In the experiments, we compare the proposed algorithm with five existing methods on three types of interdependent networks with different sizes, and the experimental results show that MA-RINint performs excellently in enhancing the robustness of interdependent networks.

The utilization of stratosphere in earth observing is getting more attention. For maximizing the usage of stratosphere space, it is of vital importance to deploy the platforms of which airship is the representative, properly. Under such a background, a multiobjective model for the deployment problem of multiple airships in the earth observing system (MOM_DP_MAEOS), considering the number of covered tasks and the total profits of the observable tasks, is designed. Furthermore, a multiobjective evolutionary algorithm based on decomposition (MOEA/D) with dynamic weight vectors (DW) and stable matching (STM) schemes (MOEA/D_DW-STM) is proposed to optimize the deployment problem in this paper. DW is applied in the process of updating the individuals in the neighborhoods, playing the role of assisting local search. STM, including a bi-direction selection process, is designed to overcome the shortage that only the process of choosing solutions to subproblems exists in MOEA/D. Besides, K-means clustering operator applied in the initialization and the normalization operator for balancing the search efforts of each objective are applied. A variety of experiments are carried out on different kinds of benchmarks to verify the effectiveness of MOEA/D_DW-STM and the rationality of MOM_DP_MAEOS. Compared with the original MOEA/D and nondominated sorting genetic algorithm II (NSGA-II), the designed algorithm obtains better Pareto fronts (PF) under the same computational cost.

Video-text retrieval is an important yet challenging task in vision-language understanding, which aims to learn a joint embedding space where related video and text instances are close to each other. Most current works simply measure the video-text similarity based on video-level and text-level embeddings. However, the neglect of more fine-grained or local information causes the problem of insufficient representation. Some works exploit the local details by disentangling sentences, but overlook the corresponding videos, causing the asymmetry of video-text representation. To address the above limitations, we propose a Hierarchical Alignment Network (HANet) to align different level representations for video-text matching. Specifically, we first decompose video and text into three semantic levels, namely event (video and text), action (motion and verb), and entity (appearance and noun). Based on these, we naturally construct hierarchical representations in the individual-local-global manner, where the individual level focuses on the alignment between frame and word, local level focuses on the alignment between video clip and textual context, and global level focuses on the alignment between the whole video and text. Different level alignments capture fine-to-coarse correlations between video and text, as well as take the advantage of the complementary information among three semantic levels. Besides, our HANet is also richly interpretable by explicitly learning key semantic concepts. Extensive experiments on two public datasets, namely MSR-VTT and VATEX, show the proposed HANet outperforms other state-of-the-art methods, which demonstrates the effectiveness of hierarchical representation and alignment. Our code is publicly available at https://github.com/Roc-Ng/HANet.

Decomposition-based evolutionary algorithms have been quite successful in dealing with multiobjective optimization problems. Recently, more and more researchers attempt to apply the decomposition approach to solve many-objective optimization problems. A many-objective evolutionary algorithm based on decomposition with correlative selection mechanism (MOEA/D-CSM) is also proposed to solve many-objective optimization problems in this article. Since MOEA/D-SCM is based on a decomposition approach which adopts penalty boundary intersection (PBI), a set of reference points must be generated in advance. Thus, a new concept related to the set of reference points is introduced first, namely, the correlation between an individual and a reference point. Thereafter, a new selection mechanism based on the correlation is designed and called correlative selection mechanism. The correlative selection mechanism finds its correlative individuals for each reference point as soon as possible so that the diversity among population members is maintained. However, when a reference point has two or more correlative individuals, the worse correlative individuals may be removed from a population so that the solutions can be ensured to move toward the Pareto-optimal front. In a comprehensive experimental study, we apply MOEA/D-CSM to a number of many-objective test problems with 3 to 15 objectives and make a comparison with three state-of-the-art many-objective evolutionary algorithms, namely, NSGA-III, MOEA/D, and RVEA. Experimental results show that the proposed MOEA/D-CSM can produce competitive results on most of the problems considered in this study.

In many real-world networks, the structural connections of networks and the attributes about each node are always available. We typically call such graphs attributed networks, in which attributes always play the same important role in community detection as the topological structure. It is shown that the very existence of overlapping communities is one of the most important characteristics of various complex networks, while the majority of the existing community detection methods was designed for detecting separated communities in attributed networks. Therefore, it is quite challenging to detect meaningful overlapping structures with the combination of node attributes and topological structures. Therefore, in this article, we propose a multiobjective evolutionary algorithm based on the similarity attribute for overlapping community detection in attributed networks (MOEA-SA$_{OV}$ ). In MOEA-SA$_{OV}$ , a modified extended modularity $EQ_{OV}$ , dealing with both directed and undirected networks, is well designed as the first objective. Another objective employed is the attribute similarity $S_{A}$ . Then, a novel encoding and decoding strategy is designed to realize the goal of representing overlapping communities efficiently. MOEA-SA$_{OV}$ runs under the framework of the nondominated sorting genetic algorithm II (NSGA-II) and can automatically determine the number of communities. In the experiments, the performance of MOEA-SA$_{OV}$ is validated on both synthetic and real-world networks, and the experimental results demonstrate that our method can effectively find Pareto fronts about overlapping community structures with practical significance in both directed and undirected attributed networks.

In order to find the nodes with better propagation ability, a large body of studies on the influence maximization problem has been conducted. Several influence spreading models and corresponding optimization algorithms have been proposed and successfully identified the infusive seeds in single isolated networks. However, as indicated by some recent studies and online materials, modern networked systems tend to have more complicated structures and multiple layers, which makes it difficult for existing seed determination techniques to deal with these networks. Thus, finding influential nodes in realistic multiplex networks remains open. Therefore, this paper aims to design an extended influence spreading model to simulate the influence diffusion process in multiplex networks, based on which a memetic algorithm is developed to find the seeds that are influential in all network layers. Experimental results on synthetic and real-world networks validate the effectiveness of the proposed algorithm. These results are helpful for identifying potential propagators in multiplex social networks, and provide solutions to analyze and gain deeper insights into networked systems.

The problem of inferring nonlinear and complex dynamical systems from available data is prominent in many fields, including engineering, biological, social, physical, and computer sciences. Many evolutionary algorithm (EA)-based network reconstruction methods have been proposed to address this problem, but they ignore several useful information of network structure, such as community structure, which widely exists in various complex networks. Inspired by the community structure, this article develops a community-based evolutionary multiobjective network reconstruction framework to promote the reconstruction performance of EA-based network reconstruction methods due to their good performance; we refer this framework as CEMO-NR. CEMO-NR is a generic framework and any population-based multiobjective metaheuristic algorithm can be employed as the base optimizer. CEMO-NR employs the community structure of networks to divide the original decision space into multiple small decision spaces, and then any multiobjective EA (MOEA) can be used to search for improved solutions in the reduced decision space. To verify the performance of CEMO-NR, this article also designs a test suite for complex network reconstruction problems. Three representative MOEAs are embedded into CEMO-NR and compared with their original versions, respectively. The experimental results have demonstrated the significant improvement benefiting from the proposed CEMO-NR in 30 multiobjective network reconstruction problems (MONRPs).

In recent research, hyper-heuristics have attracted increasing attention in various fields. The most appealing feature of hyper-heuristics is that they aim to provide more generalized solutions to optimization problems by searching in a high-level space of heuristics instead of direct problem domains. Despite the promising findings in hyper-heuristics, the design of more general search methodologies still presents a key research. Evolutionary multitasking is a relatively new evolutionary paradigm which attempts to solve multiple optimization problems simultaneously. It exploits the underlying similarities among different optimization tasks by transferring information among them, thus accelerating the optimization of all tasks. Inherently, hyper-heuristics and evolutionary multitasking are similar in the following three ways: 1) they both operate on third-party search spaces; 2) high-level search methodologies are universal; and 3) they both conduct cross-domain optimization. To integrate their advantages effectively, i.e., the knowledge-transfer and cross-domain optimization of evolutionary multitasking and the search in the heuristic spaces of hyper-heuristics, in this article, a unified framework of evolutionary multitasking graph-based hyper-heuristic (EMHH) is proposed. To assess the generality and effectiveness of the EMHH, population-based graph-based hyper-heuristics integrated with evolutionary multitasking to solve exam timetabling and graph-coloring problems, separately and simultaneously, are studied. The experimental results demonstrate the effectiveness, efficiency, and increased the generality of the proposed unified framework compared with single-tasking hyper-heuristics.

The robustness of complex networks is of great significance. Great achievements have been made in robustness optimization based on single measures, however, such networks may still be vulnerable to multiple attack scenarios. Therefore, recently, multiobjective robustness optimization of networks has received increasing attention. Nevertheless, several challenges remain to be addressed, including the different computational complexities in evaluating the objectives, insufficient diversity in the obtained networks, and high computational costs of the search process. In this article, we address the aforementioned challenges by developing a computationally efficient multiobjective optimization algorithm. Based on the unique features of complex networks, a new parallel fitness evaluation method guided by a network property parameter is designed and embedded in a reference vector-guided multiobjective evolutionary algorithm. In addition, a surrogate ensemble with heterogeneous inputs is constructed based on graph embedding information to efficiently estimate multiple robustness of networks. The proposed algorithm is validated on synthetic and real-world network data and our results show that the designed algorithm outperforms the state-of-the-art method with a marked improvement on the computational efficiency. Compared with other single-objective optimization methods, the proposed algorithm demonstrates a considerable exploitation ability.

