arXiv subjects

Yi Mei

Publications and source records attributed to Yi Mei.

At least 37 records · Page 2Linked to original sources

arXiv2025

ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data

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

cs.LG↗

arXiv2025

GAMA: A Neural Neighborhood Search Method with Graph-aware Multi-modal Attention for Vehicle Routing Problem

Recent advances in neural neighborhood search methods have shown potential in tackling Vehicle Routing Problems (VRPs). However, most existing approaches rely on simplistic state representations and fuse heterogeneous information via naive concatenation, limiting their ability to capture rich structural and semantic context. To address these limitations, we propose GAMA, a neural neighborhood search method with Graph-aware Multi-modal Attention model in VRP. GAMA encodes the problem instance and its evolving solution as distinct modalities using graph neural networks, and models their intra- and inter-modal interactions through stacked self- and cross-attention layers. A gated fusion mechanism further integrates the multi-modal representations into a structured state, enabling the policy to make informed and generalizable operator selection decisions. Extensive experiments conducted across various synthetic and benchmark instances demonstrate that the proposed algorithm GAMA significantly outperforms the recent neural baselines. Further ablation studies confirm that both the multi-modal attention mechanism and the gated fusion design play a key role in achieving the observed performance gains.

cs.AI↗

arXiv2025

SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control

Deep Reinforcement Learning have achieved significant success in automatically devising effective traffic signal control (TSC) policies. Neural policies, however, tend to be over-parameterized and non-transparent, hindering their interpretability and deployability on resource-limited edge devices. This work presents SymLight, a priority function search framework based on Monte Carlo Tree Search (MCTS) for discovering inherently interpretable and deployable symbolic priority functions to serve as the TSC policies. The priority function, in particular, accepts traffic features as input and then outputs a priority for each traffic signal phase, which subsequently directs the phase transition. For effective search, we propose a concise yet expressive priority function representation. This helps mitigate the combinatorial explosion of the action space in MCTS. Additionally, a probabilistic structural rollout strategy is introduced to leverage structural patterns from previously discovered high-quality priority functions, guiding the rollout process. Our experiments on real-world datasets demonstrate SymLight's superior performance across a range of baselines. A key advantage is SymLight's ability to produce interpretable and deployable TSC policies while maintaining excellent performance.

cs.LG↗

arXiv2025

DyRo-MCTS: A Robust Monte Carlo Tree Search Approach to Dynamic Job Shop Scheduling

Dynamic job shop scheduling, a fundamental combinatorial optimisation problem in various industrial sectors, poses substantial challenges for effective scheduling due to frequent disruptions caused by the arrival of new jobs. State-of-the-art methods employ machine learning to learn scheduling policies offline, enabling rapid responses to dynamic events. However, these offline policies are often imperfect, necessitating the use of planning techniques such as Monte Carlo Tree Search (MCTS) to improve performance at online decision time. The unpredictability of new job arrivals complicates online planning, as decisions based on incomplete problem information are vulnerable to disturbances. To address this issue, we propose the Dynamic Robust MCTS (DyRo-MCTS) approach, which integrates action robustness estimation into MCTS. DyRo-MCTS guides the production environment toward states that not only yield good scheduling outcomes but are also easily adaptable to future job arrivals. Extensive experiments show that DyRo-MCTS significantly improves the performance of offline-learned policies with negligible additional online planning time. Moreover, DyRo-MCTS consistently outperforms vanilla MCTS across various scheduling scenarios. Further analysis reveals that its ability to make robust scheduling decisions leads to long-term, sustainable performance gains under disturbances.

cs.AI↗

arXiv2025

Genetic Programming with Model Driven Dimension Repair for Learning Interpretable Appointment Scheduling Rules

Appointment scheduling is a great challenge in healthcare operations management. Appointment rules (AR) provide medical practitioners with a simple yet effective tool to determine patient appointment times. Genetic programming (GP) can be used to evolve ARs. However, directly applying GP to design ARs may lead to rules that are difficult for end-users to interpret and trust. A key reason is that GP is unaware of the dimensional consistency, which ensures that the evolved rules align with users' domain knowledge and intuitive understanding. In this paper, we develop a new dimensionally aware GP algorithm with dimension repair to evolve ARs with dimensional consistency and high performance. A key innovation of our method is the dimension repair procedure, which optimizes the dimensional consistency of an expression tree while minimizing structural changes and ensuring that its output dimension meets the problem's requirements. We formulate the task as a mixed-integer linear programming model that can be efficiently solved using common mathematical programming methods. With the support of the dimension repair procedure, our method can explore a wider range of AR structures by temporarily breaking the dimensional consistency of individuals, and then restoring it without altering their overall structure, thereby identifying individuals with greater potential advantages. We evaluated the proposed method in a comprehensive set of simulated clinics. The experimental results demonstrate that our approach managed to evolve high-quality ARs that significantly outperform not only the manually designed ARs but also existing state-of-the-art dimensionally aware GP methods in terms of both objective values and dimensional consistency. In addition, we analyzed the semantics of the evolved ARs, providing insight into the design of more effective and interpretable ARs.

