Cross-view geo-localization (CVGL) matches query images (e.g., drone) to geographically corresponding opposite-view imagery (e.g., satellite). While supervised methods achieve strong performance, their reliance on extensive pairwise annotations limits scalability. Unsupervised alternatives avoid annotation costs but suffer from noisy pseudo-labels due to intrinsic cross-view domain gaps. To address these limitations, we propose UniABG, a novel dual-stage unsupervised cross-view geo-localization framework integrating adversarial view bridging with graph-based correspondence calibration. Our approach first employs View-Aware Adversarial Bridging (VAAB) to model view-invariant features and enhance pseudo-label robustness. Subsequently, Heterogeneous Graph Filtering Calibration (HGFC) refines cross-view associations by constructing dual inter-view structure graphs, achieving reliable view correspondence. Extensive experiments demonstrate state-of-the-art unsupervised performance, showing that UniABG improves Satellite → Drone AP by +10.63% on University-1652 and +16.73% on SUES-200, even surpassing supervised baselines.

Cognitive diagnosis (CD), inferring student knowledge mastery based on historical response records, is crucial for personalized educational services such as adaptive practice and learning path planning. Existing CD models were built based on the assumption that student's response data is integral, overlooking the nonrandom missingness of data caused by student answering exercises selectively. This missingness generally leads to biased and incomplete observations, where confounders, such as selection bias and exposure bias, significantly undermine the accuracy of student knowledge modeling. To address missingness, we propose a Debiased Cognitive Diagnosis (DBCD) framework through the perspective of counterfactual modeling to remove exogenous confounders from the response data. Specifically, the proposed DBCD achieves debiasing for CD by applying the idea of contrastive learning to constrain the model's prediction distributions on both factual and counterfactual data. For a student, the factual data is his/her original response records, while the counterfactual data is generated by sampling the same number of exercises from all exercises of each concept through a similarity-based counterfactual sampling strategy. Considering the difficulty of directly removing the exogenous confounders for student, we devise a β-Variational Autoencoder to model their exogenous confounders within the latent representations of knowledge proficiency by leveraging exercise priors and student response patterns. Then, the learned representations are further combined with the vanilla student's ability embedding via a gating mechanism-based fusion for final diagnosis prediction of the model. Extensive experiments on real-world educational datasets demonstrate that the proposed DBCD effectively mitigates confounders and even outperforms existing methods, thereby validating the feasibility and effectiveness of the DBCD framework.

With the rapid advancement of intelligent education, Computerized Adaptive Testing (CAT) has attracted increasing attention by integrating educational psychology with deep learning technologies. Unlike traditional paper-and-pencil testing, CAT aims to efficiently and accurately assess ex- aminee abilities by adaptively selecting the most suitable items during the assessment process. However, its real-time and sequential nature presents limitations in practical scenarios, particularly in large-scale assessments where interaction costs are high, or in sensitive domains such as psychological evaluations where minimizing noise and interfer- ence is essential. These challenges constrain the applicability of conventional CAT methods in time-sensitive or resource- constrained environments. To this end, we first introduce a novel task called one-shot adaptive testing (OAT), which aims to select a fixed set of optimal items for each test-taker in a one-time selection. Meanwhile, we propose PEOAT, a Personalization-guided Evolutionary question assembly framework for One-hot Adaptive Testing from the perspec- tive of combinatorial optimization. Specifically, we began by designing a personalization-aware initialization strategy that integrates differences between examinee ability and ex- ercise difficulty, using multi-strategy sampling to construct a diverse and informative initial population. Building on this, we proposed a cognitive-enhanced evolutionary framework incorporating schema-preserving crossover and cognitively guided mutation to enable efficient exploration through infor- mative signals. To maintain diversity without compromising fitness, we further introduced a diversity-aware environmen- tal selection mechanism. The effectiveness of PEOAT is val- idated through extensive experiments on two datasets, com- plemented by case studies that uncovered valuable insights.

Low-Rank Adaptation (LoRA) is a widely utilized technique in topic of Parameter-Efficient Transfer Learning (PETL) which could use a limited number of trainable parameters to adapt the model to various downstream tasks. However, the setting of the locations and low-rank sizes in traditional LoRA relies heavily on the fixed and empirical values, which may hinder adaptability and lead to sharply decreasing performance, especially on some self-supervised pre-trained models. To alleviate this dilemma, we introduce a feature responsive LoRA (ResLoRA) method, a resource-efficient algorithm that automatically determines the LoRA modules’ required size based on the downstream task’s response. Firstly, we propose a Feature Decomposition loss (FD-loss) which leverages the feature singular values to mine the corresponding features of different downstream tasks, making the model parameters able to adequately represent downstream tasks. Subsequently, we leverage the Taylor expansion to measure the salience of the model parameters, then some high-efficient parameters with high significance could be leveraged to design a dynamically responsive LoRA. Specifically, the location and low-rank sizes of LoRA are determined based on the response parameters of the features for downstream tasks. Extensive experiments show that our ResLoRA achieves state-of-the-art performance, especially in the transfer capability of self-supervised models based on MoCo v3 and MAE. Our code is available at: https://github.com/wildboarman/ResLoRA.

Cross-view object-level image geo-localization (CVOIGL) aims to locate ground/drone-view query objects in satellite imagery. This task confronts two obstacles, namely view differences from imaging platform viewpoint changes and detection ambiguities from similar objects in large-scale satellite views. Existing methods typically employ uniform feature processing across objects while overlooking query-reference cross-view differences, leading to compromised localization precision when handling structurally analogous objects with scale variations. In this paper, we propose HiSymGeo, a Hierarchical Context Symbiosis framework with dual cooperative learning, achieving cross-view representation alignment and structural ambiguity resolution. Specifically, to mitigate cross-view differences, the Diversified View Enhancer (DiVE) first incorporates context-aware query enhancement for ground/drone-view representation while constructing scale-agnostic reference enhancement in satellite views to handle scale variations. These view-specific features then undergo contrastive learning via semantic-aware matching to align query and reference representations. Furthermore, the Query-Gated Multi-Expert View Fusion (QG-MEVF) introduces dynamic expert routing via multi-scale pyramidal representations, in which a Mixture-of-Experts (MoE) inspired architecture employs query-driven gating to adaptively select scale-specific fusion expert. This differentiable routing mechanism boosts structural discrimination against analogous objects, enabling precise object localization. Extensive ablation experiments demonstrate HiSymGeo's superiority, achieving state-of-the-art effectiveness while ensuring high cross-dataset generalization. We have released our code at https://github.com/chenqi142/HiSymGeo.

Test-time adaptation (TTA) has emerged as a key strategy to enhance vision-language models (VLMs) under real-world distribution changes. However, existing methods always face two problems: 1) The fundamental trade-off dilemma: parameter-free TTA retains inference efficiency but fails to correct modality misalignment, while prompt tuning adapts to shifts, incurs high computational costs, and lacks knowledge retention. 2) Discriminative collapse also exists in TTA when faced with fine-grained downstream tasks. To alleviate these two bottlenecks, we introduce Style-aware Contrastive Test-Time Adaptation (SCTTA), a novel framework that jointly addresses modality misalignment and discriminative collapse. Firstly, we introduce Style-aware Embedding Adaptation (SEA), which dynamically refines text embeddings by incorporating domain-specific style attributes, improving alignment between visual and textual modalities. Secondly, we propose Fine-grained Contrastive Adaptation (FCA), which enhances feature separation by enforcing contrastive learning with adaptive prototypes, reducing inter-class feature overlap in fine-grained tasks. In addition, we introduce Dual-Cache Model (DCM), which extends prior unimodal cache model to a multimodal cache for the first time. Eventually, it accumulates adaptation knowledge through a visual-cache (capturing evolving domain styles) and a textual-cache (retaining discriminative semantics), enabling long-term adaptation without additional overhead. Extensive experiments on 15 datasets demonstrate that our approach achieves state-of-the-art performance for both fine-grained and out-of-distribution dataset benchmarks. Furthermore, SCTTA continuously improves as more test samples accumulate, validating its sustainable adaptation capacity. Our code is available at https://github.com/alusi123/SCTTA.

Cognitive modeling, as an emerging technology in the field of computer-aided education, aims to explore students’ knowledge levels and learning abilities to achieve various intelligent educational applications. Although some existing work focuses on addressing the problem of student forgetting, it is still a less explored area how to naturally integrate the forgetting effect caused by the time interval between answering exercises into student knowledge state modeling. Additionally, traditional cognitive modeling methods mostly assume that students answer exercises one by one, which often does not align with real answering behavior and cannot be directly extended to diverse learning scenarios. Therefore, in this article, we propose a Continuous Time-based Neural Cognitive (CT-NC) framework and several implemented models (CT-NCM and two extensions) to effectively integrate the dynamic and continuous characteristics of knowledge forgetting into student learning process modeling, making it more natural. Specifically, we adopt a specially designed learning event encoding method to adjust the neural Hawkes process to capture the relationship between knowledge learning and forgetting over continuous time. Furthermore, we propose a customizable learning function to jointly model the changes in different knowledge states and their interaction with each practice moment. In the end, we demonstrate an extension CT-NCM+ that can adapt well to diverse learning scenarios, indicating that CT-NCM can solve real-world problems by flexibly adjusting its structure. Extensive experimental results on real datasets clearly demonstrate that CT-NCM and CT-NCM+ outperform the current state-of-the-art KT methods in student performance prediction, while our work points out a realistic research direction for KT and demonstrates its interpretability in knowledge learning visualization.

The Vehicle Routing Problem with Time Windows under Uncertain Travel Times (VRPTW-UT) is a challenging and practically significant combinatorial optimization problem. Although evolutionary algorithms (EAs) have shown potential in solving VRPTW-UT, they often struggle to balance robustness and convergence. Conventional EA approaches evaluate solutions across multiple disturbance scenes and discard those that become infeasible under any scenario. This often leads to the premature elimination of solutions that are only infeasible in a limited number of scenes, hindering the ability to effectively explore the trade-off between robustness and convergence. To address this issue, this paper proposes a Game-Theoretic Evolutionary Algorithm (GTEA) that models the search process as a game between two adversarial components: a perturbation generation part that constructs high-impact uncertainty scenes, and a robustness enhancement part that improves solutions under those critical conditions. This antagonistic process forces the population to evolve toward solutions that possess both high robustness and convergence, so that GTEA can efficiently produce solutions with high robustness and convergence. Extensive experiments on four benchmark datasets demonstrate that GTEA outperforms five state-of-the-art algorithms designed for VRPTW-UT, achieving superior convergence and robustness.

The capacitated electric vehicle routing problem (CEVRP) has drawn much attention from researchers in the recent decade against the background of the rising electric transportation industry. Existing studies have found the CEVRP more difficult to address than the typical CVRP since the CEVRP needs to simultaneously optimize routing plans and charging decisions at a high computational budget. Given a certain routing plan, it takes much computational cost to exhaustively or approximately achieve the accurate optimal charging decision under the routing plan. This paper proposes that it is unnecessary to search for the accurate optimal charging decisions for potentially low-quality routing plans found during the CEVRP optimization, and instead obtaining acceptable charging decisions significantly reduces the computational cost and helps maintain fast convergence. A multifidelity-based ant colony optimization (MFACO) algorithm is then proposed to flexibly search charging decisions based on the potential quality of routing plans so that CEVRPs can be addressed at high efficiency. The proposed MFACO employs a low-fidelity search strategy to obtain coarse charging decisions for potentially low-quality routing plans, whereas for potentially high-quality routing plans MFACO employs three high-fidelity search strategies to local search in different regions of decision space and provide accurate optimal charging decisions. Experimental results demonstrate that the proposed multifidelity method enhances the efficiency of ACO in solving CEVRPs and the proposed MFACO significantly outperforms four state-of-the-art algorithms for CEVRPs, providing a competitive performance in terms of both solution quality and computational cost.

Cognitive Diagnosis is a critical task in computer-assisted education, aimed at assessing students' mastery of knowledge concepts and analyzing exercise indices. In fact, this direction has received a lot of research attention in the past few decades. However, the inherent heterogeneity in students' abilities introduces significant challenges to accurate exercise indices estimation, resulting biases that lead to inaccurate diagnostics within student groups and undermining the generalizability of exercise indices across diverse groups. To address these challenges, we propose a Counterfactual Adaptive-Debiasing Framework (CADF) for Cognitive Diagnosis, which employs a causal graph to model the intricate relationships among key variables influencing student performance and knowledge mastery. Specifically, by introducing exercise adjustment factors, we capture both the intrinsic attributes of exercises and their dynamic adaptability to individual students. Then, to disentangle the direct and indirect effects of these factors, we adopt a counterfactual inference approach to answer the critical question:How would the diagnostic feedback from a cognitive diagnosis model change if it were only directly influenced by exercise adjustment factors?This allows CADF to retain the beneficial indirect effects while neutralizing the direct effects that introduce bias, thereby achieving debiased exercise indices estimation. Finally, Extensive experiments on three real-world datasets demonstrate that CADF significantly reduces bias in exercise indices estimation and enhances the accuracy of diagnostic feedback.

The spatiotemporal dynamics of traffic forecasting make it a challenging task. In recent years, by adapting to the topology of traffic networks where road segments serve as nodes, graph convolutional networks (GCNs) have been able to capture spatiotemporal dependencies, thereby improving traffic forecasting performance. However, there are two shortcomings of GCN-based methods: 1) existing methods treat the delays between nodes in the traffic network as equally important and fail to extract critical information effectively, leading to information redundancy, the introduction of irrelevant noise, and increased computational costs and 2) most methods overlook the issue that spatiotemporal correlations between nodes are inconsistent across different timescales. This article designs a new dynamic delay-aware multiscal spatiotemporal graph convolutional network (DDAMGCN) for traffic forecasting. Specifically, a dynamic delay-aware module is designed to identify key nodes and model the important delays from key nodes, so that the model focuses on key information and reduces computational cost. Additionally, a novel multiscale spatiotemporal graph convolution module is designed to achieve fine-grained modeling of the spatiotemporal correlation of different nodes at different timescales. Experiments on eight real traffic datasets verify the superiority of the proposed method compared to several state-of-the-art baselines.

Cognitive Diagnosis Modeling is a fundamental task in intelligent education, intending to assess students’ mastery levels on knowledge concepts through interactions. Previous methodologies prioritized enhancing average diagnostic accuracy. However, they often neglected the Long-Tailed issue in interactions. To address this issue, we propose an Adaptive Self-Supervised Graph Learning for Cognitive Diagnosis (ASCD) framework that leverages relatively balanced sparse views to forcing the graph network to focus on long-tailed nodes, aiming to tackle the long-tailed problem in graph-based cognitive diagnosis. Additionally, we employ self-supervised manners to mitigate the impact of dropped information on other nodes. Our approach leverages the adaptive graph confusion method to create sparse views of the original student-exercise interaction graph. In these sparse views, both long-tailed and head students carry similar weights, pushing the graph network to allocate attention impartially across all students. We integrate two different graph confusion techniques into adaptive graph confusion to accommodate varying degrees of data sparsity: edge dropout and feature masking. ASCD can serve as a plug-and-play module integrated into any graph-based cognitive diagnosis model, enhancing its performance regarding long-tailed scenarios. Extensive experiments on real-world datasets show the effectiveness of our approach, especially on the students with much sparser interaction records.