Fuzzy cognitive maps (FCMs) have been successfully applied to time series forecasting. However, it still remains challenging to handle multivariate long nonstationary time series, such as EEG data, which may change rapidly and have patterns of trend. To overcome this limitation, in this article, we propose a fast prediction model to deal with multivariate long nonstationary time series based on the combination of elastic net and high order fuzzy cognitive map (HFCM), which is termed as ElasticNetHFCM. The designed FCM models each variable by one node and the high-order FCM helps to capture the patterns of trend. A case study on predicting human actions through the Electroencephalogram (EEG) data in the form of multichannel long nonstationary time series is investigated based on the proposed prediction model. Specifically, we first predict EEG signals based on the historical data, then a 1D-convolutionary neural network (1D-CNN) is developed to classify the predicted time series. The experimental results on the Grasp-and-Lift dataset show that the proposal can predict the EEG data with lower prediction error compared with the other regression methods. The area under the curve scores obtained on the Grasp-and-Lift dataset by 1D-CNN are higher than those obtained by state-of-the-art classification methods for EEG data in most cases. These results illustrate that the proposal can predict and classify multivariate long nonstationary time series with high accuracy and efficiency.

The fuzzy cognitive map (FCM) is an effective tool for modeling and simulating complex dynamic systems. The research on the problem of learning FCM from the available time series is outstanding. Many batch FCM learning methods have been proposed to address this issue and the performance of these methods is satisfactory. However, these batch-learning methods are difficult to cope with large-scale data sets (for example, the memory in computers is not enough to store all instances) and real-time streaming data, leading to the failure of real-time and online analysis of complex systems. In this article, unlike the existing batch learning methods, such as evolutionary and regression-based methods, we first extend the FCM learning to an online setting, and then develop an effective algorithm based on a follow-the-regularized-leader (FTRL)-proximal style learning algorithm to address the online FCM learning problem, termed as OFCM. The performance of OFCM is validated on constructed benchmark data sets, including synthetic data sets, and gene regulatory network reconstruction data sets. The experimental results demonstrate the merits of OFCM, which can effectively solve online FCM learning problems.

Weakly supervised anomaly detection is a challenging task since frame-level labels are not given in the training phase. Previous studies generally employ neural networks to learn features and produce frame-level predictions and then use multiple instance learning (MIL)-based classification loss to ensure the interclass separability of the learned features; all operations simply take into account the current time information as input and ignore the historical observations. According to investigations, these solutions are universal but ignore two essential factors, i.e., the temporal cue and feature discrimination. The former introduces temporal context to enhance the current time feature, and the latter enforces the samples of different categories to be more separable in the feature space. In this article, we propose a method that consists of four modules to leverage the effect of these two ignored factors. The causal temporal relation (CTR) module captures local-range temporal dependencies among features to enhance features. The classifier (CL) projects enhanced features to the category space using the causal convolution and further expands the temporal modeling range. Two additional modules, namely, compactness (CP) and dispersion (DP) modules, are designed to learn the discriminative power of features, where the compactness module ensures the intraclass compactness of normal features, and the dispersion module enhances the interclass dispersion. Extensive experiments on three public benchmarks demonstrate the significance of causal temporal relations and feature discrimination for anomaly detection and the superiority of our proposed method.

Generating both accurate and diverse recommendations is required for modern recommender systems. Accurate recommendations can well meet the needs of users, while diverse recommendations can bring users novelty, discover the unknown preferences of users, and can also alleviate the long tail problem. However, these two metrics are conflicting and it is very hard to improve both at the same time. Thus, a compromise needs to be made. The easiest way is using hyperparameters to combine different objective functions or the recommendations of different recommendation algorithms, but it is difficult to determine parameters. Another common strategy is applying multi-objective evolutionary algorithm to provide multiple recommendations for each user, but how to choose the final recommendation becomes a new problem. To this end, we propose a two-phase evolutionary algorithm-based recommendation framework, named EARF. In EARF, a novel fitness function is designed, which converts the evaluation of accuracy and diversity into a single objective and automatically trades off these two goals. Based on the property of recommendation problem and fitness function, the genetic representation and operators are redefined. The experiments on real-world rating datasets indicate that the EARF is effective and the proposed evolutionary algorithm can achieve a good balance between accuracy and diversity.

In radio frequency identification (RFID) networks, designing the positions and the transmitter power parameters of readers to achieve optimal coverage, interference, load balance, power consumption, and total cost is the task of RFID network planning (RNP) problems, which is the core challenge and an NP-hard optimization problem, where nature-inspired optimization methods have been proved extremely useful. In this paper, on account of the well-known multi-objective evolutionary algorithm based on decomposition (MOEA/D), we propose a Decomposition-based Multi-objective Self-adaptive Differential Evolution algorithm (MOSDE/D), in which all these objective functions are optimized simultaneously in a single run by decomposition, and the improved cyclic crowding distance sorting strategy is introduced to ensure the diversity of solutions. Our approach is tested on standard static RFID networks and compared with other algorithms. Our approach is better than other compared methods in terms of the coverage, interference, load balance, number of readers, and power consumption.

Graph embedding methods aim to represent nodes in the network into a low-dimensional and continuous vector space while preserving the topological structure and varieties of relational information maximally. Nowadays the structural connections of networks and the attribute information about each node are more easily available than before. As a result, many community detection algorithms for attributed networks have been proposed. However, the majority of these methods cannot deal with the overlapping community detection problem, which is one of the most significant issues in the real-world complex network study. In addition, it is quite challenging to make full use of both structural and attribute information instead of only focusing on one part. To this end, in this paper we innovatively combine the graph embedding with multiobjective evolutionary algorithms (MOEAs) for overlapping community detection problems in attributed networks. As far as I am concerned, MOEA is first used to integrate with graph embedding methods for overlapping community detection. We term our method as MOEA-GEOV, which can automatically determine the number of communities without any prior knowledge and consider topological structure and vertex properties synchronously. In MOEA-GEOV, two objective functions concerning community structure and attribute similarity are carefully designed. Moreover, a heuristic initialization method is proposed to get a relatively good initial population. Then a novel encoding and decoding strategy is designed to efficiently represent the overlapping communities and corresponding embedded representation. In the experiments, the performance of MOEA-GEOVis validated on both single and multiple attribute real-world networks. The experimental results of community detection tasks demonstrate our method can effectively obtain overlapping community structures with practical significance.

Path planning is a key technology to realize the automatic navigation of unmanned aerial vehicles (UAV), which has great significance both in theory and practical application. Evolutionary algorithms (EAs) are a type of nature-inspired computational methodologies for addressing complex real-world problems that cannot be solved well by mathematical or traditional modeling. However, the huge calculation of each iteration in the EAs greatly reduces the efficiency of the algorithm. In this paper, to accelerate the search speed of EAs and consider the dynamics of the environment, we propose a hierarchical recursive multi-agent genetic algorithm that can perform path planning in real time, termed as HR-MAGA. We used a strategy of layer-by-layer optimization on 3D maps with different resolution in the optimization process. The local search ability of the algorithm is improved by competition and self-learning process. In addition, the hierarchical recursive optimization process can greatly reduce the amount of computation and effectively deal with the dynamic characteristics of the environment. The experimental results show that HR-MAGA not only has strong global optimization ability, but more importantly, is able to generate collision free paths in real time after considering the physical limitations of the UAV and the dynamics of the environment.

The complex network is an important tool to represent relational data in nature and human society, which has been widely applied in various real-world application scenarios. A key issue for analyzing the features of networks is to represent the characteristic information in the network with rationality. Network embedding, attracting plenty of attention recently, aims to convert network information into a low-dimensional space while maintaining the structure and properties of the network maximally. Most of the existing network embedding methods intend to preserve the pairwise relationship or similarity between nodes, but the community structure, which is one of the most important features of complex networks, is largely ignored. In this article, we propose a novel network embedding method based on evolutionary algorithm (EA), termed as EA-NECommunity, which can preserve both the local proximity of nodes and the community structure of the network by optimizing a carefully designed objective function. The number of communities in the network can be automatically determined without any prior knowledge. Moreover, taking the intrinsic properties of the network embedding problems in mind, we design a local search operator based on multidirectional search which can effectively find feasible solutions. In the experiments, we first visualize the embedding representation obtained by different algorithms, and then use the problems of node clustering, node classification, and link prediction to further validate the quality of the embedding representation obtained. The experimental results show that EA-NECommunity outperforms other state-of-the-art algorithms on both the real life and synthetic networks.

Robust optimization of complex networks has attracted much attention in recent years. Although existing methods have been successful in achieving promising results, the computational cost for robust optimization tasks is extremely high, which prevents them from being further applied to large-scale networks. Thus, computationally efficient robust optimization methods are in high demand. This article proposes a low-cost method for estimating the robustness of networks with the help of graph embedding techniques and surrogate models. An evolutionary algorithm is then developed to find large-scale robust networks by combining the surrogate-assisted low-cost robustness estimator with the time-consuming real robustness measure by means of a model management strategy. The experimental results on different kinds of synthetic and real networks demonstrate the highly competitive search ability of the proposed algorithm. In addition, the algorithm is able to save up to 80% of the computation time for enhancing the robustness of large-scale networks compared with the state-of-the-art methods.