cs.LG↗

arXiv2025

GPLight+: A Genetic Programming Method for Learning Symmetric Traffic Signal Control Policy

Recently, learning-based approaches, have achieved significant success in automatically devising effective traffic signal control strategies. In particular, as a powerful evolutionary machine learning approach, Genetic Programming (GP) is utilized to evolve human-understandable phase urgency functions to measure the urgency of activating a green light for a specific phase. However, current GP-based methods are unable to treat the common traffic features of different traffic signal phases consistently. To address this issue, we propose to use a symmetric phase urgency function to calculate the phase urgency for a specific phase based on the current road conditions. This is represented as an aggregation of two shared subtrees, each representing the urgency of a turn movement in the phase. We then propose a GP method to evolve the symmetric phase urgency function. We evaluate our proposed method on the well-known cityflow traffic simulator, based on multiple public real-world datasets. The experimental results show that the proposed symmetric urgency function representation can significantly improve the performance of the learned traffic signal control policies over the traditional GP representation on a wide range of scenarios. Further analysis shows that the proposed method can evolve effective, human-understandable and easily deployable traffic signal control policies.

cs.LG↗

arXiv2025

Learning Traffic Signal Control via Genetic Programming

The control of traffic signals is crucial for improving transportation efficiency. Recently, learning-based methods, especially Deep Reinforcement Learning (DRL), garnered substantial success in the quest for more efficient traffic signal control strategies. However, the design of rewards in DRL highly demands domain knowledge to converge to an effective policy, and the final policy also presents difficulties in terms of explainability. In this work, a new learning-based method for signal control in complex intersections is proposed. In our approach, we design a concept of phase urgency for each signal phase. During signal transitions, the traffic light control strategy selects the next phase to be activated based on the phase urgency. We then proposed to represent the urgency function as an explainable tree structure. The urgency function can calculate the phase urgency for a specific phase based on the current road conditions. Genetic programming is adopted to perform gradient-free optimization of the urgency function. We test our algorithm on multiple public traffic signal control datasets. The experimental results indicate that the tree-shaped urgency function evolved by genetic programming outperforms the baselines, including a state-of-the-art method in the transportation field and a well-known DRL-based method. Our code is available online.

cs.AI↗

arXiv2025

Bridging Fitness With Search Spaces By Fitness Supremums: A Theoretical Study on LGP

Genetic programming has undergone rapid development in recent years. However, theoretical studies of genetic programming are far behind. One of the major obstacles to theoretical studies is the challenge of developing a model to describe the relationship between fitness values and program genotypes. In this paper, we take linear genetic programming (LGP) as an example to study the fitness-to-genotype relationship. We find that the fitness expectation increases with fitness supremum over instruction editing distance, considering 1) the fitness supremum linearly increases with the instruction editing distance in LGP, 2) the fitness infimum is fixed, and 3) the fitness probabilities over different instruction editing distances are similar. We then extend these findings to explain the bloat effect and the minimum hitting time of LGP based on instruction editing distance. The bloat effect happens because it is more likely to produce better offspring by adding instructions than by removing them, given an instruction editing distance from the optimal program. The analysis of the minimum hitting time suggests that for a basic LGP genetic operator (i.e., freemut), maintaining a necessarily small program size and mutating multiple instructions each time can improve LGP performance. The reported empirical results verify our hypothesis.

cs.NE↗

arXiv2025

LiBOG: Lifelong Learning for Black-Box Optimizer Generation

Meta-Black-Box Optimization (MetaBBO) garners attention due to its success in automating the configuration and generation of black-box optimizers, significantly reducing the human effort required for optimizer design and discovering optimizers with higher performance than classic human-designed optimizers. However, existing MetaBBO methods conduct one-off training under the assumption that a stationary problem distribution with extensive and representative training problem samples is pre-available. This assumption is often impractical in real-world scenarios, where diverse problems following shifting distribution continually arise. Consequently, there is a pressing need for methods that can continuously learn from new problems encountered on-the-fly and progressively enhance their capabilities. In this work, we explore a novel paradigm of lifelong learning in MetaBBO and introduce LiBOG, a novel approach designed to learn from sequentially encountered problems and generate high-performance optimizers for Black-Box Optimization (BBO). LiBOG consolidates knowledge both across tasks and within tasks to mitigate catastrophic forgetting. Extensive experiments demonstrate LiBOG's effectiveness in learning to generate high-performance optimizers in a lifelong learning manner, addressing catastrophic forgetting while maintaining plasticity to learn new tasks.