Computerized adaptive testing(CAT) is a crucial task in computer-aided education, which aims to adaptively select suitable question to diagnose examinees' ability status. Existing CAT approaches enhance selection performance by exploring examinee-question(E-Q) relation. These approaches either exclusively utilize explicit E-Q relation. For instance, policy-based approaches determine question selection based on predefined criteria. While effective in adapting to changes in question banks, these methods often entail significant computational costs in searching for suitable questions. Conversely, some studies focus solely on implicit E-Q relation. For example, learning-based approaches train agents to efficiently select questions by learning from large-scale datasets. However, they may struggle with newly introduced questions. Additionally, most of these existing question selectors are based on greedy strategies, which potentially overlooks promising quuestions. To bridge the above two types of approaches, we propose a novel framework named Relation Exploiting-based CAT(RECAT) by exploring and exploiting the implicit and explicit examinee-question relation. Specifically, we first define an examinee true ability-oriented selection objective to select more suitable questions. Then, to learn the implicit E-Q relation, we design a question selector, which explores the examinee ability and generates best-fitting questions for specific examinee ability from two aspects, including generation consistency and knowledge matching. The former aims to maximize the likelihood estimation of the implicit E-Q relation learning process, while the latter is employed to fit the distribution of real questions. To fully exploit explicit E-Q relation, we generate a high-quality candidate set for the given examinee's ability using implicit E-Q relation, which streamlines the search process, minimizing selection latency. We demonstrate the effectiveness and efficiency of our framework through comprehensive experiments on real-world datasets.

For black-box expensive optimization problems, the limitation in the number of function evaluations prevents evolutionary algorithms (EAs) from achieving convergence. To date, surrogate models have emerged as the predominant technique to accelerate the convergence of EAs by offering numerous virtual evaluations. However, surrogate models are often criticized for their low accuracy in fitting complex objective functions and low generalizability in handling heterogeneous decision variables. In this work, we propose an alternative idea that abandons surrogate models, focusing instead on the customization of simple EAs for expensive optimization. We construct EAs by incorporating the translation, scale, and rotation invariant variation operators, which have robust generalization capabilities due to their space independent properties, and have outstanding convergence performance due to their learnable parameterized representation. Through a series of comparative experiments, this work answers two questions: Can an EA without surrogate models outperform those with surrogate models for expensive optimization? If so, can surrogate models further accelerate the convergence of such an EA?

Sparse large-scale multi-objective optimization problems are widespread across various domains, where traditional mathematical methods and many existing multi-objective evolutionary algorithms face difficulties in achieving satisfactory results. In this paper, we propose an Adaptive Multi-Granular Pareto-optimal Subspace Learning algorithm (AMG-PSL). The algorithm employs a multi-level decision space stratification mechanism based on variable importance, implements population partitioning through k-means clustering-derived sparsity metrics, and guides population evolution using a hierarchical mutation strategy in reduced subspaces constructed by unsupervised neural networks. The algorithm incorporates a feedback-based adaptation scheme that uses offspring performance to guide solution generation and adjusts neural network architectures according to the non-dominated solutions. Experimental validation across eight benchmark problems and two practical applications demonstrates that AMG-PSL achieves superior optimization results compared to existing strategies in the domain of sparse large-scale optimization.

Non-contact voltage measurement represents a novel but challenging area within modern smart grid systems, which mainly includes structure design for sensing the electric field and voltage estimation via the sensed information. Existing approaches regarded the two components as independent optimization tasks, where the former is low-dimensional but computationally expensive while the latter is high-dimensional but relatively cheap. In this study, we argue that the non-contact measurement task is an asynchronous optimization problem with heterogeneous features in both the decision and objective spaces. Specifically, the problem includes two subproblems to be optimized sequentially, and the result of the first subproblem affects the optimum of the second one. Consequently, we propose a new optimization paradigm called evolutionary asynchronous optimization to achieve the collaborative optimization of the two tasks, and accordingly develop a new asynchronous evolutionary algorithm to solve it. Experimental results on three laboratory cases validate that, the proposed algorithm exhibits superior performance over existing multi-stage, multi-objective, and bi-level evolutionary algorithms.

With the rise of web-based technologies, online tutoring platforms have emerged to provide personalized learning services by modeling learners' engagement behaviors, improving both convenience and efficiency in academic progress. Cognitive diagnosis has been always recognized a essential learner modeling task in personalized education, which aims to infer learners' mastery in specific knowledge concepts by mining and analyzing their practice behavior. However, most existing studies fail to explicitly disentangling the multiple interdependent factors that influence learner's response feedback during the problem-solving process, both in web-based environments and real-world contexts. To address this issue, we propose DISCD, a feedback-centric DIS entangled Cognitive Diagnosis framework for enhancing effective and interpretable learner modeling. Specifically, we first introduce a feedback-centric disentangled encoder grounded in variational inference to effectively characterize learners' cognitive traits by modeling their practice responses. To achieve this, we fully leverage the interaction matrix and the exercise-concept correlation matrix to extract implicit signals in the disentanglement process, employing three dedicated sub-encoders to efficiently and comprehensively capture these attributes. Next, we develop a multi-level cognitive coordination module to systematically model the disentangled cognitive factors, ensuring their seamless integration into the diagnosis decoding process. Finally, we design a cognitive interaction decoder to reconstruct and refine learners' engagement trajectories in exercises. Extensive experiments on four educational datasets validate the effectiveness of the proposed DISCD model in learner modeling for cognitive diagnosis.

Computerized Adaptive Testing (CAT) aims to select the most appropriate questions based on the examinee's ability and is widely used in online education. However, existing CAT systems often lack initial understanding of the examinee's ability, requiring random probing questions. This can lead to poorly matched questions, extending the test duration and negatively impacting the examinee's mindset, a phenomenon referred to as the Cold Start with Insufficient Prior (CSIP) task. This issue occurs because CAT systems do not effectively utilize the abundant prior information about the examinee available from other courses on online platforms. These response records, due to the commonality of cognitive states across different knowledge domains, can provide valuable prior information for the target domain. However, no prior work has explored solutions for the CSIP task. In response to this gap, we propose Diffusion Cognitive States TransfeR Framework (DCSR), a novel domain transfer framework based on Diffusion Models (DMs) to address the CSIP task. Specifically, we construct a cognitive state transition bridge between domains, guided by the common cognitive states of examinees, encouraging the model to reconstruct the initial ability state in the target domain. To enrich the expressive power of the generated data, we analyze the causal relationships in the generation process from a causal perspective. Redundant and extraneous cognitive states can lead to limited transfer and negative transfer effects. Therefore, we designed three decoupling strategies to control confounding variables, thereby blocking backdoor paths that hinder causal discovery. Given that excessive uncertainty can affect the applicability of generated results to the CAT system, we propose consistency constraint and task-oriented constraint to control the randomness of the generated results and their relevance to the CAT task, respectively. Our DCSR can seamlessly apply the generated initial ability states in the target domain to existing question selection algorithms, thus improving the cold start performance of the CAT sys- tem. Extensive experiments conducted on five real-world datasets demonstrate that DCSR significantly outperforms existing baseline methods in addressing the CSIP task.

Knowledge tracing (KT), which is instrumental in monitoring and forecasting students' knowledge states throughout their learning trajectory in online learning environments, has over the past decade garnered widespread attention due to its pivotal role in facilitating personalized education. Existing KT approaches were mainly invented from the model-centric perspective to overcome the sequence modeling difficulty while not exploiting the potential information of sparsity, thereby limiting their performance. To make full use of the information in the dataset, this paper proposes a data-centric knowledge tracing paradigm, termed LPDG, aiming to generate interaction data between students and exercises by revealing students' Learning Patterns and facilitating the Generation of ideal training Data. Specifically, we propose a learning patterns-guided exercise sequence regenerator, which incorporates Transformer and a tailor-made pattern enhancer, thereby aiding in the extraction of valuable information for generating high-quality training data. Moreover, we devise a learning patterns-guided pseudo-label generator, which leverages the diffusion process to construct pseudo-labels for the regenerated sequences. Afterwards, the fully generated ideal data is incorporated into the training data, and we integrate this framework with various model-centric approaches in KT. Finally, experimental results across datasets clearly demonstrate the efficacy of our proposed LPDG framework.

Learning path recommendation (LPR) aims to provide individualized and effective learning item routes by modeling learners' learning histories and goals, which has been widely considered a essential task in the field of personalized education. Indeed, considerable research efforts have been dedicated to this direction in recent years, focusing on step-based and sequence-based modeling approaches. However, most of existing studies overlook the complementarity between explicit and implicit relationships among knowledge concepts, while failing to harmonize static knowledge structures with dynamic path generation. To this end, in this paper, we propose LIGHT, a knowLedge topology-aware sequence optImization model for enhancing learninG patH recommendaTion. Specifically, we first construct a composite concept graph that incorporates explicit prerequisite relationships and implicit collaborative relationships, achieved by mining interaction statistics and collaborative signals from learners' learning processes. Next, we design a complementary contrastive fusion module to fully capture the interplay between the two relational views of concepts through graph structure learning and contrastive constraints, which enhances the effectiveness of the learned representations. Following this, we introduce a knowledge topology-aware modeling module that integrates structural semantics clustering with candidate path sampling. Finally, we develop a bidirectional sensing path optimization network to deeply model and optimize the sampled paths from a sequential perspective, thereby enhancing modeling efficiency while preserving structural semantics. Extensive experiments on three real-world educational datasets clearly demonstrate the effectiveness of the proposed LIGHT model in the LPR task.

With the rapid development of intelligent education, Computerized Adaptive Testing(CAT) has garnered significant attention for its ability to tailor exercises to individual examinees. The adaptability of CAT is primarily achieved through the alternating optimization of two core components: the cognitive diagnosis model and the exercise selection module. However, existing CAT approaches, despite their remarkable achievements, often come at the expense of high time costs. Statistical-based approaches incur increased time overhead due to complex computations, while data-driven approaches further exacerbate time inefficiency because of the iterative processes in reinforcement learning, making it challenging to balance evaluation effectiveness and time efficiency. To this end, in this paper, we propose HashCAT, an efficient CAT approach based on learning to hash, aiming to balance efficiency and evaluation effectiveness. Our approach comprises two stages: the hash representation generation and the exercise selection. In the first stage, we design an information alignment module and a novel cognitive diagnosis function to model the interaction between examinees and exercises, generating hash representations with clear physical significance. In the second stage, we propose an uncertainty reduction-based algorithm that utilize information entropy to quantify the uncertainty in student ability estimation and selects exercises that most effectively reduce this uncertainty. Experimental results on four real-world datasets demonstrate that the proposed method significantly improves question selection efficiency while maintaining competitive evaluation performance. The code exists anonymously in https://github.com/sherklock/Intelligent-Education/tree/main/HashCAT-main.

The 21st century has already witnessed so many outbreaks with pandemic potential, including SARS (2002), H1N1 (2009), MERS (2012), Ebola (2014), Zika virus (2015), and the COVID-19 pandemic (2019). Using 60 million geotagged Sina Weibo tweets covering over 20 million active accounts, we investigate the collective emotional dynamics on social media in the most recent global pandemic, i.e., COVID-19. This research features two highlights: (1) It focuses on the Chinese population located in the initial epicenter of the pandemic. (2) It examines the initial year after the pandemic outbreak, a critical period where emotions were most intense due to the uncertainty and rapid developments related to the crisis. Using cross-disciplinary methods, we reveal a positive connection between online emotional resonance and geographic proximity, demonstrating a direct mapping between virtual network distances and physical spatial embedding. We propose a percolation-based index to measure the nationwide emotional resonance level with which we illustrate the significant economic impact of the global health issue. Finally, we identify a leader-follower pattern in emotional resonance fluctuations based on time-lag emotion correlations, revealing that less active regions play a crucial role in leading and responding to emotional changes. In the face of long COVID and emerging global health crises, our analysis elucidates how collective emotional resonance evolves, providing potential directions for online opinion interventions during global shocks.

Molecular optimization, aiming to identify molecules with improved properties from a huge chemical search space, is a critical step in drug development. This task is challenging due to the need to optimize multiple properties while adhering to stringent drug-like criteria. Recently, numerous effective artificial intelligence methods have been proposed for molecular optimization. However, most of them neglect the constraints in molecular optimization, thereby limiting the development of high-quality molecules that simultaneously satisfy property objectives and constraint compliance. To address this issue, we proposed a deep multi-objective optimization framework, termed CMOMO, for constrained molecular multi-property optimization. The proposed CMOMO divides the optimization process into two stages, which enables it to use a dynamic constraint handling strategy to balance multi-property optimization and constraint satisfaction. Besides, a latent vector fragmentation based evolutionary reproduction strategy is designed to generate promising molecules effectively. Experimental results on two benchmark tasks show that the proposed CMOMO outperforms five state-of-the-art methods to obtain more successfully optimized molecules with multiple desired properties and satisfying drug-like constraints. Moreover, the superiority of CMOMO is verified on two practical tasks, including a potential protein-ligand optimization task of 4LDE protein, which is the structure of $\beta $2-adrenoceptor GPCR receptor, and a potential inhibitor optimization task of glycogen synthase kinase-3$\beta $ target (GSK3$\beta $). Notably, CMOMO demonstrates a two-fold improvement in success rate for the GSK3$\beta $ optimization task, successfully identifying molecules with favorable bioactivity, drug-likeness, synthetic accessibility, and adherence to structural constraints.

The Dynamic Vehicle Routing Problem with Time Windows (DVRPTW) is a widespread real-world challenge, and numerous algorithms have been proposed to address it. However, in the context of an emerging logistics paradigm, namely the instant delivery, the performance of existing algorithms tailored for DVRPTW degrades significantly, as instant delivery allows only very limited computational time for solving DVRPTW instances. Owing to the periodic nature of customer orders, this paper proposes a data-driven evolutionary algorithm (DDEA) for solving DVRPTW under limited computation time. In the offline phase, a set of generalized solutions is derived from historical data via a dedicated evolutionary algorithm. These solutions are then directly employed in the online phase to construct high-quality solutions for new problem instances. By leveraging these precomputed generalized solutions, DDEA effectively operates within tight time constraints. Extensive experiments using synthetic and real-world data demonstrate that DDEA outperforms five state-of-the-art algorithms designed for DVRPTW under limited computation time, particularly under extremely short time constraints.