Learning large-scale fuzzy cognitive maps (FCMs) with the sparse attribute automatically from time series without prior knowledge remains a challenging problem. Most existing automated learning methods were applied to learn small-scale FCMs, and the learned FCMs are much denser than the maps constructed by human experts. Learning FCMs is the procedure of judging whether there are connecting edges and determining the weights of connecting edges. Thus, we transform the problem of learning FCMs into a biobjective optimization problem with two objects of minimizing the measure error and the number of nonzero entries, respectively. To solve this optimization problem, a preference-based iterative thresholding evolutionary biobjective optimization algorithm for learning FCMs is proposed. The strategy focuses on the knee area of the Pareto front (PF) with preference on the solutions near the true sparsity. Moreover, an initialization operator based on random forest is proposed to increase the speed of convergence toward the PF. The experiments on large-scale synthetic data with varying sizes and densities and the application to the gene regulatory network reconstruction problem have been conducted to demonstrate that our proposal matches or exceeds the existing state-of-the-art FCM learning approaches in most cases in terms of four measures, namely, Data_Error, Out_of_Sample_Error, Model Error, and SS_Mean. The Data_Error obtained by the proposed method can achieve 3.07E-06 even when the number of nodes reaches 200. We also demonstrate the effectiveness of the proposed initialization operator and the preference-based strategy, which can result in a fast convergence speed and higher accuracy.

The problem of time series prediction based on fuzzy cognitive maps (FCMs) is unresolved. Although many methods have been proposed to cope with this issue, the performance of these methods is far from satisfactory. Traditional FCM-based predictors have three limitations. First, current feature extraction operators are incapable of learning good representations of original time series. Second, current methods use just the output of FCMs to predict the next value; they do not directly utilize the important information of the latent features. Third, current FCM-based predictors optimize each component individually, thereby leading to low prediction accuracy. For example, these methods first optimize the feature extraction operator and then learn the FCMs from the latent features; they do not simultaneously optimize the whole prediction model. In this article, we develop a framework based on a sparse autoencoder (SAE) and a high-order FCM (HFCM) to address the time series prediction problem; we refer this framework as SAE-FCM. To overcome the first limitation of current methods, an SAE is employed to extract features from original time series. Unlike current FCM-based predictors, our method combines the output of both the SAE and the HFCM to calculate the predicted value, thereby overcoming the second limitation of traditional FCM-based predictors. In an application of the idea of “fine tuning” in deep learning, the weights of SAE-FCM can be updated by the batch gradient descent method if the prediction errors are great. Thus, we can optimize SAE-FCM as a whole and overcome the third limitation. We validate the performance of SAE-FCM on ten datasets. Compared with the experimental results obtained by using state-of-the-art methods, the experimental results obtained by using SAE-FCM demonstrate the effectiveness of our method. Extensive experiments also show that SAE-FCM can effectively overcome the above limitations.

How to build a generic deep one-class (DeepOC) model to solve one-class classification problems for anomaly detection, such as anomalous event detection in complex scenes? The characteristics of existing one-class labels lead to a dilemma: it is hard to directly use a multiple classifier based on deep neural networks to solve one-class classification problems. Therefore, in this article, we propose a novel DeepOC neural network, termed as DeepOC, which can simultaneously learn compact feature representations and train a DeepOC classifier. Only with the given normal samples, we use the stacked convolutional encoder to generate their low-dimensional high-level features and train a one-class classifier to make these features as compact as possible. Meanwhile, for the sake of the correct mapping relation and the feature representations' diversity, we utilize a decoder in order to reconstruct raw samples from these low-dimensional feature representations. This structure is gradually established using an adversarial mechanism during the training stage. This mechanism is the key to our model. It organically combines two seemingly contradictory components and allows them to take advantage of each other, thus making the model robust and effective. Unlike methods that use handcrafted features or those that are separated into two stages (extracting features and training classifiers), DeepOC is a one-stage model using reliable features that are automatically extracted by neural networks. Experiments on various benchmark data sets show that DeepOC is feasible and achieves the state-of-the-art anomaly detection results compared with a dozen existing methods.

Recommender systems are efficient tools to alleviate the information overload problem. The information core extraction problem aims at finding a group of users who carry reliable, objective information to represent the system to provide recommendations. Many greedy algorithms have been proposed to deal with this problem, but most algorithms only focus on finding an information core to achieve accurate recommendation results, losing sight of other recommendation objectives with equivalent importance. To this end, we model the information core extraction problem as a multiobjective optimization problem, and propose a multiobjective evolutionary algorithm to extract information cores, labeled as MOEA-IC. MOEA-IC extracts information cores with multi-property at the same time, which can provide candidate solutions with different properties for decision makers. In the experiments, the performance of MOEA-IC is validated on three datasets with varying selection rates and compared with that of two existing greedy algorithms. The experimental results demonstrate the efficiency of MOEA-IC and show that the information core extracted by MOEA-IC can not only be helpful in providing accuracy recommendation, but also provide recommendations of good performance in terms of coverage and diversity criteria. The significance of this study is that the information-core-based recommendation is timesaving, and decision makers can choose information cores with different properties provided by MOEA-IC based on practical requirements.

Gene regulatory networks (GRNs) denote the interrelation among genes in the genomic level. In reality, gene regulatory networks are presented as sparse networks, so using sparse models to represent GRNs is a meaningful task. Fuzzy cognitive maps (FCMs) have been used to reconstruct GRNs. However, the networks learned by automated derivate-free methods are much denser than those in practical applications. Moreover, the performance of current sparse FCM learning algorithms is worse than what we expect. The fireworks algorithm is an efficient and simple optimization algorithm. However, there are few fireworks algorithms currently used to solve the sparse optimization problem. To utilize the powerful learning ability of fireworks algorithms to learn sparse FCMs, we propose a sparse fireworks algorithm (SFWA-FCM). Compared with existing FCM learning algorithms, SFWA-FCM's excellent numerical fitting ability and sparse modeling ability are illustrated. In addition, SFWA-FCM is used to solve the problem of GRN reconstruction. On the GRN reconstruction benchmark DREAM4, SFWA shows the high accuracy. The good performance in learning sparse FCMs illustrates the effectiveness of SFWA-FCM, and the simplicity and scalability of the framework ensure that it can be adapted to a wide range of needs.

Classification-based optimization (CBO) is a recently proposed global optimization method which exhibits a good prospect. Previous studies have shown that CBO has a good performance when a function evaluation is cheap. However, its performance is far from being completely and precisely consummated in the optimization of an expensive black box function f. We term this task as multi-fidelity black-box optimization and develop MF-CBO, a novel method based on CBO. To the best of our knowledge, this is the first work to extend classification-based optimization methods to the multi-fidelity case. MF-CBO explores the space using the low fidelities and exploits the high fidelity on successively smaller regions. Experimental results demonstrate that MF-CBO outperforms the strategies which ignore the multi-fidelity information and other multi-fidelity methods on several real cases and synthetic examples.

Fuzzy cognitive maps (FCMs) are generally applied to model and analyze complex dynamical systems. However, the accuracy of population-based FCM learning algorithms is relatively low. Boosting is an effective method to improve the accuracy of any learning algorithm. To this end, we combine FCMs with boosting, termed as boosting fuzzy cognitive maps (BFCMs). The BFCM is an extension of FCMs and has a better performance on fast numerical reasoning than FCMs. In this paper, a real-coded genetic algorithm, which is a popular population-based learning algorithm, is improved on mutation operator and applied to learn the BFCM models, termed as RCGA-BFCM. In the experiments, RCGA-BFCM is applied to learn the BFCM from synthetic data with varying sizes and densities. The experimental results show that RCGA-BFCM can learn BFCMs with high accuracy from synthetic data. In addition, the performance of RCGA-BFCM is validated on the benchmark datasets DREAM3 and DREAM4. The experimental results show that RCGA-BFCM outperforms other learning algorithms obviously, which illustrates that RCGA-BFCM can reconstruct gene regulatory networks (GRNs) effectively.

Fault-tolerant syndrome measurement plays an important role in the process of quantum error correction, and considerable effort had been taken for reducing the physical overhead of syndrome measurement which including the ancilla qubits, the CNOT gates and the time-slots. The two extra qubits syndrome measurement technique, known as "flag"-style syndrome measurement, cuts down the number of extra qubits to the utmost. However, it works slowly because it measures only one syndrome at a time. We extend the technique to extract all syndromes of the distance-3 quantum error-correcting code at once. We propose a new method that increases the parallelism of the syndrome measurement circuit and reduces the time overhead by allocating and adjusting the order of CNOT gates for measuring data block reasonably, which we call dynamic time-slot allocation scheme, and which is applicable to both Hamming codes and color codes. For a CSS quantum error-correcting code with the number of stabilizers m and the maximum weight w, we only need 2m extra qubits and 2 × (w+2) time-slots for one-shot measurement of all syndromes.

Although the obtained accuracy on some lab-controlled facial expression datasets has been very high, the recognition of facial expressions in wild environments is still a challenging problem. Local Binary Patterns (LBP) is a widely used operator in facial expression recognition. However, there are few variations of LBP operators specifically designed for facial expression recognition. In this paper, we propose a novel representation approach called the Double Complete d-LBP (Double Cd-LBP) according to the characteristics of facial expressions. Two d-LBP are employed to represent details and the contour of faces separately, and complete LBP is used to take sign and magnitude components into account. Moreover, multi-scale LBP is exploited to obtain local texture and global information. We then use the extreme learning machine auto-encoder (ELM-AE) as the feature selection approach to learn the discriminative feature. Cascade forest is employed as the final decision classifier. Experiments conducted on the six facial expression databases, including both lab-controlled and wild environments databases, show that our method outperforms or on par with state-of-the-arts.

Most of the existing community detection algorithms are based on vertex connectivity. While in many real networks, each vertex usually has one or more attributes describing its properties which are often homogeneous in a cluster. Such networks can be modeled as attributed graphs, whose attributes sometimes are equally important to topological structure in graph clustering. One important challenge is to detect communities considering both topological structure and vertex properties simultaneously. To this propose, a multiobjective evolutionary algorithm based on structural and attribute similarities (MOEA-SA) is first proposed to solve the attributed graph clustering problems in this paper. In MOEA-SA, a new objective named as attribute similarity is proposed and another objective employed is the modularity . A hybrid representation is used and a neighborhood correction strategy is designed to repair the wrongly assigned genes through making balance between structural and attribute information. Moreover, an effective multi-individual-based mutation operator is designed to guide the evolution toward the good direction. The performance of MOEA-SA is validated on several real Facebook attributed graphs and several ego-networks with multiattribute. Two measurements, namely density and entropy , are used to evaluate the quality of communities obtained. Experimental results demonstrate the effectiveness of MOEA-SA and the systematic comparisons with existing methods show that MOEA-SA can get better values of and in each graph and find more relevant communities with practical meanings. Knee points corresponding to the best compromise solutions are calculated to guide decision makers to make convenient choices.

Fuzzy cognitive maps (FCMs) have been successfully used to model and predict stationary time series. However, it still remains challenging to deal with large-scale nonstationary time series, which have trend and vary rapidly with time. In this paper, we propose a time-series prediction model based on the hybrid combination of high-order FCMs (HFCMs) with the redundant wavelet transform to handle large-scale nonstationary time series. The model is termed as Wavelet-HFCM. The redundant Haar wavelet transform is applied to decompose original nonstationary time series into multivariate time series; then, the HFCM is used to model and predict multivariate time series. In learning HFCMs to represent large-scale multivariate time series, a fast HFCM learning method is designed on the basis of ridge regression to reduce the learning time. Finally, summing multivariate time series up yields the predicted time series at each time step. Compared with existing classical methods, the experimental results on eight benchmark datasets show the effectiveness of our proposal, indicating that our prediction model can be applied to various prediction tasks.

Various automatic learning algorithms have been proposed to learn fuzzy cognitive maps (FCMs), but most of them were only applied to learn small-scale FCMs and the learned maps obtained by such methods are usually much denser than the real maps. Learning FCMs requires the learning methods to not only determine the existence of links between concepts but also optimize the edge weights, which is the difficulty for FCM learning methods. Therefore, we propose a mutual information (MI)-based two-phase memetic algorithm (MA) for learning large-scale FCMs, termed as MIMA-FCM. In MIMA-FCM, the first phase is oriented to determine the existence of links between concepts by MI, which can reduce the search space significantly for MA, and then MA is used to optimize the edge weights according to the multiple observed response sequences in the second phase. Experiments on both synthetic and real-life data and the application for the gene regulatory network reconstruction problem demonstrate that the proposed method can not only find the plausible existence of links between concepts, but also optimize the edge weights rapidly. The comparison with existing algorithms shows that MIMA-FCM can learn large-scale FCMs with higher accuracy without expert knowledge.

The emergency logistics scheduling (ELS) is to enable the dispatch of emergency supplies to the victims of disasters timely and effectively, which plays a crucial role in large-scale disaster relief. In this paper, we first design a new multi-objective model that considers both the total unsatisfied time and transportation cost for the ELS problem in large-scale disaster relief (ELSP-LDR), which is on the scenery of multi-disasters and multi-suppliers with several kinds of resources and vehicles. Then, a modified non-dominated sorting genetic algorithm II (mNSGA-II) is proposed to search for a variety of optimal emergency scheduling plans for decision-makers. With the intrinsic properties of ELSP-LDR in mind, we design three repair operators to generate improved feasible solutions. Compared with the original NSGA-II, a local search operator is also designed for mNSGA-II, which significantly improves the performance. We conduct two experiments (the case of Chi-Chi earthquake and Great Sichuan Earthquake) to validate the performance of the proposed algorithm.

The design of robust networked structures is of significance in reality, and the integrity of network connections has been greatly emphasized in previous studies. However, besides structural integrity, a system should also keep the functionality when suffering from attacks and failures, i.e. robust community structure. Focusing on enhancing community robustness on complex networks, in this paper, based on a community robustness measure Rc, a multi-agent genetic algorithm, termed as MAGA-Rc, has been proposed to enhance the community robustness against attacks. The performance of MAGA-Rcis validated on several real-world networks, and the results show that MAGA-Rccould deal with the optimization of community robustness and outperforms several existing methods. The results provide convenience for networked property analyses and applicable to solve realistic optimization problems.

Existing studies indicated that it is crucial to design network structures with well tolerance against potential attacks and failures in reality, and several attack models have been proposed and lucubrated. Aiming at enhancing network robustness suffering from edge-based attack cascading failures, we first propose a measure, Rce, to numerically evaluate the robustness of networks under cascading failures, and then a memetic algorithm, termed as MA-Rce, is devised to optimize network robustness without changing the degree distribution. The experimental results on synthetic and real-world networks show that MA-Rcecan provide candidate networks with better anti-attack performance initialized by an initial network, also outperforms exist heuristic optimization algorithm, which facilitates theoretic analyses and provides potential solutions to realistic dilemmas in networked systems for decision makers.

With the frequent occurrence of large-scale disasters, such as landslide and earthquake, timely and effective emergency resource scheduling becomes more and more important. Lots of disasters need multi-period rescue to satisfy the demand of disaster areas. In order to find a better plan to achieve the multi-period disaster relief, in this paper, a multi-period emergency resource scheduling problem is solved using the multi-agent genetic algorithm (MAGA) considering the uncertainty of traffic. The experimental results show that multi-agent genetic algorithm is more effective than genetic algorithm (GA) for this problem and it has better convergence.

Reconstructing gene regulatory networks (GRNs) from expression data plays an important role in understanding the fundamental cellular processes and revealing the underlying relations among genes. Although many algorithms have been proposed to reconstruct GRNs, more rapid and efficient methods which can handle large-scale problems still need to be developed. The process of reconstructing GRNs can be formulated as an optimization problem, which is actually reconstructing GRNs from time series data, and the reconstructed GRNs have good ability to simulate the observed time series. This is a typical big optimization problem, since the number of variables needs to be optimized increases quadratically with the scale of GRNs, resulting an exponential increase in the number of candidate solutions. Thus, there is a legitimate need to devise methods capable of automatically reconstructing large-scale GRNs. In this paper, we use fuzzy cognitive maps (FCMs) to model GRNs, in which each node of FCMs represent a single gene. However, most of the current training algorithms for FCMs are only able to train FCMs with dozens of nodes. Here, a new evolutionary algorithm is proposed to train FCMs, which combines a dynamical multi-agent genetic algorithm (dMAGA) with the decomposition-based model, and termed as dMAGA-FCM D , which is able to deal with large-scale FCMs with up to 500 nodes. Both large-scale synthetic FCMs and the benchmark DREAM4 for reconstructing biological GRNs are used in the experiments to validate the performance of dMAGA-FCM D . The dMAGA-FCM D is compared with the other four algorithms which are all state-of-the-art FCM training algorithms, and the results show that the dMAGA-FCM D performs the best. In addition, the experimental results on FCMs with 500 nodes and DREAM4 project demonstrate that dMAGA-FCM D is capable of effectively and computationally efficiently training large-scale FCMs and GRNs.

Designing robust networks has attracted increasing attentions in recent years. Most existing work focuses on improving the robustness of networks against a specific type of attacks. However, networks which are robust against one type of attacks may not be robust against another type of attacks. In the real-world situations, different types of attacks may happen simultaneously. Therefore, we use the Pearson's correlation coefficient to analyze the correlation between different types of attacks, model the robustness measures against different types of attacks which are negatively correlated as objectives, and model the problem of optimizing the robustness of networks against multiple malicious attacks as a multiobjective optimization problem. Furthermore, to effectively solve this problem, we propose a two-phase multiobjective evolutionary algorithm, labeled as MOEA-RSFMMA. In MOEA-RSFMMA, a single-objective sampling phase is first used to generate a good initial population for the later two-objective optimization phase. Such a two-phase optimizing pattern well balances the computational cost of the two objectives and improves the search efficiency. In the experiments, both synthetic scale-free networks and real-world networks are used to validate the performance of MOEA-RSFMMA. Moreover, both local and global characteristics of networks in different parts of the obtained Pareto fronts are studied. The results show that the networks in different parts of Pareto fronts reflect different properties, and provide various choices for decision makers.