Large-scale sparse multiobjective optimization problems (LSMOPs) are of great significance in the context of practical applications, such as critical node detection, feature selection, and pattern mining. Since many LSMOPs are pursued based on large datasets, they involve a large number of decision variables, resulting in a huge search space that is challenging to explore efficiently. To rapidly approximate sparse Pareto optimal solutions, some evolutionary algorithms have been proposed to reduce the dimensionality of LSMOPs. However, their adaptability to different LSMOPs remains limited due to their reliance on fixed dimensionality reduction schemes, which can potentially lead to local optima and inefficient utilization of function evaluations. To address this issue, a knowledge learning-based dimensionality reduction approach is proposed in this article. First, in the early stages of evolution, the impact of different dimensionality reduction schemes on the sparse distribution of the population is evaluated. Then, the multilayer perceptron is employed to learn the accumulated knowledge from the evolutionary process, thereby constructing a mapping model between the sparse features of the evolutionary process and the candidate dimensionality reduction schemes. Finally, the model recommends the best dimensionality reduction scheme in each generation, achieving a good balance between exploration and exploitation. Experimental evaluations on both benchmark and real-world LSMOPs demonstrate that an evolutionary algorithm incorporating the proposed knowledge learning-based dimensionality reduction approach outperforms most existing evolutionary algorithms.

Robust multiobjective optimization problems (RMOPs) widely exist in real-world applications, which introduce a variety of uncertainty in optimization models. While some evolutionary algorithms have been developed to find optimal solutions robust to uncertainty, they are ineffective to handle RMOPs in high-dimensional decision spaces. Focusing on the large-scale RMOPs with sparse optimal solutions, this article proposes an evolutionary algorithm with novel strategies for the selection, generation, and evaluation of robust solutions. In order to handle the uncertainty in the optimization models, we first introduce an archive to separately consider optimality and robustness, which can achieve the selection of robust solutions effectively at a low cost. Based on the robust knowledge extracted from the archive, a guiding vector is adaptively updated to facilitate the generation of robust solutions in high-dimensional decision spaces. With the assistance of the guiding vector, a robustness indicator is suggested to assist in the evaluation of robust solutions without additional perturbations. Besides, we design a test suite to evaluate the performance of the proposed algorithm on the large-scale RMOPs. Our experimental results demonstrate that the proposed algorithm has significant advantages over the state-of-the-art evolutionary algorithms in terms of optimality and robustness, on both the proposed test suite and practical applications.

Despite that the surrogate-assisted evolutionary algorithms have achieved great success in addressing expensive optimization problems, they still suffer from stiff challenges when the number of dimensions of problems becomes large. The primary reason lies in that it is very hard to build an acceptable surrogate model in the high-dimensional search space with small amounts of evaluated historical data in evolution. To tackle this issue, we suggest an effective surrogate modeling method for large-scale expensive optimization in this paper, where the models are built on a number of linear subspaces instead of the original search space. Specifically, a linear subspace is constructed by a pair of points/solutions which are generated based on the set of elite solutions. For each linear subspace, several historical solutions are first associated according to their distance to the linear subspace, and then a surrogate model is trained by the associated solutions and used to evaluate the offspring. To ensure the exploration and exploitation capacity of the proposed method, these linear subspaces and the surrogate models are updated after a few iterations. Experimental results on CEC’2010 and CEC’2013 single-objective optimization problems with up to 1500 decision variables show that the proposed algorithm is superior over six comparison algorithms. Moreover, we also extend the proposed algorithm to multi-objective optimization problems and verified its competitiveness on problems with up to 1500 decision variables.

Binary optimization assumes a pervasive significance in the context of practical applications, such as knapsack problems, maximum cut problems, and critical node detection problems. Existing techniques including mathematical programming, heuristics, evolutionary computation, and neural networks have been employed to tackle binary optimization problems (BOPs), however, they grapple with the challenge of optimizing a large number of binary variables. In this paper, we propose a dimensionality reduction method to assist evolutionary algorithms in solving large-scale BOPs, which is achieved based on neural networks. The proposed method converts the optimization of a large number of binary variables into the optimization of a small number of network weights, resulting in a significant reduction in search space dimensionality. Crucially, the proposed method obviates the necessity for a training process, which eliminates the requirement for a priori knowledge and enhances the search efficiency. On six types of single-and multi-objective BOPs with up to 10 000 000 variables, the proposed method demonstrates superiority over top-tier evolutionary algorithms and neural network-based methods.

Surrogate-assisted evolutionary algorithms (SAEAs) rely on the infill criterion to select candidate solutions for expensive evaluations. However, in the context of expensive constrained multi-objective optimization problems (ECMOPs) with complex feasible regions, guiding the optimization algorithm towards the constrained Pareto optimal front and achieving a balance between feasibility, convergence, diversity, exploration, and exploitation using a single infill criterion pose significant challenges. We propose an ensemble infill criterion-based multi-stage SAEA (EIC-MSSAEA) to tackle these challenges. Specifically, EIC-MSSAEA comprises three stages. In the first stage, we ignore constraints to facilitate the rapid traversal of infeasible obstacles. In the second stage, only one constraint is activated at a time to increase algorithm diversity. Finally, in the last stage, we activate all constraints to improve overall feasibility. In each stage, EIC-MSSAEA first employs NSGA-III as the underlying baseline solver to explore the search space, in which promising solutions are then selected by an ensemble infill criterion that incorporates multiple base-infill criteria to measure the feasibility, convergence, diversity, and uncertainty of candidate solutions. Experimental results demonstrate the competitiveness of EIC-MSSAEA against state-of-the-art SAEAs for ECMOPs.

Multitasking multiobjective evolutionary algorithms (MMEAs) have been extensively studied in the past decade, which mainly concentrate on multitasking multiobjective optimization problems (MMOPs) with dozens of decision variables. Nevertheless, many real-world MMOPs have thousands of decision variables and are of sparse nature, which are regarded as large-scale MMOPs (LSMMOPs) in this study. To address LSMMOPs, a sparsity knowledge transfer-based evolutionary multiobjective algorithm, termed EMO-SKT, is proposed for efficiently finding high-quality sparse solutions of LSMMOPs. For each target optimization task, a sparsity knowledge transfer strategy extracts sparse distribution information from a source task and incorporates the information into the target task for two types of sparsity knowledge: 1) variable importance and 2) sparse degree. The variable importance is utilized to produce high-quality sparse solutions during the evolutionary search for EMO-SKT, while the sparse degree facilitates the reduction of search space and thus speeds up the convergence of the evolutionary search. Experimental results on eight benchmark problems and six practical LSMMOPs demonstrate the effectiveness of the sparsity knowledge transfer strategy. Furthermore, the proposed EMO-SKT is capable of efficiently finding high-quality sparse solutions on an LSMMOP with over 1000 decision variables. In comparison with five state-of-the-art multitasking or sparse optimization algorithms, the proposed EMO-SKT exhibits superior performance in terms of both solution quality and search efficiency.

As a pivotal technique in intelligent education systems, cognitive diagnosis (CD) serves to reveal students’ knowledge proficiency for better tackling subsequent tasks. Unfortunately, due to pursuing high model interpretability, existing manually designed models for CD often hold simplistic architectures, which cannot cope with intricate data in modern education platforms. Furthermore, the bias of human design limits the emergence of novel and effective CD models (CDMs). To develop interpretable and more effective models, thus this article proposes an evolutionary multiobjective neural architecture search (NAS) approach for CD. Specifically, we first adopt a comprehensive search space for the NAS task of CD: all candidate models can be encompassed by a general model that deals with three distinct types of inputs. Then, an innovative model interpretability objective is devised to formulate the architecture search task as a bi-objective optimization problem (BOP). To solve the BOP, we employ a multiobjective genetic programming (MOGP) as the search strategy to explore the search space. To make the employed MOGP search well, all architectures are first encoded by trees for easy optimization, and we devise a genetic operation and a population initialization strategy to expedite its convergence. Finally, the proposed approach is actually an MOGP-based NAS approach for CD. Extensive experiments show that CDMs searched by the proposed approach exhibit significantly better performance than existing models and hold as good interpretability as handcrafted models. Besides, the effectiveness of the proposed MOGP search strategy, the devised objective, and tailored strategies are validated.

Domain generalization (DG) aims to solve the problem of significant performance degradation when target domain data collected from the Out-Of-Distribution (O.O.D). Previous efforts try to exploit invariant features in the source domain through CNN networks. However, inspired by causal mechanisms, we find that the complex spurious-invariant information is still hidden in this view invariant features, and the impact of domain and class discrepancies on extracting invariance has not been effectively mitigated. To alleviate these issues, we propose a self-weighted multi-view mining invariance domain generalization framework (SMIDG). On the one hand, to make up for the insufficiency of traditional single-view convolutional feature extraction networks, we propose to mine features from another frequency view and use the self-adaptive adversarial masks to eliminate some spurious correlations, ensuring causal invariance in the coarse-grained generalization. However, due to inconsistencies in discriminative information between inter-domain and intra-domain samples, as well as inter-class and intra-class samples, the coarse-grained elimination of spurious associations does not fully resolve this issue. On the other hand, we also consider the fine-grained generalization from two aspects. Firstly, to better tackle the domain discrepancies, we propose a novel progressive contrastive learning strategy that learns the underlying specific features of samples while gradually mitigating domain discrepancies, thereby ensuring domain invariance in fine-grained generalization. Secondly, due to the issue of feature inconsistency, we adopt a self-adaptive hard sample mining method with information gain to ensure that the model pays more attention on hard disentangled samples, thus maintaining feature invariance. Extensive experiments on five benchmark datasets demonstrate that our method outperforms state-of-the-art approaches. Our code is available at https://github.com/bihhm/SMIDG.

The Multi-depot Vehicle Routing Problem with Uncertain Demand (MD-VRPUD) can be modeled as a bi-level optimization problem (BLOP), because it requires both assigning customers to different depots and determining the routes for servicing customers, where the optimization of these two parts is coupled with each other. Although the bi-level evolutionary algorithm is a fitting approach for tackling the MD-VRPUD, its nested structure often leads to computational inefficiency. To this end, this paper tailors a surrogate-assisted bi-level evolutionary algorithm (SABLEA) to achieve highly efficient nested algorithms tailored for solving the MD-VRPUD. To deal with the combinatorial property of MD-VRPUD, two groups of continuous features are first extracted to help the surrogate model to effectively distinguish the superiority and inferiority of schemes. Then, a management strategy is designed to adaptively build the surrogate models in different subspaces so as to alleviate the performance bottleneck faced by the model. Finally, an adaptive computing resource allocation strategy is integrated into the lower-level optimization, to allocate more resources to promising customer assignment schemes, enabling the discovery of better routes and improving the overall accuracy of models. The comprehensive experimental results demonstrate the effectiveness of the SABLEA in handling MD-VRPUD, outperforming four existing algorithms in terms of both computational efficiency and solution quality.

Knowledge tracing has been widely used in online learning systems to guide the students’ future learning. However, most existing KT models primarily focus on extracting abundant information from the question sets and explore the relationships between them, but ignore the personalized student behavioral information in the learning process. This will limit the model’s ability to accurately capture the personalized knowledge states of students and reasonably predict their performances. To alleviate this limitation, we explicitly models the personalized learning process by incorporating the emotions, a representative personalized behavior in the learning process, into KT framework. Specifically, we present a novel Dual-State Personalized Knowledge Tracing with Emotional Incorporation model to achieve this goal: First, we incorporate emotional information into the modeling process of knowledge state, resulting in the Knowledge State Boosting Module. Second, we design an Emotional State Tracing Module to monitor students’ personalized emotional states, and propose an emotion prediction method based on personalized emotional states. Finally, we apply the predicted emotions to enhance students’ response prediction. Furthermore, to extend the generalization capability of our model across different datasets, we design a transferred version of DEKT, named Transfer Learning-based Self-loop model (T-DEKT). Extensive experiments show our method achieves the state-of-the-art performance.

Cognitive diagnosis is a crucial task in computer-aided education, aimed at evaluating students' proficiency levels across various knowledge concepts through exercises. Current models, however, primarily rely on students' answered exercises, neglecting the complex and rich information contained in un-interacted exercises. While recent research has attempted to leverage the data within un-interacted exercises linked to interacted knowledge concepts, aiming to address the long-tail issue, these studies fail to fully explore the informative, un-interacted exercises related to broader knowledge concepts. This oversight results in diminished performance when these models are applied to comprehensive datasets. In response to this gap, we present the Collaborative-aware Mixed Exercise Sampling (CMES) framework, which can effectively exploit the information present in un-interacted exercises linked to un-interacted knowledge concepts. Specifically, we introduce a novel universal sampling module where the training samples comprise not merely raw data slices, but enhanced samples generated by combining weight-enhanced attention mixture techniques. Given the necessity of real response labels in cognitive diagnosis, we also propose a ranking-based pseudo feedback module to regulate students' responses on generated exercises. The versatility of the CMES framework bolsters existing models and improves their adaptability. Finally, we demonstrate the effectiveness and interpretability of our framework through comprehensive experiments on real-world datasets.

Cognitive Diagnosis Modeling aims to infer students' proficiency level on knowledge concepts from their response logs. Existing methods typically model students’ response processes as the interaction between students and exercises or concepts based on hand-crafted or deeply-learned interaction functions. Despite their promising achievements, they fail to consider the relationship between students' cognitive states and affective states in learning, e.g., the feelings of frustration, boredom, or confusion with the learning content, which is insufficient for comprehensive cognitive diagnosis in intelligent education. To fill the research gap, we propose a novel Affect-aware Cognitive Diagnosis (ACD) model which can effectively diagnose the knowledge proficiency levels of students by taking into consideration the affective factors. Specifically, we first design a student affect perception module under the assumption that the affective state is jointly influenced by the student's affect trait and the difficulty of the exercise. Then, our inferred affective distribution is further used to estimate the student's subjective factors, i.e., guessing and slipping, respectively. Finally, we integrate the estimated guessing and slipping parameters with the basic neural cognitive diagnosis framework based on the DINA model, which facilitates the modeling of complex exercising interactions in a more accurate and interpretable fashion. Besides, we also extend our affect perception module in an unsupervised learning setting based on contrastive learning, thus significantly improving the compatibility of our ACD. To the best of our knowledge, we are the first to unify the cognition modeling and affect modeling into the same framework for student cognitive diagnosis. Extensive experiments on real-world datasets clearly demonstrate the effectiveness of our ACD. Our code is available at https://github.com/zeng-zhen/ACD.

The ability of model quantization with arbitrary bit-width to dynamically meet diverse bit-width requirements during runtime has attracted significant attention. Recent research has focused on optimizing large-scale training methods to achieve robust bit-width adaptation, which is a time-consuming process requiring hundreds of GPU hours. Furthermore, converting bit-widths requires recalculating statistical parameters of the norm layers, thereby impeding real-time switching of the bit-width. To overcome these challenges, we propose an efficient Post-Training Multi-bit Quantization (PTMQ) scheme that requires only a small amount of calibration data to perform block-wise reconstruction of multi-bit quantization errors. It eliminates the influence of statistical parameters by fusing norm layers, and supports real-time switching bit-widths in uniform quantization and mixed-precision quantization. To improve quantization accuracy and robustness, we propose a Multi-bit Feature Mixer technique (MFM) for fusing features of different bit-widths to enhance robustness across varying bit-widths. Moreover, we introduced the Group-wise Distillation Loss (GD-Loss) to enhance the correlation between different bit-width groups and further improve the overall performance of PTMQ. Extensive experiments demonstrate that PTMQ achieves comparable performance to existing state-of-the-art post-training quantization methods, while optimizing it speeds up by 100$\times$ compared to recent multi-bit quantization works. Code can be available at https://github.com/xuke225/PTMQ.