Sparse unmixing of hyperspectral data is an important technique aiming at estimating the fractional abundances of the end members. Traditional sparse unmixing is faced with the l0-norm problem which is an NP-hard problem. Sparse unmixing is inherently a multiobjective optimization problem. Most of the recent works combine cost functions into single one to construct an aggregate objective function, which involves weighted parameters that are sensitive to different data sets and difficult to tune. In this paper, a novel multiobjective cooperative coevolutionary algorithm is proposed to optimize the reconstruction term, the sparsity term and the total variation regularization term simultaneously. A problem-dependent cooperative coevolutionary strategy is designed because sparse unmixing encounters a large scale optimization problem. The proposed approach optimizes the nonconvex l0-norm problem directly and can find a better compromise between two or more competing cost function terms automatically. Experimental results on simulated and real hyperspectral data sets demonstrate the effectiveness of the proposed method.

Learning large-scale sparse fuzzy cognitive maps (FCMs) from observed data automatically without any prior knowledge remains an outstanding problem. Most existing methods are slow and have difficulty in dealing with large-scale FCMs, because of the large searching space. We develop a framework based on compressed sensing (CS), a convex optimization method, to learn large-scale sparse FCMs, called CS-FCM. Combining with the sparsity of FCMs, the task of learning FCMs is first decomposed into sparse signal reconstruction problems. The ability of CS to exactly recover the sparse signals provides CS-FCM the probability to exactly learn FCMs. In the experiments, CS-FCM is applied to learn both synthetic data with varying sizes and densities and real-life data. The results show that CS-FCM obtains good performance by just learning from a small amount of data. CS-FCM can effectively learn sparse FCMs with 1000 nodes and even more, which have one million weights to be determined. CS-FCM is also applied to reconstruct gene regulatory networks (GRNs), and the well-known benchmark datasets DREAM3 and DREAM4 are tested. The results show that CS-FCM also obtains high accuracy in reconstructing GRNs. CS-FCM establishes a paradigm for learning large-scale sparse FCMs with high accuracy.

The disaster emergency relief plays a vital role in reducing casualties and economic losses. Emergency logistics scheduling (ELS) aims at dispatching emergency resources to the victims of disasters, which is an important event of disaster relief. In this paper, a model for ELS in disaster relief is built that includes several suppliers with a variety of resources, several kinds of vehicles, and multiple disasters. To ensure timely and effective dispatching, an objective is first designed to minimize the completion time of scheduling and the total unsatisfied time of the whole relief. Then, a multi-agent genetic algorithm (MAGA) is proposed to solve this problem. Four evolutionary operators, namely, the crossover, mutation, self-learning and the effective neighborhood competition operators are designed for agents. The proposed algorithm is applied to the case of Chi-Chi earthquake in Taiwan, and the experimental results show that the performance of this algorithm is better than that of genetic algorithm and memetic algorithm.

In this paper, a new moving block sequence (MBS) representation for resource-constrained project scheduling problems (RCPSPs) is proposed, which is different from the classical activity list that has been widely used for RCPSPs. An activity in a project of RCPSPs has fixed duration and resource demands, thus, it can be modeled as a rectangle block whose height represents the resource demands and width the duration. Therefore, by modeling every activity in a project as a block, a project that consists of N activities can be represented as a permutation of N blocks that satisfy the precedence constraints. Then, for every activity in the project, four initial positions and corresponding move modes are designed, by using which activities can be moved from their initial positions to the appropriate locations that minimize the makespan of the project without violating the precedence and resource constraints. Based on this newly designed MBS representation, the multi-agent evolutionary algorithm (MAEA) is used for solving RCPSPs. The comparison with 16 existing state-of-the-art algorithms on benchmark J30 test set, which contains 480 instances in total, shows that the proposed algorithm is competitive in solving RCPSPs.

Finding local community structure is an appealing problem that has attracted increasing attentions. Currently, it is unrealistic to get the complete information from graphs that are too large or evolve quickly. Moreover, in many real situations, we are only interested in the local community structure of networks, but not the whole network, because the local community structures can provide us much micro analysis, which is complementary to the macroscopic analysis. Most existing methods for local community detection which are based on the source nodes are sensitive to the position of source nodes. Thus, in this paper, a new multi-agent genetic algorithm (MAGA) is proposed to find local community (LC) based on the tightest nodes rather than the given source node, which is termed as MAGA-LC. MAGA-LC first finds a set of tightest nodes, and then extends the tightest nodes to get a local community. In the experiments on synthetic and real networks, MAGA-LC can get a high F-Measure score and is quite effective and flexible in identifying local communities, and is robust to the positions of source nodes.

Evolutionary algorithms are powerful tools for optimizing problems, and their performance in various fields is a continuous subject of research. Network reconstruction is the problem of trying to discover the original structure of an existing network using limited information. In this paper, we attempt to explore the ability of evolutionary algorithms to reconstruct networks by using the degree of each node as the available information. To achieve this, we introduce a novel method of representing networks with each edge being a value that corresponds to the likelihood of its existence. Moreover, we design two fitness functions that only use the degree of each node to determine the reconstruction quality, and analyze and compare them using fitness landscape and schema analysis for small networks, and verify the performance using two evolutionary algorithms for larger networks.

Unexpected accidents, such as earthquakes, snowstorms, and tsunamis, occur frequently at present. Emergency management is an important subject in both management science and social science, and has attracted increasing attentions. It is very important to determine emergency resources scheduling quickly and efficiently from multiple emergency logistics centers, as supply points, to multiple disaster affected points. In order to improve the efficiency of supplying organization and reduce casualties and economic losses, a decision support model whose target is to minimize the earliest rescuing time, the latest rescuing time and the number of supply activities simultaneously is first designed. Then, a multiagent genetic algorithm using natural coding is proposed to solve the designed problem. Computational experiments show that the proposed model is reasonable and the proposed algorithm is valid. At the same time, the scheduling found by the proposed algorithm can help decision-makers make a rational decision.

Module identification or community detection in complex networks has become increasingly important in many scientific fields because it provides insight into the relationship and interaction between network function and topology. In recent years, module identification algorithms based on stochastic optimization algorithms such as evolutionary algorithms have been demonstrated to be superior to other algorithms on small- to medium-scale networks. However, the scalability and resolution limit (RL) problems of these module identification algorithms have not been fully addressed, which impeded their application to real-world networks. This paper proposes a novel module identification algorithm called cooperative co-evolutionary module identification to address these two problems. The proposed algorithm employs a cooperative co-evolutionary framework to handle large-scale networks. We also incorporate a recursive partitioning scheme into the algorithm to effectively address the RL problem. The performance of our algorithm is evaluated on 12 benchmark complex networks. As a medical application, we apply our algorithm to identify disease modules that differentiate low- and high-grade glioma tumors to gain insights into the molecular mechanisms that underpin the progression of glioma. Experimental results show that the proposed algorithm has a very competitive performance compared with other state-of-the-art module identification algorithms.

Fuzzy cognitive maps (FCMs) are cognition fuzzy influence graphs, which are based on fuzzy logic and neural networks. Many automated learning algorithms have been proposed to reconstruct FCMs from data, but most learned maps using such methods are much denser than those constructed by human experts. To this end, we first model the FCM learning problem as a multiobjective optimization problem, and then propose a multiobjective evolutionary algorithm, labeled as MOEA-FCM, to learn FCM models. MOEA-FCM is able to learn FCMs with varying densities at the same time from input historical data, which can provide candidate solutions with different properties for decision makers. In the experiments, the performance of MOEA-FCM is validated on both synthetic and real data with varying sizes and densities. The experimental results demonstrate the efficiency of MOEA-FCM and show that MOEA-FCM can not only reconstruct FCMs with high accuracy without expert knowledge, but also create a diverse Pareto optimal front which consists of FCMs with varying densities. The significance of this study is that decision makers can choose different FCM models provided by MOEA-FCM based on their practical requirements.

In order to reconstruct large-scale gene regulatory networks (GRNs) with high accuracy, a robust evolutionary algorithm, a dynamic multiagent genetic algorithm (dMAGA), is proposed to reconstruct GRNs from time-series expression profiles based on fuzzy cognitive maps (FCMs) in this paper. The algorithm is labeled as dMAGAFCM-GRN. In dMAGAFCM-GRN, agents and their behaviors are designed with the intrinsic properties of GRN reconstruction problems in mind. All agents live in a lattice-like environment, and the neighbors of each agent are changed dynamically according to their energy in each generation. dMAGAFCM-GRN can learn continuous states directly for FCMs from data. In the experiments, the performance of dMAGAFCM-GRN is validated on both large-scale synthetic data and the benchmark DREAM3 and DREAM4. The experimental results show that dMAGAFCM-GRN is able to effectively learn FCMs with 200 nodes; that is, 40 000 weights need to be optimized. The systematic comparison with five existing algorithms shows that dMAGAFCM-GRN outperforms all other algorithms and can approximate the time series with high accuracy.

In this paper, we propose a differential evolution algorithm to solve the resource investment problem (RIP) with tardiness, which is one class of project scheduling problems. The tardiness of a project is allowed with defined penalty. We adapt a self-adaptive differential evolution algorithm combined with a local search operator to solve this problem. The performance of this algorithm is evaluated using 450 problem instances. The results show that these instances can reach their optimal solutions in a fixed number of schedules evaluated. The experimental results are quite satisfactory.

Multi-objective optimization problems with many objective functions (3> 3) are difficult to solve. This is because the time complexity of optimization algorithms often grows fast with the number of objective functions and the results of many objective optimization algorithms (Pareto front approximation) require large memory and their interpretation can be difficult for the decision maker. It is therefore attractive to reduce complexity of these problems. This can be achieved by decomposing them into a set of independent lower dimensional subproblems, or by aggregating some objective functions into a single objective function. This work introduces a new approach for decomposition and aggregation based on techniques from social network analysis. The key idea is to interpret an objective function as a node (agent) in a social network, and arcs between nodes indicate relationships: Negatively weighted arcs stand for conflicting objectives, zero weighted arcs for independent objectives, and positively weighted arcs for objectives that support each other. Using well-known algorithms BGLL for community detection we show that — given certain preconditions — it is possible to decompose a many objective optimization problem to a set of lower dimensional multi-objective optimization problems. This makes it easier to solve the problem and interpret the resulting trade-off (hyper-)surfaces. In the paper, after introducing the idea of Communtiy Detection for Many-Objective Optimization (CoDeMO), we lay out an interactive workflow and test it on simple, scalable many-objective optimization problems-variants of facility location problems — and thereby provide a prove-of-concept study.

In this paper, we propose a differential evolution algorithm with local search to solve the resource investment project scheduling problems (RIPSPs), labeled as DELS-RIPSP. Project tardiness is not permitted during the process of optimization. DELS-RIPSP improves the population quality by changing existing chromosomes to those with better fitness using the local search operator in order to reduce resource cost. The performance of DELS-RIPSP is validated on 450 benchmark problems, including Mohring instances and ProGen instances with 10, 14 and 20 non-dummy activities. The percentages of optimal solutions under a fixed number of evaluations are reported. The experimental results illustrate the effectiveness of the proposed algorithm and its potential for solving RIPSPs.

In this paper, the multi-agent genetic algorithm (MAGA) is combined with the variable neighborhood search (VNS) to solve resource investment project scheduling problems (RIPSPs). An agent, coded by a valid activity list and a capacity list, represents a candidate solution to the RIPSPs. All agents live in a lattice-like environment, with each agent fixed on a lattice point. To increase energies, a series of operators, namely crossover, mutation, competition, self-learning and a VNS, are designed. The effectiveness of the algorithm is demonstrated through experiments on Möhring instances, synthetic instances and generated instances of J10, J14 and J20. The tests results are satisfactory.

With the coming of big data age, the data usually present in a huge magnitude such as TB or more. These data contain both useful and useless information. Therefore, techniques which can effectively analyze these data are in urgent demand. In practice, dealing with Electroencephalographic (EEG) signals with Independent Component Analysis (ICA) approximates to a big optimization problem because it requires real-time, or at least automatic in dealing with signals. Thus, in the Optimization of Big Data 2015 Competition, the problem abstracted from dealing with EEG signals through ICA is modeled as a big optimization problem (BigOpt). Evolutionary optimization techniques have been successfully used in solving various optimization problems, and in the age of big data, they have attracted increasing attentions. Since the multi-agent genetic algorithm (MAGA) shows a good performance in solving large-scale problems, in this paper, based on the framework of MAGA, an MAGA is proposed for solving the big optimization problem, which is labeled as MAGA-BigOpt. In MAGA-BigOpt, the competition and self-learning operators are redesigned and combined with crossover and mutation operators to simulate the cooperation, competition, and learning behaviors of agents. Especially, in the self-learning operator, agents quickly find decreasing directions to improve itself with a heuristic strategy. In the experiments, the performance of MAGA-BigOpt is validated on the given benchmark problems from the Optimization of Big Data 2015 Competition, where both the data with and without noise are used. The results show that MAGA-BigOpt outperforms the baseline algorithm provided by the competition in both cases with lower computational costs.

Fuzzy cognitive maps (FCMs) are cognition fuzzy influence graphs, which are based on fuzzy logic and neural network. In this paper, we propose a novel method combining Memetic Algorithms (MAs) and Neural Networks (NNs) to learn large-scale FCMs, which is labeled as MA-NN-FCM. In MA-NN-FCM, MAs are used to determine the regulatory connections in the network from multiple observed response sequences and NNs are used to calculate the interactions between concepts. In the experiments, the performance of MA-NN-FCM is validated on synthetic data with different number of nodes. The experimental results demonstrate the efficiency of our method, and show MA-NN-FCM can construct FCMs with high accuracy without expert knowledge. The performance of MA-NN-FCM is better than that of other FCM learning algorithms, such as ant colony optimization, non-linear Hebbian learning, and real-coded genetic algorithm.

In this paper, we present a new Markov Random Field based FCM image segmentation algorithm. A new energy function is proposed to utilize the spatial and contextual information simultaneously. In the proposed energy function, we use a weighted distance to reflect the different effects of neighborhood pixels. By using the new energy function, the new algorithm has a better performance in noise-corrupted images. Experimental results on real and synthetic images show our method is effective.

Various types of social relationships, such as friends and foes, can be represented as signed social networks (SNs) that contain both positive and negative links. Although many community detection (CD) algorithms have been proposed, most of them were designed primarily for networks containing only positive links. Thus, it is important to design CD algorithms which can handle large-scale SNs. To this purpose, we first extend the original similarity to the signed similarity based on the social balance theory. Then, based on the signed similarity and the natural contradiction between positive and negative links, two objective functions are designed to model the problem of detecting communities in SNs as a multiobjective problem. Afterward, we propose a multiobjective evolutionary algorithm, called MEAs-SN. In MEAs-SN, to overcome the defects of direct and indirect representations for communities, a direct and indirect combined representation is designed. Attributing to this representation, MEAs-SN can switch between different representations during the evolutionary process. As a result, MEAs-SN can benefit from both representations. Moreover, owing to this representation, MEAs-SN can also detect overlapping communities directly. In the experiments, both benchmark problems and large-scale synthetic networks generated by various parameter settings are used to validate the performance of MEAs-SN. The experimental results show the effectiveness and efficacy of MEAs-SN on networks with 1000, 5000, and 10,000 nodes and also in various noisy situations. A thorough comparison is also made between MEAs-SN and three existing algorithms, and the results show that MEAs-SN outperforms other algorithms.

Planning problems, such as mission capability planning in defense, can traditionally be modeled as a resource investment project scheduling problem (RIPSP) with unconstrained resources and cost. This formulation is too abstract in some real-world applications. In these applications, the durations of tasks depend on the allocated resources. In this paper, we first propose a new version of RIPSPs, namely extended RIPSPs (ERIPSPs), in which the durations of tasks are a function of allocated resources. Moreover, we introduce a resource proportion coefficient to manifest the contribution degree of various resources to activities. Since the more realistic nature of projects in practice implies that the circumstances under which the plan will be executed are stochastic in nature, we present a stochastic version of ERIPSPs, namely stochastic extended RIPSPs (SERIPSPs). To solve SERIPSPs, we first use scenarios to capture the space of possibilities (i.e., stochastic elements of the problem). We focus on three sources of uncertainty: duration perturbation, resource breakdown, and precedence alteration. We propose a robustness measure for the solutions of SEPIPSPs when uncertainties interact. We then formulate an SERIPSP as a multiobjective optimization model with three optimization objectives: makespan, cost, and robustness. A knowledge-based multiobjective evolutionary algorithm (K-MOEA) is proposed to solve the problem. The mechanism of K-MOEA is simple and time efficient. The algorithm has two main characteristics. The first is that useful information (knowledge) contained in the obtained approximated nondominated solutions is extracted during the evolutionary process. The second is that extracted knowledge is utilized by updating the population periodically to guide subsequent search. The approach is illustrated using a synthetic case study. Randomly generated benchmark instances are used to analyze the performance of the proposed K-MOEA. The experimental results illustrate the effectiveness of the proposed algorithm and its potential for solving SERIPSPs.

Understanding the emergence of cooperation among selfish individuals is an enduring conundrum in evolutionary biology, which has been studied using a variety of game theoretical models. Most of the previous studies presumed that interactions between individuals are discrete, but behavior in real systems can hardly be expected to have this dramatically discrete nature. In addition, existing research on continuous strategy games mostly focus on infinite well-mixed populations. Especially, there is few theoretical work on their evolutionary dynamics in structured populations. In the previous work [1], we theoretically studied the game dynamics of continuous strategies in a spatially structured population with its average degree k ≥ 3 under weak selection. Here, we study their evolutionary dynamics under weak selection on a cycle (k = 2), where each individual only interacts with its two immediate neighbors. Using the concept of fixation probability, we derive exact conditions for natural selection favoring one strategy over another for three update rules, called `birth-death', `death-birth', and `imitation'. It shows that for continuous strategy games, the same conditions are derived; especially, the simple rule b/c >; k is valid as well, where b/c is the benefit-to-cost ratio of an altruistic act. In addition, we present a network gain decomposition of the game equilibrium, which might provide a new view of network reciprocity, one of five mechanisms for evolution of cooperation.

A novel clustering algorithm called Immune Memetic Clustering Algorithm (IMCA) is proposed in the paper. IMCA combines Immune Clone Selection and Memetic algorithm; Two populations are used in the evolutionary process. Clone reproduction and selection, Memetic mutation, crossover, individual learning and selection are adopted to evolve the two populations. After watershed proceeding, extracting the texture features of an image and encoding them with real numbers, IMCA is used to partition these features, and the final segmentation result is obtained. This approach is applied to segment three types of images, including artificial synthetic texture images, natural images, and SAR images, the experimental results show the effectiveness of the proposed algorithm.