Evolutionary algorithms have demonstrated superior performance in solving multi-objective optimization problems (MOPs), but no single algorithm is consistently effective across all MOPs. When using evolutionary algorithms to solve MOPs, environmental selection strategies determining which solutions should survive are crucial to population evolution. While different environmental selection strategies exhibit different search behaviors on various MOPs, existing multi-objective evolutionary algorithms rarely focus on the adaptation of environmental selection strategies. To fill this gap, this paper proposes a framework for assembling environmental selection strategies, which utilizes neural networks to assess the effects of different strategies on population evolution, and employs reinforcement learning to adaptively select the most effective strategies. The effectiveness and versatility of the proposed framework are verified on four test sets, where the proposed framework shows significant superiority over the state-of-the-art.

The traveling salesman problem (TSP) has long been a central focus in combinatorial optimization, with extensive applications in areas such as logistics and transportation. With the rapid development of machine learning, the research focusing on TSPs has shifted from traditional heuristics, often involving a substantial amount of manually designed rules, to machine learning-based approaches. However, due to the limitations of models and hardware, generative approaches based on machine learning often fall short of expectations in terms of effectiveness, and they generally lag behind well-established traditional heuristics. To address these limitations and leverage the strengths of both approaches, the integration of heuristics with machine learning has become a crucial branch for solving TSPs. Thus, this paper proposes an approach that combines a traditional heuristic, specifically guided fast local search, with a neural network to tackle TSPs, where reinforcement learning techniques are employed to train the neural network. Experimental results showcase the superiority of the proposed approach over the original heuristic, outperforming the majority of mainstream machine learning-based approaches. Notably, the proposed approach achieves zero-gap results for instances with 20 and 50 nodes and a minimal gap of 0.07% for instances with 100 nodes. Compared with existing reinforcement learning-based approaches, the proposed approach also stands out with the best overall performance.

In the face of a series of challenging control tasks, multi-agent reinforcement learning has demonstrated its superiority. However, it suffers from certain drawbacks like deceptive reward functions, unstable training processes, and a lack of exploration for novel policies. To address these issues, the combination of evolutionary algorithms and reinforcement learning has been introduced, as evolutionary algorithms possess good exploration and convergence properties, enabling reinforcement learning to better leverage its performance. To enhance the complementary advantages of evolutionary algorithms and reinforcement learning, we combine them into an asymmetric reinforcement learning framework by utilizing a shared observation encoder, allowing the algorithm's performance to break through certain bottlenecks. In addition to the consideration of reward, we propose the concept of policy novelty, which measures the degree of difference between a policy's behavior and others. Consequently, the training of multiple agents is formulated as a large-scale bi-objective optimization problem, and solved by a multi-objective evolutionary algorithm. The proposed approach is tested on eight experimental tasks within the MA-MuJoCo framework, exhibiting superiority over commonly used approaches.

The rapid development of online recruitment platforms has created unprecedented opportunities for job seekers while concurrently posing the significant challenge of quickly and accurately pinpointing positions that align with their skills and preferences. Job recommendation systems have significantly alleviated the extensive search burden for job seekers by optimizing user engagement metrics, such as clicks and applications, thus achieving notable success. In recent years, a substantial amount of research has been devoted to developing effective job recommendation models, primarily focusing on text-matching based and behavior modeling based methods. While these approaches have realized impressive outcomes, it is imperative to note that research on the explainability of recruitment recommendations remains profoundly unexplored. To this end, in this paper, we propose DISCO, a hierarchical Disentanglement based Cognitive diagnosis framework, aimed at flexibly accommodating the underlying representation learning model for effective and interpretable job recommendations. Specifically, we first design a hierarchical representation disentangling module to explicitly mine the hierarchical skill-related factors implied in hidden representations of job seekers and jobs. Subsequently, we propose level-aware association modeling to enhance information communication and robust representation learning both inter- and intra-level, which consists of the inter-level knowledge influence module and the level-wise contrastive learning. Finally, we devise an interaction diagnosis module incorporating a neural diagnosis function for effectively modeling the multi-level recruitment interaction process between job seekers and jobs, which introduces the cognitive measurement theory. Extensive experiments on two real-world recruitment recommendation datasets and an educational recommendation dataset clearly demonstrate the effectiveness and interpretability of our proposed DISCO framework. Our codes are available at https://github.com/LabyrinthineLeo/DISCO.

Unsupervised domain adaptation (UDA) aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain. Traditional methods often focus on minimizing the distribution gap between feature spaces of the two domains to achieve domain-invariant representations. However, this approach may not fully leverage the inherent class-specific information and could adversely affect decision boundaries in the target domain. In this paper, we introduce an adversarial contrastive self-training framework. The model integrates both intra-class and inter-class domain differences for better alignment between the source and target domains. Initially, we augment target domain samples using Fourier transformations, obtaining reliable samples and pseudo-labels through self-training. We then employ intra-domain contrastive learning on the reliable samples and pseudo-labels, alongside labeled source domain samples, to achieve intra-domain compactness. Finally, we utilize adversarial learning to achieve global alignment. This comprehensive approach ensures improved adaptation performance while also addressing the limitations of previous methods.

In the realm of education, both independent learning and group learning are esteemed as the most classic paradigms. The former allows learners to self-direct their studies, while the latter is typically characterized by teacher-directed scenarios. Recent studies in the field of intelligent education have leveraged deep temporal models to trace the learning process, capturing the dynamics of students' knowledge states, and have achieved remarkable performance. However, existing approaches have primarily focused on modeling the independent learning process, with the group learning paradigm receiving less attention. Moreover, the reciprocal effect between the two learning processes, especially their combined potential to foster holistic student development, remains inadequately explored. To this end, in this paper, we propose RIGL, a unified Reciprocal model to trace knowledge states at both the individual and group levels, drawing from the Independent and Group Learning processes. Specifically, we first introduce a time frame-aware reciprocal embedding module to concurrently model both student and group response interactions across various time frames. Subsequently, we employ reciprocal enhanced learning modeling to fully exploit the comprehensive and complementary information between the two behaviors. Furthermore, we design a relation-guided temporal attentive network, comprised of dynamic graph modeling coupled with a temporal self-attention mechanism. It is used to delve into the dynamic influence of individual and group interactions throughout the learning processes, which is crafted to explore the dynamic intricacies of both individual and group interactions during the learning sequences. Conclusively, we introduce a bias-aware contrastive learning module to bolster the stability of the model's training. Extensive experiments on four real-world educational datasets clearly demonstrate the effectiveness of the proposed RIGL model. Our codes are available at https://github.com/LabyrinthineLeo/RIGL.

Existing graph learning-based cognitive diagnosis (CD) methods have made relatively good results, but their student, exercise, and concept representations are learned and exchanged in an implicit unified graph, which makes the interaction-agnostic exercise and concept representations be learned poorly, failing to provide high robustness against noise in students' interactions. Besides, lower-order exercise latent representations obtained in shallow layers are not well explored when learning the student representation. To tackle the issues, this paper suggests a meta multigraph-assisted disentangled graph learning framework for CD (DisenGCD), which learns three types of representations on three disentangled graphs: student-exercise-concept interaction, exercise-concept relation, and concept dependency graphs, respectively. Specifically, the latter two graphs are first disentangled from the interaction graph. Then, the student representation is learned from the interaction graph by a devised meta multigraph learning module; multiple learnable propagation paths in this module enable current student latent representation to access lower-order exercise latent representations, which can lead to more effective nad robust student representations learned; the exercise and concept representations are learned on the relation and dependency graphs by graph attention modules. Finally, a novel diagnostic function is devised to handle three disentangled representations for prediction. Experiments show better performance and robustness of DisenGCD than state-of-the-art CD methods and demonstrate the effectiveness of the disentangled learning framework and meta multigraph module.The source code is available at https://github.com/BIMK/Intelligent-Education/tree/main/DisenGCD.

The purpose of this study was to develop an evolutionary algorithm (EA) with bilevel surrogate modeling, called BL-SAEA, for tackling bilevel optimization problems (BLOPs), in which an upper level problem is to be solved subject to the optimality of a corresponding lower level problem. The motivation of this article is that the extensive lower level optimization required by each upper level solution consumes too many function evaluations, leading to poor optimization performance of EAs. To this end, during the upper level optimization, the BL-SAEA builds an upper level surrogate model to select several promising upper level solutions for the lower level optimization. Because only a small number of upper level solutions require the lower level optimization, the number of function evaluations can be considerably reduced. During the lower level optimization, the BL-SAEA constructs multiple lower level surrogate models to initialize the population of the lower level optimization, thus further decreasing the number of function evaluations. Experimental results on two widely used benchmarks and two real-world BLOPs demonstrate the superiority of our proposed algorithm over six state-of-the-art algorithms in terms of effectiveness and efficiency.

This study focuses on building an intelligent decision-making attention mechanism in which the channel relationship and conduct feature maps among specific deep Dense ConvNet blocks are connected to each other. Thus, develop a novel freezing network with a pyramid spatial channel attention mechanism (FPSC-Net) in deep modeling. This model studies how specific design choices in the large-scale data-driven optimization and creation process affect the balance between the accuracy and effectiveness of the designed deep intelligent model. To this end, this study presents a novel architecture unit, which is termed as the "Activate-and-Freeze" block on popular and highly competitive datasets. In order to extract informative features by fusing spatial and channel-wise information together within local receptive fields and boost the representation power, this study constructs a Dense-attention module (pyramid spatial channel (PSC) attention) to perform feature recalibration, and through the PSC attention to model the interdependence among convolution feature channels. We join the PSC attention module in the activating and back-freezing strategy to search for one of the most important parts of the network for extraction and optimization. Experiments on various large-scale datasets demonstrate that the proposed method can achieve substantially better performance for improving the ConvNets representation power than the other state-of-the-art deep models.

Cognitive diagnosis has been widely recognized as a crucial task in the field of computational education, which is capable of learning the knowledge profiles of students and predicting their future exercise performance. Indeed, considerable research efforts have been made in this direction over the past decades. However, most of the existing studies only focus on individual-level diagnostic modeling, while the group-level cognitive diagnosis still lacks an in-depth exploration, which is more compatible with realistic collaborative learning environments. To this end, in this paper, we propose aRelation-guidedDual-sideGraphTransformer (RDGT) model for achieving effective group-level cognitive diagnosis. Specifically, we first construct the dual-side relation graphs (i.e., student-side and exercise-side) from the group-student-exercise heterogeneous interaction data for explicitly modeling associations between students and exercises, respectively. In particular, the edge weight between two nodes is defined based on the similarity of corresponding student-exercise interactions. Then, we introduce two relation-guided graph transformers to learn the representations of students and exercises by integrating the whole graph information, including both nodes and edge weights. Meanwhile, the inter-group information has been incorporated into the student-side relation graph to further enhance the representations of students. Along this line, we design a cognitive diagnosis module for learning the groups' proficiency in specific knowledge concepts, which includes an attention-based aggregation strategy to obtain the final group representation and a hybrid loss for optimizing the performance prediction of both group and student. Finally, extensive experiments on 5 real-world datasets clearly demonstrate the effectiveness of our model as well as some interesting findings (e.g., the representative groups and potential collaborations among students).

Recently, the problem of user identification across multiple social networks (UIAMSNs) has attracted considerable attention since it is a prerequisite for many downstream tasks and applications. Although substantial network feature-based approaches have been proposed to solve the UIAMSNs' problem, the matching degree in most of the current works is given by experience, which lacks a solid theoretical basis. To alleviate the above predicament, we propose a user identification algorithm based on naive Bayes model (UI-NBM) within the network feature-based framework. First, a matching degree index is designed based on the naive Bayes model, which can accurately measure the contributions of different common matched node pairs (MNPs) to the connection probability of unmatched node pairs (UMNPs). Second, the matching degrees of all UMNPs are formulated as the product of matrices, giving rise to the great reduction of the time complexity and the compact expression; Finally, with the idea of recursion process, more UMNPs can be iteratively predicted even when only a small amount of prior information (i.e., a few number of MNPs) is known. The experimental results on the synthetic and real cross platforms demonstrate that the method outperforms the baseline methods within the feature-based framework.

Multiobjective optimization problems (MOPs) with expensive constraints pose stiff challenges to existing surrogate-assisted evolutionary algorithms (SAEAs) in a very limited computational cost, due to the fact that the number of expensive constraints for an MOP is often large. For existing SAEAs, they always approximate constraint functions in a single granularity, namely, approximating the constraint violation (CV, coarse-grained) or each constraint (fine-grained). However, the landscape of CV is often too complex to be accurately approximated by a surrogate model. Although the modeling of each constraint function may be simpler than that of CV, approximating all the constraint functions independently may result in tremendous cumulative errors and high computational costs. To address this issue, in this article, we develop a multigranularity surrogate modeling framework for evolutionary algorithms (EAs), where the approximation granularity of constraint surrogates is adaptively determined by the position of the population in the fitness landscape. Moreover, a dedicated model management strategy is also developed to reduce the impact resulting from the errors introduced by constraint surrogates and prevent the population from trapping into local optima. To evaluate the performance of the proposed framework, an implementation called K-MGSAEA is proposed, and the experimental results on a large number of test problems show that the proposed framework is superior to seven state-of-the-art competitors.

Due to the curse of dimensionality and the unknown sparsity of search spaces, evolutionary algorithms face immense challenges in approximating optimal solutions for widely studied sparse large-scale multiobjective optimization problems (SLMOPs). Most bilevel encoding scheme (BLES)-based algorithms primarily focus on exploring sparsity in the binary layer, neglecting the real layer. Moreover, the interactions between two layers may be disregarded in these algorithms, thus the latent gap between the two encoding scales could lead to evolutionary ambiguity and performance limitations. To tackle the above issues, this article proposes a novel BLES-based collaborative algorithm using cross-scale knowledge fusion for SLMOPs. The algorithm integrates dual grouping and dual dimension reduction techniques via two subpopulations in a coevolutionary manner. Additionally, the interaction strategy is designed for each technique, leveraging the binary layer to guide the real layer, thus facilitating sufficient cross-scale cooperation. Extensive experiments on benchmark SLMOPs and four real-world applications validate the proposed algorithm’s strong competitiveness in solving SLMOPs compared to state-of-the-art algorithms.

Cognitive diagnosis is a fundamental yet critical research task in the field of intelligent education, which aims to discover the proficiency level of different students on specific knowledge concepts. Despite the effectiveness of existing efforts, previous methods always considered the mastery level on the whole students, so they still suffer from the Long Tail Effect. A large number of students who have sparse interaction records are usually wrongly diagnosed during inference. To relieve the situation, we proposed a Self-supervised Cognitive Diagnosis (SCD) framework which leverages the self-supervised manner to assist the graph-based cognitive diagnosis, then the performance on those students with sparse data can be improved. Specifically, we came up with a graph confusion method that drops edges under some special rules to generate different sparse views of the graph. By maximizing the cross-view consistency of node representations, our model could pay more attention on long-tailed students. Additionally, we proposed an importance-based view generation rule to improve the influence of long-tailed students. Extensive experiments on real-world datasets show the effectiveness of our approach, especially on the students with much sparser interaction records. Our code is available at https://github.com/zeng-zhen/SCD.

The pneumonia caused by COVID-19 is spreading worldwide, threatening human health and life. In the last three years, China has taken a series of effective measures to prevent the spread of the virus, where a core measure is the stay-home quarantine imposed in infected communities. The quarantine can effectively reduce physical contacts and transmission risk, however, it encounters several difficulties especially the guarantee of living materials. In order to ensure the quantity and freshness of living materials such as vegetables and fruits, it is necessary to construct multi-level logistics distribution centers, where the selection of locations for these centers becomes a vital issue. Such facility location problems are challenging in terms of both modeling and optimization, especially when facing the millions of residents and thousands of communities in a city commonly existing in China. In this study, we build a large-scale multi-objective optimization model for the distribution center location problem, and solve it via state-of-the-art sparse evolutionary algorithms. The experimental results verify that the center locations obtained by our approach can save human resources while reducing the risk of virus propagation.

Sparse large-scale multi-objective optimization problems (LSMOPs) widely exist in real-world applications. Due to the characteristics of high-dimensional search space and sparse Pareto optimal solutions, most existing multi-objective evolutionary algorithms encounter difficulties in solving this kind of optimization problems. In this paper, a sparsity-guided elitism co-evolutionary framework, namely SGECF, is proposed. At each generation, SGECF first performs k-means clustering on non-dominated solutions to calculate the present best sparsity. Then, SGECF divides the population into a winner subpopulation and two loser subpopulations based on the Pareto dominance relationship and the present best sparsity. In the process of offspring reproduction, the winner subpopulation generates offspring solutions using conventional genetic operators, and the two loser subpopulations reproduce offspring solutions under the guidance of the present best sparsity and decision variable importance. In the experiments, the performance of SGECF is investigated on eight benchmark problems and a real-world application. Experimental results show that SGECF is superior over four state-of-the-art algorithms.

Cognitive Diagnosis has been widely investigated as a fundamental task in the field of education, aiming at effectively assessing the students' knowledge proficiency level by mining their exercise records. Recently, group-level cognitive diagnosis is also attracting attention, which measures the group-level knowledge proficiency on specific concepts by modeling the response behaviors of all students within the classes. However, existing work tends to explore group characteristics with a coarse-grained perspective while ignoring the inter-individual variability within groups, which is prone to unstable diagnosis results. To this end, in this paper, we propose a novel Homogeneous cohort-aware Group Cognitive Diagnosis model, namely HomoGCD, to effectively model the group's knowledge proficiency level from a multi-grained modeling perspective. Specifically, we first design a homogeneous cohort mining module to explore subgroups of students with similar ability status within a class by modeling their routine exercising performance. Then, we construct the mined cohorts into fine-grained organizations for exploring stable and uniformly distributed features of groups. Subsequently, we develop a multi-grained modeling module to comprehensively learn the cohort and group ability status, which jointly trains both interactions with the exercises. In particular, an extensible diagnosis module is introduced to support the incorporation of different diagnosis functions. Finally, extensive experiments on two real-world datasets clearly demonstrate the generality and effectiveness of our HomoGCD in group as well as cohort~assessments.

Current model quantization methods have shown their promising capability in reducing storage space and computation complexity. However, due to the diversity of quantization forms supported by different hardware, one limitation of existing solutions is that usually require repeated optimization for different scenarios. How to construct a model with flexible quantization forms has been less studied. In this paper, we explore a one-shot network quantization regime, named Elastic Quantization Neural Networks (EQ-Net), which aims to train a robust weight-sharing quantization supernet. First of all, we propose an elastic quantization space (including elastic bit-width, granularity, and symmetry) to adapt to various mainstream quantitative forms. Secondly, we propose the Weight Distribution Regularization Loss (WDR-Loss) and Group Progressive Guidance Loss (GPG-Loss) to bridge the inconsistency of the distribution for weights and output logits in the elastic quantization space gap. Lastly, we incorporate genetic algorithms and the proposed Conditional Quantization-Aware Accuracy Predictor (CQAP) as an estimator to quickly search mixed-precision quantized neural networks in supernet. Extensive experiments demonstrate that our EQ-Net is close to or even better than its static counterparts as well as state-of-the-art robust bit-width methods. Code can be available at https://github.com/xuke225/EQ-Net.

During the past few decades, cognitive diagnostics modeling has attracted increasing attention in computational education communities, which is capable of quantifying the learning status and knowledge mastery levels of students. Indeed, the recent advances in neural networks have greatly enhanced the performance of traditional cognitive diagnosis models through learning the deep representations of students and exercises. Nevertheless, existing approaches often suffer from the issue of overconfidence in predicting students’ mastery levels, which is primarily caused by the unavoidable noise and sparsity in realistic student-exercise interaction data, severely hindering the educational application of diagnostic feedback. To address this, in this paper, we propose a novel Reliable Cognitive Diagnosis (ReliCD) framework, which can quantify the confidence of the diagnosis feedback and is flexible for different cognitive diagnostic functions. Specifically, we first propose a Bayesian method to explicitly estimate the state uncertainty of different knowledge concepts for students, which enables the confidence quantification of diagnostic feedback. In particular, to account for potential differences, we suggest modeling individual prior distributions for the latent variables of different ability concepts using a pre-trained model. Additionally, we introduce a logical hypothesis for ranking confidence levels. Along this line, we design a novel calibration loss to optimize the confidence parameters by modeling the process of student performance prediction. Finally, extensive experiments on four real-world datasets clearly demonstrate the effectiveness of our ReliCD framework.

Most efforts in unsupervised domain adaptation (UDA) focus on learning the domain-invariant representations between the two domains. However, such representations may still confuse two patterns due to the domain gap. Considering that semantic information is useful for the final task and domain information always indicates the discrepancy between two domains, to address this issue, we propose to decouple the representations of semantic features from domain features to reduce domain bias. Different from traditional methods, we adopt a simple but effective module with only one domain discriminator to decouple the representations, offering two benefits. Firstly, it eliminates the need for labeled sample pairs, making it more suitable for UDA. Secondly, without adversarial learning, our model can achieve a more stable training phase. Moreover, to further enhance the task-specific features, we employ a causal mechanism to separate semantic features related to causal factors from the overall feature representations. Specially, we utilize a dual-classifier strategy, where each classifier is fed with the entire features and the semantic features, respectively. By minimizing the discrepancy between the outputs of the two classifiers, the causal influence of the semantic features is accentuated. Experiments on several public datasets demonstrate the proposed model can outperform the state-of-the-art methods. Our code is available at: https://github.com/qzxRtY37/DRLC https://github.com/qzxRtY37/DRLC.

Knowledge tracing (KT) aims to trace students' knowledge states by predicting whether students answer correctly on exercises. Despite the excellent performance of existing Transformer-based KT approaches, they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach.

In many cases, a network may be dispersedly recorded by different participants and each participant is one part of the original network, and no one is willing to share its data due to commercial competition. Therefore, each participant forms an independent private network, and they form a “ multiple private networks” regarding the original network. Existing methods only use the structure of private network itself to predict missing links, leading to underutilized information and deteriorated prediction accuracy. One natural question arises: how to integrate the information of multiple private networks by formulating a security protocol, so as to help each private network to better predict missing links in its own network without disclosing its structure to others. To this end, we propose an SMPC-LP method based on secure multiparty computation (SMPC) to solve this problem. The method fuses the information of each private network without disclosing their inputs, and then, the similarity score of each node pair is jointly calculated, achieving enhanced link prediction performance in each private network. The experimental results show that the SMPC-LP method can better predict the missing links than the methods only using the information of the one private network, without violating data privacy agreement.

Complex optimization problems with hundreds or even thousands of decision variables and dozens of conflicting objectives are not uncommon in the real world. In the past five years, increased research efforts have been dedicated to large-scale multiobjective optimization problems (LSMOPs) by using a variety of search strategies, including variable grouping, variable analysis, problem transformation, dimensionality reduction, and novel recombination operators. Despite the success of these efforts in solving some general LSMOPs, there still remains a big gap between the LSMOPs that have been addressed and those encountered in real life, such as sparse, highly constrained, dynamic, and expensive LMOPs, as well as very large-scale and many-objective optimization problems that are widely seen and of paramount importance for solving scientific and engineering problems. Due to the significant practical importance of large-scale multiobjective optimization, there is a high demand for computationally efficient and effective evolutionary algorithms for solving LSMOPs.

Hyperspectral images (HSI) contain hundreds of bands, which provide a wealth of spectral information and enable better characterization of features. However, the excessive dimensions and redundant information also cause a dimensional disaster for subsequent processing. Band selection is a widely-used dimension reduction technique for hyperspectral images. Traditional methods mainly consider the hyperspectral band selection problem at the level of data, and maintain the information contained in the data, without considering the spatial structures inside hyperspectral images. To fill the gap, in this work, an unsupervised hyperspectral band selection method through structure-conserved and neighborhood-grouped evolutionary algorithm (SNEA) is proposed. Different from other evolutionary algorithms for hyperspectral band selection, firstly, two spatial-structure related optimization objectives are designed, including the locally spatial structure denoted by the pixel’s spatial consistency with its adjacent neighbors and the globally spatial structure denoted by the affinity graph among pixels. With the designed objectives, the hyperspectral band selection is formulated as the problem of conserving spatial structures. Moreover, a neighborhood-grouped pair-wise learning strategy is proposed to generate high-quality offsprings. In this novel strategy, a neighborhood grouping operation is developed to divide the band space into several groups. The population can be initialized efficiently and the offspring solutions can be generated pairwisely under the guidance of grouping. Compared with 9 state-of-the-art comparison algorithms, experimental results on 3 standard hyperspectral datasets demonstrate that the band subset obtained by our proposed SNEA has a better classification performance than the comparison algorithms.

Electric location-routing problem is a challenging problem consisting of the optimization of electric vehicle routing and charging facility location, simultaneously. Existing algorithms generally adopt the two-phase search strategy to alternately optimize the routing and the location. However, they are usually criticized for the inefficiency as the problem scale increases. In order to improve the search efficiency in each phase, we propose an accelerating two-phase multiobjective evolutionary algorithm, where the learning method is used to mine the useful information from the historical search process to generate the high-quality routing and location offspring. To be specific, in the routing optimization phase, an interpolation method is developed to extract the frequent visiting orders existing in the historical best solutions. These frequent visiting orders are used to create potential routing offspring that can accelerate the convergence toward the optimal solutions. In the location optimization phase, a surrogate model is used to approximatively represent the relationship from routing to location, which can directly output a promising location scheme for a given routing offspring and thus reduce the optimization time. Experimental results on different scales of test instances demonstrate the competitiveness of the proposed algorithm in comparison with several state of-the-art algorithms, including four widely used heuristic algorithms and two multiobjective evolutionary algorithms.

Unsupervised domain adaptation, which transfers knowledge from the source domain to the target domain, has still been a challenging problem. However, previous domain adaptation methods typically minimize the domain discrepancy by using the pseudo target labels. Since the pseudo labels can be noisy, which may cause misalignment and unsatisfying adaptation performance. To address the above challenges, we propose an information maximization adaptation network with label distribution priors. We revisit feature alignment in unsupervised domain adaptation from the perspective of distribution alignment, and find that learning discriminant feature representation requires to minimizing distribution discrepancy and maximizing source mutual information between the outputs of the classifier and feature representations. Due to domain shift, maximizing target mutual information may align features to incorrect class directly. We propose a weighted target mutual information by re-weighting the estimated mutual information via the mean prediction confidence in mini-batch, which can eliminate the negative impact of inaccurate estimation. In addition, we introduce a regularization term of label priors distribution to encourage the similarity to the real label distribution. Extensive experimental results on three benchmark datasets show that our proposed method can achieve remarkable results compared with previous methods.

Existing methods regarding the influential nodes identification in complex networks usually assume that the structures of the networks are fully known. However, in many cases, knowing the full structure of one network is hard or impossible, and each participant can only obtain the partial structure of the networks. Therefore, each participant can be viewed as a private network (PN) of the original network, and they form multiple PNs. Then, one question arises: how to collaboratively identify influential nodes in multiple PNs while protecting the privacy of each PN. To this end, a secure multiparty computation ranking (SMPC-ranking) method is proposed to solve such an all-new problem based on the secure multiparty computation (SMPC) protocol, in which the SMPC protocol jointly computes a centrality function to measure the comprehensive importance of nodes or their ranking results by integrating each PN’s inputs without disclosing their inputs (i.e., the nodes’ importance). Experimental results in different networks demonstrate that, no matter what type of the centrality index is, the SMPC-ranking method can better identify the influential nodes in networks than that of the baseline method only using the structural information of one PN. What is more, our SMPC-ranking method does not violate the privacy of each PN. Therefore, the proposed method provides new insights on collaboratively identifying influential nodes in multiple PNs and has potential applications in many fields.

The Pareto front (PF) estimation has become an emerging strategy for solving multiobjective optimization problems in recent studies. By approximating the geometrical structure of the PF during the evolutionary procedure, some PF estimation approaches have been suggested and shown effectiveness in guiding the search direction of evolutionary algorithms. However, these approaches encounter difficulties in handling irregular PFs, whose geometrical structures are too complex to be properly approximated. To address this issue, this article proposes a novel PF estimation approach based on local models. In contrast to existing approaches estimating the PF via a reference point set or a single model, the proposed approach automatically divides the population into several groups and builds a local model for each group of solutions. In spite of the simplicity of each local model, the combination of all the local models can approximate the PFs with complex geometrical structures. An evolutionary algorithm is then developed based on the local model-based PF estimation approach and a novel fitness function and is compared with four evolutionary algorithms on 39 problems. Statistical results indicate that the proposed algorithm exhibits better performance than the compared algorithms, especially on problems with highly irregular PFs.

Evolutionary algorithms and mathematical programming methods are currently the most popular optimizers for solving continuous optimization problems. Owing to the population based search strategies, evolutionary algorithms can find a set of promising solutions without using any problem-specific information. By contrast, with the assistance of gradient and other information of the functions, mathematical programming methods can quickly converge to a single optimum. While these two types of optimizers have their own advantages and disadvantages, the performance comparison between them is rarely touched. It is known that gradient descent methods generally converge faster than evolutionary algorithms, but when can evolutionary algorithms outperform gradient descent methods? How is the scalability of them? To answer these questions, this paper first gives a review of popular evolutionary algorithms and mathematical programming methods, then conducts several experiments to compare their performance from various aspects, and finally draws some conclusions.