One of the major challenges in the field of evolutionary algorithms (EAs) is to characterise which kinds of problems are easy and which are not. Researchers have been attracted to predict the behaviour of EAs in different domains. We introduce fitness landscape networks (FLNs) that are formed using operators satisfying specific conditions and define a new predictive measure that we call motif difficulty (MD) for comparison-based EAs. Because it is impractical to exhaustively search the whole network, we propose a sampling technique for calculating an approximate MD measure. Extensive experiments on binary search spaces are conducted to show both the advantages and limitations of MD. Multidimensional knapsack problems (MKPs) are also used to validate the performance of approximate MD on FLNs with different topologies. The effect of two representations, namely binary and permutation, on the difficulty of MKPs is analysed.

Based on texture features, we propose an unsupervised image classification method by using a novel evolutionary clustering technique, namely multiagent genetic clustering algorithm (MAGAc). In MAGAc, the clustering problem is considered from an optimization viewpoint. Each agent is a matrix of real numbers representing the cluster centers. Agents interact with others under the pressure of environment to search the best partition of data. After extracting texture features from an image, MAGAc determines the partition of feature vectors using evolutionary search. In experiments, six UCI datasets and four artificial textural images are used to test the performance of MAGAc. The experimental results show that in terms of cluster quality, MAGAc outperforms the K-means algorithm and a genetic algorithm-based clustering technique.

Many planning problems, such as mission capability planning, can be modelled as project scheduling problems. Unlike conventional deterministic project scheduling problems, project scheduling problems involve uncertainty and the execution of the plan is very likely to be perturbed by many factors. In other words, the circumstances under which the plan will be executed are changing and stochastic. In this paper, we first use scenarios to represent the stochastic elements in the problem; these are: perturbation strength and perturbation occurrence time. We define and explain the Stochastic Resource Investment Project Scheduling (SRIPS) problem. A multi-objective optimization model of SRIPS is proposed where three optimization objectives are considered simultaneously: makespan, cost, and robustness. A multi-objective genetic algorithm is employed to solve the problem. Finally, we generate two test problems with 30 and 60 non-dummy activities to validate the performance of the proposed approach and analyze the sensitivity of the results to different parameter settings.

Cooperation is a fundamental principle of all biological systems. Most previous studies presumed that the interactions between individuals are discrete, namely, each individual offers either cooperation or defection. This discrete strategy seems unrealistic in real systems and cooperative behavior in nature should be viewed as a continuous trait. Existing research work on games with a continuous strategy mainly focuses on infinite well-mixed populations. Additionally, our previous work showed that there is a considerable difference in terms of equilibria between continuous and discrete strategy games on graphs under strong selection. This paper studies the game dynamics in finite structured populations under weak selection using the stochastic dynamics based on respectively the mutant fixation probability (ργ) and the fixation probability ratio of mutant to resident (ργ/ρχ). For three update rules, called 'birth death' (BD), 'death-birth' (DB) and 'imitation' (IM), we derive exact conditions for natural selection favoring one strategy over another. Comparing discrete strategy games, we find that for continuous ones (i) the rule, b/c >; k, is also valid; (ii) the same selection conditions are also derived using ργ/ρχ; however, (iii) the selection conditions obtained using ργ and ργ/ρχ are the same instead of different; and (iv) interestingly, the '1/3' rule is not observed for DB and IM updating.

Understanding complex networks in the real world is a nontrivial task. In the study of community structures we normally encounter several examples of these networks, which makes any statistical inferencing a challenging endeavor. Researchers resort to computer-generated networks that resemble networks encountered in the real world as a means to generate many networks with different sizes, while maintaining the real-world characteristics of interest. The generation of networks that resemble the real world turns out in itself to be a complex search problem. We present a new rewiring algorithm for the generation of networks with unique characteristics that combine the scale-free effects and community structures encountered in the real world. The algorithm is inspired by social interactions in the real world, whereby people tend to connect locally while occasionally they connect globally. This local-global coupling turns out to be a powerful characteristics that is required for our proposed rewiring algorithm to generate networks with community structures, power law distributions both in degree and in community size, positive assortative mixing by degree, and the rich-club phenomenon.

Both separated and overlapping communities are useful to analyze real networks in different situations. However, to the best of our knowledge, existing community detection methods based on Evolutionary Algorithms (EAs) can detect separate communities only. This is because it is difficult to represent overlapping communities in ways that are suitable for EAs. In this paper, we first design a representation method that can represent each individual as both separated and overlapping communities without assigning the number of communities in advance. We then design three objective functions to guide the evolutionary process in different conditions. Finally, based on the designed representation and objective functions, we propose a multiobjective evolutionary algorithm to solve CDPs (MEA_CDPs) under the framework of NSGA-II. In the experiments, 4 well-known real-life benchmark networks are used to validate the performance of MEA_CDPs, and the results shown that MEA_CDPs not only can find high quality communities, but also can detect both separated and overlapping communities at the same time, and present multiple types of communities. Moreover, the overlapping nodes identified by MEA_CDPs are really ambiguous according to their edge distributes in different communities. This illustrates the effectiveness of the objective functions we designed.

An important aspect of airlift problems is to find the smallest fleet of aircraft to move cargo from one or more locations to a destination. In critical airlift operations, such as emergency evacuations, disaster relief and defence operations, a compromise needs to be struck between minimizing the time needed for completing all tasks and minimizing the size of the fleet. Usually, the time to complete a task is stochastic. A deterministic model, therefore, will under-estimate fleet size which results in increased levels of risk to achieve the overall airlift mission. In this paper, we introduce a stochastic version of the two-dimensional bin packing problem. We test a number of objective functions to measure different levels of risk. We then use an evolutionary multi-objective algorithm to solve a number of test problems. Analysis demonstrates that the different risk functions and level of variability/uncertainty in performing each task affect solutions non-linearly. Moreover, the multi-objective approach provides the analyst with an estimate of the range of risk; thus solutions can be selected based on criticality of meeting airlift demands.

Based on our previous works, multiagent systems and evolutionary algorithms (EAs) are integrated to form a new algorithm for combinatorial optimization problems (CmOPs), namely, MultiAgent EA for CmOPs (MAEA-CmOPs). In MAEA-CmOPs, all agents live in a latticelike environment, with each agent fixed on a lattice point. To increase energies, all agents compete with their neighbors, and they can also increase their own energies by making use of domain knowledge. Theoretical analyses show that MAEA-CmOPs converge to global optimum solutions. Since deceptive problems are the most difficult CmOPs for EAs, in the experiments, various deceptive problems with strong linkage, weak linkage, and overlapping linkage, and more difficult ones, namely, hierarchical problems with treelike structures, are used to validate the performance of MAEA-CmOPs. The results show that MAEA-CmOP outperforms the other algorithms and has a fast convergence rate. MAEA-CmOP is also used to solve large-scale deceptive and hierarchical problems with thousands of dimensions, and the experimental results show that MAEA-CmOP obtains a good performance and has a low computational cost, which the time complexity increases in a polynomial basis with the problem size.

A novel evolutionary algorithm, Organizational Evolutionary Algorithm for SATisfiability problems (OEA_SAT), is proposed in this paper. OEA_SAT first divides a SAT problem into several sub-problems, and each organization is composed of a sub-problem. Thus, three new evolutionary operators, namely the self-learning operator, the annexing operator and the splitting operator are designed with the intrinsic properties of SAT problems in mind. Furthermore, all organizations are divided into two populations according to their fitness. One is called best-population, and the other is called non-best-population. The idea behind OEA_SAT is to solve the sub-problem first, and then synthesize the solution for the original problem by adjusting the variables which have conflicts. Since the dimensions of sub-problems are smaller and the sub-ones are easy to be solved compared with the original one, the computational cost is reduced in this way. In the experiments, 3700 benchmark SAT problems in SATLIB are used to test the performance of OEA_SAT. The number of variables of these problems is ranged from 20 to 250. Moreover, the performance of OEA_SAT is compared with those of two well-known algorithms, namely WalkSAT and RFEA2. All experimental results show that OEA_SAT has a higher success ratio and a lower computational cost. OEA_SAT can solve the problems with 250 variables and 1065 clauses by only 1.524 seconds and outperforms all the other algorithms.

This paper analyzes the numerical optimization problems from the viewpoint of multiagent systems. First, Macro-Agent Evolutionary Model (MacroAEM) is proposed with the intrinsic properties of decomposable functions in mind. In this model, a subfunction forms a macro-agent, and 3 new behaviors, namely competition, cooperation, and selfishness, are developed for macro-agents to optimizing objective functions. Second, MacroAEM model is integrated with multiagent genetic algorithm, which results a new algorithm, Hierarchical MultiAgent Genetic Algorithm (HMAGA). The convergence of HMAGA is analyzed theoretically and the results show that HMAGA converges to the global optima. In experiments, HMAGA is applied to a kind of complicated decomposable function, namely Rosenbrock function. The results show that HMAGA achieves a good performance, especially for the high-dimensional functions. In addition, the analyses on time complexity demonstrate that HMAGA has a good scalability.

In many applications, one class of data is presented by a large number of examples while the other only by a few. For instance, in our previous works on identification of peer-to-peer (P2P) Internet traffics, we observed that only about 30% of examples can be labeled as ldquoP2Prdquo using a port-based heuristic rule, and even fewer examples can be labeled in the future as more and more P2P applications use dynamic ports. In this paper, the effect of three resampling techniques on balancing the class distribution in training C4.5 and neural networks for identifying P2P traffic is studied. The experimental data were captured at our campus gateway. Nine datasets with different percentages of ldquoP2Prdquo examples and six datasets of different sizes with an actual percentage of about 30% of ldquoP2Prdquo examples are used in the experiments. The results show that resampling techniques are effective and stable, and random over-sampling is a quite good choice for P2P traffic identification considering a combination of the classification performance and time complexity.

We apply streaming data mining techniques, and in particular, concept-adapting very fast decision tree (CVFDT) to identify peer-to-peer (P2P) applications in Internet traffic, as the Internet data flows dynamically in large volumes (streaming data), and in P2P applications, new communities of peers often attend and old communities of peers often leave, requiring the identification methods to be capable of coping with concept drift, and updating the model incrementally. We captured Internet traffic at a main gateway router, performed pre-processing on the captured data, selected the most significant attributes, and prepared a training data stream to which the CVFDT model was applied. We tested our approach on a data stream with 3.5 million P2P and NonP2P traffic records. The results show that our approach can effectively deal with dynamic nature of streaming data and detect the changes in communities of peers. The classification accuracy is higher than 95%, and the method is well-scalable in both time and space complexities, making it competent for large-scale dynamic data. We extracted attributes only from the IP layer, eliminating the privacy concern associated with the techniques that use deep packet inspection.

A new nonslicing floorplan representation, the moving block sequence (MBS), is proposed in this paper. Our idea of the MBS originates from the observation that placing blocks on a chip has some similarities to playing the game, Tetrisreg. Since no extra constraints are exerted on solution spaces, the MBS is not only useful for evolutionary algorithms, but also for dealing with rectangular, convex rectilinear, and concave rectilinear blocks, similarly and simultaneously, without partitioning rectilinear blocks into subblocks. This is owed to a special structure designed for recording the information of both convex and concave rectilinear blocks in a uniform form. Theoretical analyses show that the computational cost of transforming an MBS to a floorplan with rectangular blocks, in terms of the number of blocks, is between linear and quadratic. Furthermore, as a follow-up of our previous works, a new organizational evolutionary algorithm (OEA) based on the MBS (MBS-OEA) is proposed. With the intrinsic properties of the MBS in mind, three new evolutionary operators are designed in the MBS-OEA. To test the performance of the MBS-OEA, benchmarks with hard rectangular, soft rectangular, and hard rectilinear blocks are used. The number of blocks in these benchmarks varies from 9 to 300. Also, the MBS-OEA and several well-designed existing algorithms are compared. The results show that the MBS-OEA can find high quality solutions for various problems. Additionally, the MBS-OEA shows a good performance in solving the problems with 300 hard rectangular blocks, 100 soft rectangular blocks, and 100 hybrid blocks, including both soft rectangular and hard rectilinear blocks. This illustrates that the MBS-OEA is not only suitable for solving a wide range of problems, but also competent for solving large-scale problems. Finally, a set of specific experiments is designed to identify the key component that is mainly responsible for the good performance of the MBS-OEA.

With the intrinsic properties of satisfiability problem (SAT problem) in mind, we integrate the multiagent systems and evolutionary algorithms to form a new algorithm, Multiagent Evolutionary Algorithm for SAT problem (MAEA-SAT). In MAEA-SAT, all agents live in a latticeilke environment. Making use of the designed behaviors, MAEA-SAT realizes the ability of agents to sense and act on the environment in which they live. During the process of interacting with the environment and other agents, each agent increases energy as much as possible, so that MAEA-SAT can find the optima. The benchmarks about SAT problems of different scales in SATLIB are used to test the performance of MAEA-SAT, and we compared MAEA-SAT with standard GA (namely SGA). The experimental results show that the MAEA-SAT obtained an outstanding performance in solving large-scale SAT problems.

Focusing on the floorplan problem, a non-slicing representation, moving block sequence(MBS), is introduced and suitable for evolutionary computation since no extra constraints are exerted on the solution space. Then we design a multiagent evolutionary algorithm with the intrinsic properties of MBS in mind, which is named as MAEA-MBS. In experiments, 17 benchmarks from MCNC and GSRC are used to test the performance of MAEA-MBS. The experimental results are compared with other 9 existing well-designed algorithms and demonstrate that the algorithm is quite promising.

Taking inspiration from the interacting process among organizations in human societies, this correspondence designs a kind of structured population and corresponding evolutionary operators to form a novel algorithm, Organizational Evolutionary Algorithm (OEA), for solving both unconstrained and constrained optimization problems. In OEA, a population consists of organizations, and an organization consists of individuals. All evolutionary operators are designed to simulate the interaction among organizations. In experiments, 15 unconstrained functions, 13 constrained functions, and 4 engineering design problems are used to validate the performance of OEA, and thorough comparisons are made between the OEA and the existing approaches. The results show that the OEA obtains good performances in both the solution quality and the computational cost. Moreover, for the constrained problems, the good performances are obtained by only incorporating two simple constraints handling techniques into the OEA. Furthermore, systematic analyses have been made on all parameters of the OEA. The results show that the OEA is quite robust and easy to use.

Taking inspiration from the interacting process among organizations in human societies, a new classification algorithm, organizational coevolutionary algorithm for classification (OCEC), is proposed with the intrinsic properties of classification in mind. The main difference between OCEC and the available classification approaches based on evolutionary algorithms (EAs) is its use of a bottom-up search mechanism. OCEC causes the evolution of sets of examples, and at the end of the evolutionary process, extracts rules from these sets. These sets of examples form organizations. Because organizations are different from the individuals in traditional EAs, three evolutionary operators and a selection mechanism are devised for realizing the evolutionary operations performed on organizations. This method can avoid generating meaningless rules during the evolutionary process. An evolutionary method is also devised for determining the significance of each attribute, on the basis of which, the fitness function for organizations is defined. In experiments, the effectiveness of OCEC is first evaluated by multiplexer problems. Then, OCEC is compared with several well-known classification algorithms on 12 benchmarks from the UCI repository datasets and multiplexer problems. Moreover, OCEC is applied to a practical case, radar target recognition problems. All results show that OCEC achieves a higher predictive accuracy and a lower computational cost. Finally, the scalability of OCEC is studied on synthetic datasets. The number of training examples increases from 100 000 to 10 million, and the number of attributes increases from 9 to 400. The results show that OCEC obtains a good scalability.

Since all graphs in the 1993 DIMACS graph coloring challenge are undirected, each edge should be only counted once. However, in some files each edge is counted once, whereas in others each edge is counted twice; so a systematical check on the DIMACS challenge is made to eliminate the inconsistencies. Besides, the experimental results of a previous paper by Blas et al. counted each violated edges twice and neglected the inconsistencies in the DIMACS challenge. So the correct experimental results of a previous paper by Blas et al are also given.

With the intrinsic properties of constraint satisfaction problems (CSPs) in mind, we divide CSPs into two types, namely, permutation CSPs and nonpermutation CSPs. According to their characteristics, several behaviors are designed for agents by making use of the ability of agents to sense and act on the environment. These behaviors are controlled by means of evolution, so that the multiagent evolutionary algorithm for constraint satisfaction problems (MAEA-CSPs) results. To overcome the disadvantages of the general encoding methods, the minimum conflict encoding is also proposed. Theoretical analyzes show that MAEA-CSPs has a linear space complexity and converges to the global optimum. The first part of the experiments uses 250 benchmark binary CSPs and 79 graph coloring problems from the DIMACS challenge to test the performance of MAEA-CSPs for nonpermutation CSPs. MAEA-CSPs is compared with six well-defined algorithms and the effect of the parameters is analyzed systematically. The second part of the experiments uses a classical CSP, n-queen problems, and a more practical case, job-shop scheduling problems (JSPs), to test the performance of MAEA-CSPs for permutation CSPs. The scalability of MAEA-CSPs along n for n-queen problems is studied with great care. The results show that MAEA-CSPs achieves good performance when n increases from 10(4) to 10(7), and has a linear time complexity. Even for 10(7)-queen problems, MAEA-CSPs finds the solutions by only 150 seconds. For JSPs, 59 benchmark problems are used, and good performance is also obtained.

In this paper, multiagent systems and genetic algorithms are integrated to form a new algorithm, multiagent genetic algorithm (MAGA), for solving the global numerical optimization problem. An agent in MAGA represents a candidate solution to the optimization problem in hand. All agents live in a latticelike environment, with each agent fixed on a lattice-point. In order to increase energies, they compete or cooperate with their neighbors, and they can also use knowledge. Making use of these agent-agent interactions, MAGA realizes the purpose of minimizing the objective function value. Theoretical analyzes show that MAGA converges to the global optimum. In the first part of the experiments, ten benchmark functions are used to test the performance of MAGA, and the scalability of MAGA along the problem dimension is studied with great care. The results show that MAGA achieves a good performance when the dimensions are increased from 20-10,000. Moreover, even when the dimensions are increased to as high as 10,000, MAGA still can find high quality solutions at a low computational cost. Therefore, MAGA has good scalability and is a competent algorithm for solving high dimensional optimization problems. To the best of our knowledge, no researchers have ever optimized the functions with 10,000 dimensions by means of evolution. In the second part of the experiments, MAGA is applied to a practical case, the approximation of linear systems, with a satisfactory result.