Cognitive diagnosis is a fundamental issue of intelligent education platforms, whose goal is to reveal the mastery of students on knowledge concepts. Recently, certain efforts have been made to improve the diagnosis precision, by designing deep neural networks-based diagnostic functions or incorporating more rich context features to enhance the representation of students and exercises. However, how to interpretably infer the student's mastery over non-interactive knowledge concepts (i.e., knowledge concepts not related to his/her exercising records) still remains challenging, especially when not giving relations between knowledge concepts. To this end, we propose a Knowledge-Sensed Cognitive Diagnosis (KSCD) framework, aiming at learning intrinsic relations among knowledge concepts from student response logs and incorporating them for inferring students' mastery over all knowledge concepts in an end-to-end manner. Specifically, we firstly project students, exercises and knowledge concepts into embedding representation matrices, where the intrinsic relations among knowledge concepts are reflected in the knowledge embedding representation matrix. Then, the knowledge-sensed student knowledge mastery vector and exercise factor vectors are obtained by the multiply product of their embedding representations and the knowledge embedding representation matrix, which make the student's mastery of non-interactive knowledge concepts be interpretably inferred. Finally, we can utilize classical student-exercise interaction functions to predict student's exercising performance and jointly train the model. In additional, we also design a new function to better model the student-exercise interactions. Extensive experimental results on two real-world datasets clearly show the significant performance gain of our KSCD framework, especially in predicting students' mastery over non-interactive knowledge concepts, by comparing to state-of-the-art cognitive diagnosis models (CDMs).

With the rapid development of intelligent education platforms, how to enhance the performance of diagnosing students' knowledge proficiency has become an important issue, e.g., by incorporating the prerequisite relation of knowledge concepts. Unfortunately, the differentiated influence from different predecessor concepts to successor concepts is still underexplored in existing approaches. To this end, we propose a Prerequisite Attention model for Knowledge Proficiency diagnosis of students (PAKP) to learn the attentive weights of precursor concepts on successor concepts and model it for inferring the knowledge proficiency. Specifically, given the student response records and knowledge prerequisite graph, we design an embedding layer to output the representations of students, exercises, and concepts. Influence coefficient among concepts is calculated via an efficient attention mechanism in a fusion layer. Finally, the performance of each student is predicted based on the mined student and exercise factors. Extensive experiments on real-data sets demonstrate that PAKP exhibits great efficiency and interpretability advantages without accuracy loss.

As an emerging technology of computer-aided education, cognitive modeling aims at discovering the knowledge proficiency or learning ability of students, which can enable a wide range of intelligent educational applications. While considerable efforts have been made in this direction, a long-standing research challenge is how to naturally integrate the forgetting mechanism into the learning process of knowledge concepts. To this end, in this paper, we propose a novel Continuous Time based Neural Cognitive Modeling(CT-NCM) approach to integrate the dynamism and continuity of knowledge forgetting into students' learning process modeling in a realistic manner. To be specific, we first adapt the neural Hawkes process with a specially-designed learning event encoding method to model the relationship between knowledge learning and forgetting with continuous time. Then, we propose a learning function with extendable settings to jointly model the change of different knowledge states and their interactions with the exercises at each moment. In this way, CT-NCM can simultaneously predict the future knowledge state and exercise performance of students. Finally, we conduct extensive experiments on five real-world datasets with various benchmark methods. The experimental results clearly validate the effectiveness of CT-NCM and show its interpretability in terms of knowledge learning visualization.

Quantization has become a popular technique to compress deep neural networks (DNNs) and reduce computational costs, but most prior work focuses on training DNNs at each individual fixed bit-width and accuracy trade-off point. How to produce a model with flexible precision is largely unexplored. This work proposes a multi-bit quantization framework (MultiQuant) to make the learned DNNs robust for different precision configuration during inference by adopting Lowest-Random-Highest bit-width co-training method. Meanwhile, we propose an online adaptive label generation strategy to alleviate the problem of vicious competition under different precision caused by one-hot labels in the supernet training. The trained supernet model can be flexibly set to different bit widths to support dynamic speed and accuracy trade-off. Furthermore, we adopt the Monte Carlo sampling-based genetic algorithm search strategy with quantization-aware accuracy predictor as evaluation criterion to incorporate the mixed precision technology in our framework. Experiment results on ImageNet datasets demonstrate MultiQuant method can attain the quantization results under different bit-widths comparable with quantization-aware training without retraining.

Identifying functional modules in protein-protein interaction (PPI) networks elucidates cellular organization and mechanism. Various methods have been proposed to identify the functional modules in PPI networks, but most of these methods do not consider the noisy links in PPI networks. They achieve a competitive performance on the PPI networks without noisy links, but the performance of these methods considerably deteriorates in the noisy PPI networks. Furthermore, the noisy links are inevitable in the PPI networks. In this paper, we propose a novel link-driven label propagation algorithm (LLPA) to identify functional modules in PPI networks. The LLPA first find link clusters in PPI networks, and then the functional modules are identified from the link clusters. Two strategies aimed to ensure the robustness of LLPA are proposed. One strategy involves the proposed LLPA updating the link labels in accordance with the designed weight of the link, which can reduce the incidence of noisy links. The other strategy involves the filtration of some noisy labels from the link clusters to further reduce the influence of noisy links. The performance evaluation on three real PPI networks shows that LLPA outperforms other eight state-of-the-art detection algorithms in terms of accuracy and robustness.

Many link prediction algorithms regarding single-layer social networks have been proposed, and however, how to predict interlayer links in multiplex social networks is still in the initial stage. In fact, the prediction of interlayer links in multiplex networks is of great significance, which is closely related to network security, product recommendation, social network mining, and so forth. Given that many social networks are sparse and the number of the first-order common matched neighbors (CMNs) is very few, it is not sufficient to implement link prediction only based on the first-order CMNs. Moreover, many social networks have scale-free property, leading to the roles of CMNs in link prediction which are significantly different. In doing so, we propose a second-order iterative degree penalty (SOIDP) algorithm to predict interlayer links in multiplex networks, in which the information of the first- and second-order CMNs is integrally considered, as well as a degree penalty mechanism is introduced to give larger weight to the CMNs with fewer connections. In particular, to solve the problem of cumulative error in the iterative process, we demonstrate that the interlayer links can be predicted by directly calculating the matching degree matrix without iteration. Experiments on real-world networks show that the performance of SOIDP algorithm in predicting interlayer links is always better than the baseline algorithms, and the accuracy is increased 10% at least. For synthetic networks, the improvement is also very surprising when networks are rather sparse.

In real-world applications, there exist a lot of multiobjective optimization problems whose Pareto-optimal solutions are sparse, that is, most variables of these solutions are 0. Generally, many sparse multiobjective optimization problems (SMOPs) contain a large number of variables, which pose grand challenges for evolutionary algorithms to find the optimal solutions efficiently. To address the curse of dimensionality, this article proposes an evolutionary algorithm for solving large-scale SMOPs, which aims to mine the sparse distribution of the Pareto-optimal solutions and, thus, considerably reduces the search space. More specifically, the proposed algorithm suggests an evolutionary pattern mining approach to detect the maximum and minimum candidate sets of the nonzero variables in the Pareto-optimal solutions, and uses them to limit the dimensions in generating offspring solutions. For further performance enhancement, a binary crossover operator and a binary mutation operator are designed to ensure the sparsity of solutions. According to the results on eight benchmark problems and four real-world problems, the proposed algorithm is superior over existing evolutionary algorithms in solving large-scale SMOPs.

Both objective optimization and constraint satisfaction are crucial for solving constrained multiobjective optimization problems, but the existing evolutionary algorithms encounter difficulties in striking a good balance between them when tackling complex feasible regions. To address this issue, this article proposes a two-stage evolutionary algorithm, which adjusts the fitness evaluation strategies during the evolutionary process to adaptively balance objective optimization and constraint satisfaction. The proposed algorithm can switch between the two stages according to the status of the current population, enabling the population to cross the infeasible region and reach the feasible regions in one stage, and to spread along the feasible boundaries in the other stage. Experimental studies on four benchmark suites and three real-world applications demonstrate the superiority of the proposed algorithm over the state-of-the-art algorithms, especially on problems with complex feasible regions.

Medical image classification is an important task in computer-aided diagnosis systems. Its performance is critically determined by the descriptiveness and discriminative power of features extracted from images. With rapid development of deep learning, deep convolutional neural networks (CNNs) have been widely used to learn the optimal high-level features from the raw pixels of images for a given classification task. However, due to the limited amount of labeled medical images with certain quality distortions, such techniques crucially suffer from the training difficulties, including overfitting, local optimums, and vanishing gradients. To solve these problems, in this article, we propose a two-stage selective ensemble of CNN branches via a novel training strategy called deep tree training (DTT). In our approach, DTT is adopted to jointly train a series of networks constructed from the hidden layers of CNN in a hierarchical manner, leading to the advantage that vanishing gradients can be mitigated by supplementing gradients for hidden layers of CNN, and intrinsically obtain the base classifiers on the middle-level features with minimum computation burden for an ensemble solution. Moreover, the CNN branches as base learners are combined into the optimal classifier via the proposed two-stage selective ensemble approach based on both accuracy and diversity criteria. Extensive experiments on CIFAR-10 benchmark and two specific medical image datasets illustrate that our approach achieves better performance in terms of accuracy, sensitivity, specificity, and F1 score measurement.

Intensity-modulated radiotherapy (IMRT) is one of the most popular techniques for cancer treatment. However, existing IMRT planning methods can only generate one solution at a time and, consequently, medical physicists should perform the planning process many times to obtain diverse solutions to meet the requirement of a clinical case. Meanwhile, multiobjective evolutionary algorithms (MOEAs) have not been fully exploited in IMRT planning since they are ineffective in optimizing the large number of discrete variables of IMRT. To bridge the gap, this article formulates IMRT planning into a large-scale combinatorial many-objective optimization problem and proposes a coevolutionary algorithm to solve it. In contrast to the existing MOEAs handling high-dimensional search spaces via variable grouping or dimensionality reduction, the proposed algorithm evolves one population with fine encoding for local exploitation and evolves another population with rough encoding for global exploration. Moreover, the convergence speed is further accelerated by two customized local search strategies. The experimental results verify that the proposed algorithm outperforms state-of-the-art MOEAs and IMRT planning methods on a variety of clinical cases.

Due to natural disasters or system failures, the facility has the risk of disruption, and thus improving the location reliability under uncertainty of facilities becomes an important issue. In this paper, we propose a multi-objective facility location problem under uncertainty of facilities, where two objectives on reliability are constructed and multiple coverage with variable radius is imposed to reduce the influence caused by the facility disruption. A dual-population based evolutionary algorithm is also suggested to address this problem, where one population is for the location optimization and the other population is for the radius optimization. These two populations iteratively exchange the information obtained from elite solutions during the evolution to collaboratively search for the optimal solutions of the problem. The location population provides the high-quality location schemes for radius population in evaluating the quality of radii of each location, whereas the radius population equips the proper radii for location population in determining the good location schemes. Experimental results indicate that the proposed model can effectively improve the location reliability and the proposed method can obtain higher quality optimal solutions in comparison with four state-of-the-art algorithms. Moreover, the proposed method is applied to a real-world facility location with uncertainty of express cabinets in Tianjin, China, and it produces satisfactory location schemes.

Dynamic vehicle routing problems (DVRPs) have become a hot research topic due to their significance in logistics, although it is still very challenging for existing algorithms to solve DVRPs due to the dynamically changing customer requests during the optimization. In this paper, we propose a pairwise proximity learning-based ant colony algorithm, termed PPL-ACO, for tackling DVRPs. In PPL-ACO, a pairwise proximity learning method is suggested to predict the local visiting order of customers in the optimal route after the occurrence of changes, which is on the basis of learning from the optimal routes found before the changes occur. A radial basis function network is used to learn the local visiting order of customers based on the proximity between each pair of customer nodes, by which the optimal routes can be quickly tracked after changes occur. Experimental results on 22 popular DVRP instances show that the proposed PPL-ACO significantly outperforms four state-of-the-art approaches to DVRPs. More interestingly, the results on five large-scale DVRP instances demonstrate the superiority of the proposed PPL-ACO in solving large-scale DVPRs with up to 1000 customers. The results on a real case of Nankai Strict, Tianjin, China also verifies that the proposed PPL-ACO is more effective and efficient than the four compared approaches in solving real-world DVRPs.

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

Due to the curse of dimensionality of search space, it is extremely difficult for evolutionary algorithms to approximate the optimal solutions of large-scale multiobjective optimization problems (LMOPs) by using a limited budget of evaluations. If the Pareto-optimal subspace is approximated during the evolutionary process, the search space can be reduced and the difficulty encountered by evolutionary algorithms can be highly alleviated. Following the above idea, this article proposes an evolutionary algorithm to solve sparse LMOPs by learning the Pareto-optimal subspace. The proposed algorithm uses two unsupervised neural networks, a restricted Boltzmann machine, and a denoising autoencoder to learn a sparse distribution and a compact representation of the decision variables, where the combination of the learnt sparse distribution and compact representation is regarded as an approximation of the Pareto-optimal subspace. The genetic operators are conducted in the learnt subspace, and the resultant offspring solutions then can be mapped back to the original search space by the two neural networks. According to the experimental results on eight benchmark problems and eight real-world problems, the proposed algorithm can effectively solve sparse LMOPs with 10000 decision variables by only 100000 evaluations.

The capacitated vehicle routing problem (CVRP) has been extensively investigated in the past years due to their applications in a variety of real-world scenarios. However, it is still very challenging for most existing algorithms to tackle large-scale CVRPs (LSCVRPs), namely, CVRPs with hundreds or thousands of customers. In this article, we propose a heuristic algorithm, called EMRG-HA, to address LSCVRPs based on the framework of divide and conquer, where an evolutionary multiobjective route grouping (EMRG) method is suggested to decompose an LSCVRP into small subcomponents. The suggested EMRG adopts a multiobjective evolutionary algorithm for route grouping by simultaneously optimizing three well-defined objectives, intragroup distance, intergroup distance, and intergroup balance in size, which can obtain a set of promising decompositions of LSCVRPs. Based on the EMRG, a local search method is suggested to improve the quality of routes in groups, where only routes in one group instead of in all groups are improved which is determined according to the average serving cost of routes in each group. The performance of the proposed EMRG-HA is verified on 42 test instances from three popular benchmark suites. The experimental results show that the EMRG-HA is superior over eight existing algorithms on most test instances of LSCVRPs, in terms of both computational efficiency and solution quality.

Constrained multiobjective optimization problems (CMOPs) widely exist in real-world applications, and they are challenging for conventional evolutionary algorithms (EAs) due to the existence of multiple constraints and objectives. When the number of objectives or decision variables is scaled up in CMOPs, the performance of EAs may degenerate dramatically and may fail to obtain any feasible solutions. To address this issue, we propose a paired offspring generation-based multiobjective EA for constrained large-scale optimization. The general idea is to emphasize the role of offspring generation in reproducing some promising feasible or useful infeasible offspring solutions. We first adopt a small set of reference vectors for constructing several subpopulations with a fixed number of neighborhood solutions. Then, a pairing strategy is adopted to determine some pairwise parent solutions for offspring generation. Consequently, the pairwise parent solutions, which could be infeasible, may guide the generation of well-converged solutions to cross the infeasible region(s) effectively. The proposed algorithm is evaluated on CMOPs with up to 1000 decision variables and ten objectives. Moreover, each component in the proposed algorithm is examined in terms of its effect on the overall algorithmic performance. Experimental results on a variety of existing and our tailored test problems demonstrate the effectiveness of the proposed algorithm in constrained large-scale multiobjective optimization.

Multimodal multiobjective optimization problems (MMOPs) widely exist in real-world applications, which have multiple equivalent Pareto-optimal solutions that are similar in the objective space but totally different in the decision space. While some evolutionary algorithms (EAs) have been developed to find the equivalent Pareto-optimal solutions in recent years, they are ineffective to handle large-scale MMOPs having a large number of variables. This article thus proposes an EA for solving large-scale MMOPs with sparse Pareto-optimal solutions, i.e., most variables in the optimal solutions are 0. The proposed algorithm explores different regions of the decision space via multiple subpopulations and guides the search behavior of the subpopulations via adaptively updated guiding vectors. The guiding vector for each subpopulation not only provides efficient convergence in the huge search space but also differentiates its search direction from others to handle the multimodality. While most existing EAs solve MMOPs with 2-7 decision variables, the proposed algorithm is shown to be effective for benchmark MMOPs with up to 500 decision variables. Moreover, the proposed algorithm also produces a better result than state-of-the-art methods for the neural architecture search.

Constrained multiobjective optimization problems (CMOPs) are challenging because of the difficulty in handling both multiple objectives and constraints. While some evolutionary algorithms have demonstrated high performance on most CMOPs, they exhibit bad convergence or diversity performance on CMOPs with small feasible regions. To remedy this issue, this article proposes a coevolutionary framework for constrained multiobjective optimization, which solves a complex CMOP assisted by a simple helper problem. The proposed framework evolves one population to solve the original CMOP and evolves another population to solve a helper problem derived from the original one. While the two populations are evolved by the same optimizer separately, the assistance in solving the original CMOP is achieved by sharing useful information between the two populations. In the experiments, the proposed framework is compared to several state-of-the-art algorithms tailored for CMOPs. High competitiveness of the proposed framework is demonstrated by applying it to 47 benchmark CMOPs and the vehicle routing problem with time windows.

The algorithm recommendation is attracting increasing attention in solving real-world capacitated vehicle routing problems (CVRPs), due to the fact that existing meta-heuristic algorithms often show different performances on different CVRPs. To effectively perform algorithm recommendation for CVRPs, it becomes vital to extract suitable features to characterize the CVRPs accurately. To this end, in this article three groups of penetrating features are proposed to capture the characteristics of CVRPs. The first group consists of some basic features of CVRPs, where several features are suggested to capture the distribution of customer demand, the relationship between customer demand and vehicle capacity, besides some common attributes widely used in CVRPs. The second group is composed of the features extracted from some CVRP solutions generated by local search, where in addition to the feasible and better solutions, the worse solutions and the distribution of travel cost are also used to measure the sensitivity of CVRPs to local search operations. The third group is made up of image features obtained by depicting CVRP instances through images, which is first introduced by us to enhance the generalization of algorithm recommendation. Furthermore, based on the three groups of features, an algorithm recommendation method called ARM-I is built on the basis of a KNN classifier to recommend suitable algorithm for CVRPs. Experimental results on several selected benchmarks demonstrate the effectiveness of the designed features. More interestingly, the proposed ARM-I shows high generalization on real-world instances.

As the size of available networks is continuously increasing (even with millions of nodes), large-scale complex networks are receiving significant attention. While existing overlapping-community detection algorithms are quite effective in analyzing complex networks, most of these algorithms suffer from scalability issues when applied to large-scale complex networks, which can have more than 1,000,000 nodes. To address this problem, we propose an efficient local-expansion-based overlapping-community detection algorithm using local-neighborhood information (OCLN). During the iterative expansion process, only neighbors of nodes added in the last iteration (rather than all neighbors) are considered to determine whether they can join the community. This significantly reduces the computational cost and enhances the scalability for community detection in large-scale networks. A belonging coefficient is also proposed in OCLN to filter out incorrectly identified nodes. Theoretical analysis demonstrates that the computational complexity of the proposed OCLN is linear with respect to the size of the network to be detected. Experiments on large-scale LFR benchmark and real-world networks indicate the effectiveness of OCLN for overlapping-community detection in large-scale networks, in terms of both computational efficiency and detected-community quality.

Community detection has been recognized as one of the most important tools to discover useful information hidden in complex networks which is usually hard to be obtained by simple observations. Existing community detection algorithms have demonstrated their effectiveness on a variety of complex networks, most of them, however, suffer from the scalability issue on complex networks without a clear community structure due to the challenge in the detection of ambiguous community structure. To address this issue, in this paper, we propose a community structure enhancement method, termed CSE, for community detection in complex networks. In the proposed CSE, the community structure of a network is enhanced by adding links between the nodes possibly belonging to the same community and reducing links between those belonging to different communities, thereby converting an ambiguous community structure into a structure much clearer than the original one. The experimental results show the superior performance of the proposed CSE over five state-of-the-art community detection algorithms on both synthetic benchmark networks and real-world networks, especially for those without a clear community structure.

Diversity preservation is a crucial technique in multiobjective evolutionary algorithms (MOEAs), which aims at evolving the population toward the Pareto front (PF) with a uniform distribution and a good extensity. In spite of many diversity preservation approaches in existing MOEAs, most of them encounter difficulties in tackling complex PFs. This article gives a detail introduction to existing diversity preservation approaches, as well as a revelation of the limitations of them. To address the limitations of existing diversity preservation approaches, this article proposes a multistage MOEA for better diversity performance. The proposed MOEA divides the optimization process into multiple stages according to the population in each generation, and updates the population by different steady-state selection schemes in different stages. According to the experimental results on 21 benchmark problems, the proposed MOEA exhibits better diversity performance than 11 existing MOEAs.

Due to the curse of dimensionality, two main issues remain challenging for applying evolutionary algorithms (EAs) to large-scale multiobjective optimization. The first issue is how to improve the efficiency of EAs for reducing computation cost. The second one is how to improve the diversity maintenance of EAs to avoid local optima. Nevertheless, these two issues are somehow conflicting with each other, and thus it is crucial to strike a balance between them in practice. Thereby, we propose an iterated problem reformulation based EA for large-scale multiobjective optimization, where the problem reformulation based method and the decomposition based method are used iteratively to address the aforementioned issues. The proposed method is compared with several state-of-the-art EAs on a variety of large-scale multiobjective optimization problems. Experimental results demonstrate the effectiveness of our proposed iterated method in large-scale multiobjective optimization.

It has been widely recognized that evolutionary computation is one of the most effective techniques for solving complex optimization problems. As a group of meta-heuristics inspired by nature, the superiority of evolutionary algorithms is mainly attributed to the evolution of multiple candidate solutions, which can strike a balance between exploration and exploitation. However, the effectiveness of evolutionary algorithms is generally at the expense of efficiency, which reduces the prevalence of evolutionary algorithms in solving real-world optimization problems. In 2017, we proposed the evolutionary multi-objective optimization platform PlatEMO to facilitate the use of multi-objective evolutionary algorithms (MOEAs), where some delicate techniques were developed to improve the computational efficiency of MOEAs. These techniques have not been introduced before, since users need not care about them when using existing MOEAs or developing new MOEAs. To deepen the understanding of the core mechanisms of PlatEMO, this paper gives a comprehensive introduction to these techniques, including new non-dominated sorting approaches, matrix calculation, and parallel computing. Several comparative experiments are conducted for a quantitative understanding of the efficiency improvement brought by these techniques.

In evolutionary multiobjective optimization, the Pareto front (PF) is approximated by using a set of representative candidate solutions with good convergence and diversity. However, most existing multiobjective evolutionary algorithms (MOEAs) have general difficulty in the approximation of PFs with complicated geometries. To address this issue, we propose a generic front modeling method for evolutionary multiobjective optimization, where the shape of the nondominated front is estimated by training a generalized simplex model. On the basis of the estimated front, we further develop an MOEA, where both the mating selection and environmental selection are driven by the approximate nondominated fronts modeled during the optimization process. For performance assessment, the proposed algorithm is compared with several state-of-the-art evolutionary algorithms on a wide range of benchmark problems with various types of PFs and different numbers of objectives. Experimental results demonstrate that the proposed algorithm performs consistently on a variety of multiobjective optimization problems.

There exist many multiobjective optimization problems (MOPs) containing a large number of decision variables in real-world applications, which are known as large-scale MOPs. Due to the ineffectiveness of existing operators in finding optimal solutions in a huge decision space, some decision variable division-based algorithms have been tailored for improving the search efficiency in solving large-scale MOPs. However, these algorithms will encounter difficulties when solving problems with complicated landscapes, as the decision variable division is likely to be inaccurate and time consuming. In this paper, we propose a competitive swarm optimizer (CSO)-based efficient search for solving large-scale MOPs. The proposed algorithm adopts a new particle updating strategy that suggests a two-stage strategy to update position, which can highly improve the search efficiency. The experimental results on large-scale benchmark MOPs and an application example demonstrate the superiority of the proposed algorithm over several state-of-the-art multiobjective evolutionary algorithms, including problem transformation-based algorithm, decision variable clustering-based algorithm, particle swarm optimization algorithm, and estimation of distribution algorithm.

Evolutionary algorithms have been demonstrated to be very competitive in the community detection for complex networks. They, however, show poor scalability to large-scale networks due to the exponential increase of search space. In this paper, we suggest a network reduction-based multiobjective evolutionary algorithm for community detection in large-scale networks, where the size of the networks is recursively reduced as the evolution proceeds. In each reduction of the network, the local communities found by the elite individuals in the population are identified as nodes of the reduced network for further evolution, thereby considerably reducing the search space. A local community repairing strategy is also suggested to correct the misidentified nodes after each network reduction during the evolution. Experimental results on synthetic and real-world networks demonstrate the superiority of the proposed algorithm over several state-of-the-art community detection algorithms for large-scale networks, in terms of both computational efficiency and detection performance.

In the last two decades, a variety of different types of multiobjective optimization problems (MOPs) have been extensively investigated in the evolutionary computation community. However, most existing evolutionary algorithms encounter difficulties in dealing with MOPs whose Pareto optimal solutions are sparse (i.e., most decision variables of the optimal solutions are zero), especially when the number of decision variables is large. Such large-scale sparse MOPs exist in a wide range of applications, for example, feature selection that aims to find a small subset of features from a large number of candidate features, or structure optimization of neural networks whose connections are sparse to alleviate overfitting. This paper proposes an evolutionary algorithm for solving large-scale sparse MOPs. The proposed algorithm suggests a new population initialization strategy and genetic operators by taking the sparse nature of the Pareto optimal solutions into consideration, to ensure the sparsity of the generated solutions. Moreover, this paper also designs a test suite to assess the performance of the proposed algorithm for large-scale sparse MOPs. The experimental results on the proposed test suite and four application examples demonstrate the superiority of the proposed algorithm over seven existing algorithms in solving large-scale sparse MOPs.

In the last decade, the detection of overlapping communities has received increasing attention in network science. Among various clustering techniques, the fuzzy clustering has been widely adopted in overlapping community detection, since the soft assignment provided by it naturally meets the overlapping between multiple communities. The crucial step of fuzzy-clustering-based overlapping community detection is to find the optimal community centers, so that the overlapping communities can be obtained according to the membership degrees between nodes and community centers. In this article, we propose an evolutionary multiobjective optimization-based fuzzy method for overlapping community detection. In contrast to traditional fuzzy clustering methods, the proposed method optimizes the community centers by using a specially tailored multiobjective evolutionary algorithm. Moreover, it can also find an appropriate fuzzy threshold for each node, so that diverse overlapping community structures can be uncovered. In the experiments, we compare the proposed method with six state-of-the-art overlapping community detection approaches on synthetic and real-world networks with different scales and characteristics. The statistical results demonstrate that the proposed method can obtain the best results on most test instances.

The shelter location is very important for evacuation planning in natural disasters, and evolutionary algorithms (EAs) have demonstrated their effectiveness in solving this challenging problem. However, few EAs have been reported focusing on the shelter location problem under uncertainty of road networks due to the expensive cost of calculating the evacuation distance for individual evaluation. To address this issue, in this article, we propose a clustering-based surrogate-assisted multiobjective EA, termed AR-MOEA+SA, in the framework of a recently developed EA AR-MOEA. In AR-MOEA+SA, a surrogate model, the radial basis function (RBF), is adopted to approximately calculate the evacuation distance under uncertainty of road networks. Due to the fact that there often exist a large number of communities needing to be considered in shelter location, a clustering strategy is suggested to convert the surrogate of high-dimensional problem into the one of low-dimensional problem in the proposed AR-MOEA+SA for efficiently building the RBF network. A population initialization strategy is also suggested in AR-MOEA+SA to enhance the quality of training data in the early stages of evolution. Experimental results on a variety of test instances demonstrate the superiority of the proposed AR-MOEA+SA over the original version of AR-MOEA in terms of both computational efficiency and solution quality.

Many real-world optimization problems are characterized by multiple conflicting objectives, which are known as multi-objective optimization problems (MOPs). In the last two decades, evolutionary algorithms have shown promising performance in solving various MOPs, and a large number of multi-objective evolutionary algorithms (MOEAs) have been proposed. In order to determine the most suitable MOEA for a specific MOP, it is usually necessary to perform experiments to compare the performance of multiple candidate MOEAs. In 2017, an evolutionary multi-objective optimization platform was proposed by us, called PlatEMO, which provides the source codes of many state-of-the-art MOEAs and helps researchers perform batch experiments on these MOEAs. In this work, we illustrate the method of using the newest version of PlatEMO to solve MOPs in applications, by means of a case study on the feature selection problem, which is an important and difficult task in machine learning and data mining. This paper details the method of adding the feature selection problem to PlatEMO, and presents the experimental results of eight MOEAs on nine datasets in feature selection.

In this paper, we propose a framework to accelerate the computational efficiency of evolutionary algorithms on large-scale multiobjective optimization. The main idea is to track the Pareto optimal set (PS) directly via problem reformulation. To begin with, the algorithm obtains a set of reference directions in the decision space and associates them with a set of weight variables for locating the PS. Afterwards, the original large-scale multiobjective optimization problem is reformulated into a low-dimensional single-objective optimization problem. In the reformulated problem, the decision space is reconstructed by the weight variables and the objective space is reduced by an indicator function. Thanks to the low dimensionality of the weight variables and reduced objective space, a set of quasi-optimal solutions can be obtained efficiently. Finally, a multiobjective evolutionary algorithm is used to spread the quasi-optimal solutions over the approximate Pareto optimal front evenly. Experiments have been conducted on a variety of large-scale multiobjective problems with up to 5000 decision variables. Four different types of representative algorithms are embedded into the proposed framework and compared with their original versions, respectively. Furthermore, the proposed framework has been compared with two state-of-the-art algorithms for large-scale multiobjective optimization. The experimental results have demonstrated the significant improvement benefited from the framework in terms of its performance and computational efficiency in large-scale multiobjective optimization.

Surrogate-assisted evolutionary algorithms (SAEAs) have been developed mainly for solving expensive optimization problems where only a small number of real fitness evaluations are allowed. Most existing SAEAs are designed for solving low-dimensional single or multiobjective optimization problems, which are not well suited for many-objective optimization. This paper proposes a surrogate-assisted many-objective evolutionary algorithm that uses an artificial neural network to predict the dominance relationship between candidate solutions and reference solutions instead of approximating the objective values separately. The uncertainty information in prediction is taken into account together with the dominance relationship to select promising solutions to be evaluated using the real objective functions. Our simulation results demonstrate that the proposed algorithm outperforms the state-of-the-art evolutionary algorithms on a set of many-objective optimization test problems.

Both convergence and diversity are crucial to evolutionary many-objective optimization, whereas most existing dominance relations show poor performance in balancing them, thus easily leading to a set of solutions concentrating on a small region of the Pareto fronts. In this paper, a novel dominance relation is proposed to better balance convergence and diversity for evolutionary many-objective optimization. In the proposed dominance relation, an adaptive niching technique is developed based on the angles between the candidate solutions, where only the best converged candidate solution is identified to be nondominated in each niche. Experimental results demonstrate that the proposed dominance relation outperforms existing dominance relations in balancing convergence and diversity. A modified NSGA-II is suggested based on the proposed dominance relation, which shows competitiveness against the state-of-the-art algorithms in solving many-objective optimization problems. The effectiveness of the proposed dominance relation is also verified on several other existing multi- and many-objective evolutionary algorithms.

The effectiveness of evolutionary algorithms have been verified on multi-objective optimization, and a large number of multi-objective evolutionary algorithms have been proposed during the last two decades. To quantitatively compare the performance of different algorithms, a set of uniformly distributed reference points sampled on the Pareto fronts of benchmark problems are needed in the calculation of many performance metrics. However, not much work has been done to investigate the method for sampling reference points on Pareto fronts, even though it is not an easy task for many Pareto fronts with irregular shapes. More recently, an evolutionary multi-objective optimization platform was proposed by us, called PlatEMO, which can automatically generate reference points on each Pareto front and use them to calculate the performance metric values. In this paper, we report the reference point sampling methods used in PlatEMO for different types of Pareto fronts. Experimental results show that the reference points generated by the proposed sampling methods can evaluate the performance of algorithms more accurately than randomly sampled reference points.

During the past two decades, a variety of multiobjective evolutionary algorithms (MOEAs) have been proposed in the literature. As pointed out in some recent studies, however, the performance of an MOEA can strongly depend on the Pareto front shape of the problem to be solved, whereas most existing MOEAs show poor versatility on problems with different shapes of Pareto fronts. To address this issue, we propose an MOEA based on an enhanced inverted generational distance indicator, in which an adaptation method is suggested to adjust a set of reference points based on the indicator contributions of candidate solutions in an external archive. Our experimental results demonstrate that the proposed algorithm is versatile for solving problems with various types of Pareto fronts, outperforming several state-of-the-art evolutionary algorithms for multiobjective and many-objective optimization.

The current literature of evolutionary many-objective optimization is merely focused on the scalability to the number of objectives, while little work has considered the scalability to the number of decision variables. Nevertheless, many real-world problems can involve both many objectives and large-scale decision variables. To tackle such large-scale many-objective optimization problems (MaOPs), this paper proposes a specially tailored evolutionary algorithm based on a decision variable clustering method. To begin with, the decision variable clustering method divides the decision variables into two types: 1) convergence-related variables and 2) diversity-related variables. Afterward, to optimize the two types of decision variables, a convergence optimization strategy and a diversity optimization strategy are adopted. In addition, a fast nondominated sorting approach is developed to further improve the computational efficiency of the proposed algorithm. To assess the performance of the proposed algorithm, empirical experiments have been conducted on a variety of large-scale MaOPs with up to ten objectives and 5000 decision variables. Our experimental results demonstrate that the proposed algorithm has significant advantages over several state-of-the-art evolutionary algorithms in terms of the scalability to decision variables on MaOPs.

Community detection is an important tool to analyze hidden information such as functional module and topology structure in complex networks. Compared with traditional community detection, it is more challenging to find overlapping communities in complex networks, especially when the networks are of large scales. Among various overlapping community detection techniques, the well-known clique percolation method (CPM) has shown promising performance in terms of quality of found communities, but suffers from serious curse of dimensionality due to its high computational complexity, which makes it very unlikely to be applied to large-scale networks. To address this issue, in this paper, we propose a weak-CPM for overlapping community detection in large-scale networks. A new measure for characterizing the similarity between weak cliques is also suggested to check whether the weak cliques can be merged into a community. Experimental results on synthetic and realworld networks demonstrate the competitive performance of the proposed method over six popular overlapping community detection algorithms in terms of both computational efficiency and quality of found communities. In addition, the proposed method is also suitable for detecting large-scale networks with an unclear community structure under different levels of overlapping density and overlapping diversity, which is an important property of many real-world complex networks.

Designing multiobjective evolutionary algorithms (MOEAs) for community detection in complex networks has attracted much attention of researchers recently. However, most of the existing methods focus on addressing the task of nonoverlapping community detection, where each node must belong to one and only one community. In fact, communities are often overlapped with each other in many real-world networks, thus it is necessary to design overlapping community detection algorithms. To this end, this paper proposes a mixed representation-based MOEA (MR-MOEA) for overlapping community detection. In MR-MOEA, a mixed individual representation scheme is proposed to fast encode and decode the overlapping divisions of complex networks. Specifically, this mixed representation consists of two parts: one represents all potential overlapping nodes and the other delegates all nonoverlapping nodes. These two parts evolve together to detect the overlapping communities of networks based on different updating strategies suggested in MR-MOEA. We verify the effectiveness of the proposed algorithm MR-MOEA on ten real-world complex networks and the experimental results demonstrate that MR-MOEA is superior over six representative algorithms for overlapping community detection.

Non-small cell lung cancer (NSCLC) is a malignant tumor, and contains three major subtypes which are difficult to be distinguished at early stages of NSCLC. Many pathways work together to perform certain functions in cells. One might expect the high level of co-appearance or repression of pathways to distinguish different subtypes of NSCLC. However, it is difficult to detect coordinated regulations of pathways by existing methods. In our work, the coordinated regulations of pathways are detected using modified higher logic analysis of gene expression data. Specifically, we identify the genes whose regulation obeys a logic function by the modified higher logic analysis, which focuses on the relationships among the gene triplets that are not evident when genes are examined in a pairwise fashion. Then, the relationships among genes are mapped to pathways to predict the coordinated regulated relationships among pathways. By comparing coordinated regulations of pathways, we find that the regulation patterns of pathways which are associated with cell death are different in three subtypes of NSCLC. This method allows us to uncover co-appearance or repression of pathways in high level, and it has a potential to distinguish the subtypes for complex diseases.

In this paper, we propose a sampling approach of reference points used for performance metrics of multi-objective evolutionary algorithms. Traditional reference point sampling methods, such as the Das and Dennis method, usually sample the reference points via a set of uniformly distributed weight vectors generated on an ideal hyper-plane in objective space, which however often ignore the geometric shape of a specific Pareto front. Therefore, we propose a novel reference point sampling approach by taking the specific shape of the Pareto optimal front to be tackled into account for measuring the performance of multi-objective evolutionary algorithms. The performance of the proposed reference point sampling method against the other two state-of-the-art sampling methods is tested on six test instances in various conditions, which clearly demonstrate the effectiveness and superiority of the proposed sampling method.

As a pivotal component in multi-objective evolutionary algorithms (MOEAs), the environmental selection determines the quality of candidate solutions to survive at each generation. In practice, different environmental selection strategies can be based on different selection criteria, where the performance metrics (or indicators) are shown to be among the most effective ones. This paper proposes an MOEA whose environmental selection is based on an enhanced inverted generational distance metric that is able to detect noncontributing solutions (termed IGD-NS), thereby considerably accelerating the convergence of the evolutionary search. Experimental results on ZDT and DTLZ test suites demonstrate the competitive performance of the proposed MOEA/IGD-NS in comparison with some representative MOEAs.

Evolutionary algorithms have been shown to be powerful for solving multiobjective optimization problems, in which nondominated sorting is a widely adopted technique in selection. This technique, however, can be computationally expensive, especially when the number of individuals in the population becomes large. This is mainly because in most existing nondominated sorting algorithms, a solution needs to be compared with all other solutions before it can be assigned to a front. In this paper we propose a novel, computationally efficient approach to nondominated sorting, termed efficient nondominated sort (ENS). In ENS, a solution to be assigned to a front needs to be compared only with those that have already been assigned to a front, thereby avoiding many unnecessary dominance comparisons. Based on this new approach, two nondominated sorting algorithms have been suggested. Both theoretical analysis and empirical results show that the ENS-based sorting algorithms are computationally more efficient than the state-of-the-art nondominated sorting methods.

Evolutionary algorithms (EAs) have shown to be promising in solving many-objective optimization problems (MaOPs), where the performance of these algorithms heavily depends on whether solutions that can accelerate convergence toward the Pareto front and maintaining a high degree of diversity will be selected from a set of nondominated solutions. In this paper, we propose a knee point-driven EA to solve MaOPs. Our basic idea is that knee points are naturally most preferred among nondominated solutions if no explicit user preferences are given. A bias toward the knee points in the nondominated solutions in the current population is shown to be an approximation of a bias toward a large hypervolume, thereby enhancing the convergence performance in many-objective optimization. In addition, as at most one solution will be identified as a knee point inside the neighborhood of each solution in the nondominated front, no additional diversity maintenance mechanisms need to be introduced in the proposed algorithm, considerably reducing the computational complexity compared to many existing multiobjective EAs for many-objective optimization. Experimental results on 16 test problems demonstrate the competitiveness of the proposed algorithm in terms of both solution quality and computational efficiency.

Axon P systems are computing models with a linear structure in the sense that all nodes (i.e., computing units) are arranged one by one along the axon. Such models have a good biological motivation: an axon in a nervous system is a complex information processor of impulse signals. Because the structure of axon P systems is linear, the computational power of such systems has been proved to be greatly restricted; in particular, axon P systems are not universal as language generators. It remains open whether axon P systems are universal as number generators. In this paper, we prove that axon P systems are universal as both number generators and function computing devices, and investigate the number of nodes needed to construct a universal axon P system. It is proved that four nodes (respectively, nine nodes) are enough for axon P systems to achieve universality as number generators (respectively, function computing devices). These results illustrate that the simple linear structure is enough for axon P systems to achieve a desired computational power.

Spiking neural P systems (SN P systems, for short) with rules on synapses are a new variant of SN P systems, where the spiking and forgetting rules are placed on synapses instead of in neurons. Recent studies illustrated that this variant of SN P sys

Spiking neural P systems with weights are a new class of distributed and parallel computing models inspired by spiking neurons. In such models, a neuron fires when its potential equals a given value (called a threshold). In this work, spiking neural P systems with thresholds (SNPT systems) are introduced, where a neuron fires not only when its potential equals the threshold but also when its potential is higher than the threshold. Two types of SNPT systems are investigated. In the first one, we consider that the firing of a neuron consumes part of the potential (the amount of potential consumed depends on the rule to be applied). In the second one, once a neuron fires, its potential vanishes (i.e., it is reset to zero). The computation power of the two types of SNPT systems is investigated. We prove that the systems of the former type can compute all Turing computable sets of numbers and the systems of the latter type characterize the family of semilinear sets of numbers. The results show that the firing mechanism of neurons has a crucial influence on the computation power of the SNPT systems, which also answers an open problem formulated in Wang, Hoogeboom, Pan, Păun, and Pérez-Jiménez ( 2010 ).

Spiking neural P systems (SN P systems) are a class of distributed parallel computing devices inspired by spiking neurons, where the spiking rules are usually used in a sequential way (an applicable rule is applied one time at a step) or an exhaustive way (an applicable rule is applied as many times as possible at a step). In this letter, we consider a generalized way of using spiking rules by "combining" the sequential way and the exhaustive way: if a rule is used at some step, then at that step, it can be applied any possible number of times, nondeterministically chosen. The computational power of SN P systems with a generalized use of rules is investigated. Specifically, we prove that SN P systems with a generalized use of rules consisting of one neuron can characterize finite sets of numbers. If the systems consist of two neurons, then the computational power of such systems can be greatly improved, but not beyond generating semilinear sets of numbers. SN P systems with a generalized use of rules consisting of three neurons are proved to generate at least a non-semilinear set of numbers. In the case of allowing enough neurons, SN P systems with a generalized use of rules are computationally complete. These results show that the number of neurons is crucial for SN P systems with a generalized use of rules to achieve a desired computational power.

Spiking neural P systems (SN P systems) are a class of distributed parallel computing devices inspired by the way neurons communicate by means of spikes; neurons work in parallel in the sense that each neuron that can fire should fire, but the work in each neuron is sequential in the sense that at most one rule can be applied at each computation step. In this work, with biological inspiration, we consider SN P systems with the restriction that at each step, one of the neurons (i.e., sequential mode) or all neurons (i.e., pseudo-sequential mode) with the maximum (or minimum) number of spikes among the neurons that are active (can spike) will fire. If an active neuron has more than one enabled rule, it nondeterministically chooses one of the enabled rules to be applied, and the chosen rule is applied in an exhaustive manner (a kind of local parallelism): the rule is used as many times as possible. This strategy makes the system sequential or pseudo-sequential from the global view of the whole network and locally parallel at the level of neurons. We obtain four types of SN P systems: maximum/minimum spike number induced sequential/pseudo-sequential SN P systems with exhaustive use of rules. We prove that SN P systems of these four types are all Turing universal as number-generating computation devices. These results illustrate that the restriction of sequentiality may have little effect on the computation power of SN P systems.

Different biological processes take different times to be completed, which can also be influenced by many environmental factors. In this work, a realistic definition of nonsynchronized spiking neural P systems (SN P systems, for short) is considered: during the work of an SN P system, the execution times of spiking rules cannot be known exactly (i.e., they are arbitrary). In order to establish robust systems against the environmental factors, a special class of SN P systems, called time-free SN P systems, is introduced, which always produce the same computation result independent of the execution times of the rules. The universality of time-free SN P systems is investigated. It is proved that these P systems with extended rules (several spikes can be produced by a rule) are equivalent to register machines. However, if the number of spikes present in the system is bounded, then the power of time-free SN P systems falls, and in this case, a characterization of semilinear sets of natural numbers is obtained.

Spiking neural P systems are a class of distributed parallel computing models inspired from the way the neurons communicate with each other by means of electrical impulses (called "spikes"). In this paper, we consider a restricted variant of spiking neural P systems, called homogeneous spiking neural P systems, where each neuron has the same set of rules. The universality of homogeneous spiking neural P systems is investigated. One of universality results is that it is sufficient for homogeneous spiking neural P system to have only one neuron that behaves nondeterministically in order to achieve Turing completeness.