cs.LG↗

arXiv2025

Curriculum Learning in Genetic Programming Guided Local Search for Large-scale Vehicle Routing Problems

Manually designing (meta-)heuristics for the Vehicle Routing Problem (VRP) is a challenging task that requires significant domain expertise. Recently, data-driven approaches have emerged as a promising solution, automatically learning heuristics that perform well on training instances and generalize to unseen test cases. Such an approach learns (meta-)heuristics that can perform well on the training instances, expecting it to generalize well on the unseen test instances. A recent method, named GPGLS, uses Genetic Programming (GP) to learn the utility function in Guided Local Search (GLS) and solved large scale VRP effectively. However, the selection of appropriate training instances during the learning process remains an open question, with most existing studies including GPGLS relying on random instance selection. To address this, we propose a novel method, CL-GPGLS, which integrates Curriculum Learning (CL) into GPGLS. Our approach leverages a predefined curriculum to introduce training instances progressively, starting with simpler tasks and gradually increasing complexity, enabling the model to better adapt and optimize for large-scale VRP (LSVRP). Extensive experiments verify the effectiveness of CL-GPGLS, demonstrating significant performance improvements over three baseline methods.

cs.NE↗

arXiv2025

Generalized Phase Pressure Control Enhanced Reinforcement Learning for Traffic Signal Control

Appropriate traffic state representation is crucial for learning traffic signal control policies. However, most of the current traffic state representations are heuristically designed, with insufficient theoretical support. In this paper, we (1) develop a flexible, efficient, and theoretically grounded method, namely generalized phase pressure (G2P) control, which takes only simple lane features into consideration to decide which phase to be actuated; 2) extend the pressure control theory to a general form for multi-homogeneous-lane road networks based on queueing theory; (3) design a new traffic state representation based on the generalized phase state features from G2P control; and 4) develop a reinforcement learning (RL)-based algorithm template named G2P-XLight, and two RL algorithms, G2P-MPLight and G2P-CoLight, by combining the generalized phase state representation with MPLight and CoLight, two well-performed RL methods for learning traffic signal control policies. Extensive experiments conducted on multiple real-world datasets demonstrate that G2P control outperforms the state-of-the-art (SOTA) heuristic method in the transportation field and other recent human-designed heuristic methods; and that the newly proposed G2P-XLight significantly outperforms SOTA learning-based approaches. Our code is available online.

cs.LG↗

arXiv2024

Emergent Crowd Grouping via Heuristic Self-Organization

Modeling crowds has many important applications in games and computer animation. Inspired by the emergent following effect in real-life crowd scenarios, in this work, we develop a method for implicitly grouping moving agents. We achieve this by analyzing local information around each agent and rotating its preferred velocity accordingly. Each agent could automatically form an implicit group with its neighboring agents that have similar directions. In contrast to an explicit group, there are no strict boundaries for an implicit group. If an agent's direction deviates from its group as a result of positional changes, it will autonomously exit the group or join another implicitly formed neighboring group. This implicit grouping is autonomously emergent among agents rather than deliberately controlled by the algorithm. The proposed method is compared with many crowd simulation models, and the experimental results indicate that our approach achieves the lowest congestion levels in some classic scenarios. In addition, we demonstrate that adjusting the preferred velocity of agents can actually reduce the dissimilarity between their actual velocity and the original preferred velocity. Our work is available online.

cs.MA↗

arXiv2024

Multi-Representation Genetic Programming: A Case Study on Tree-based and Linear Representations

Existing genetic programming (GP) methods are typically designed based on a certain representation, such as tree-based or linear representations. These representations show various pros and cons in different domains. However, due to the complicated relationships among representation and fitness landscapes of GP, it is hard to intuitively determine which GP representation is the most suitable for solving a certain problem. Evolving programs (or models) with multiple representations simultaneously can alternatively search on different fitness landscapes since representations are highly related to the search space that essentially defines the fitness landscape. Fully using the latent synergies among different GP individual representations might be helpful for GP to search for better solutions. However, existing GP literature rarely investigates the simultaneous effective use of evolving multiple representations. To fill this gap, this paper proposes a multi-representation GP algorithm based on tree-based and linear representations, which are two commonly used GP representations. In addition, we develop a new cross-representation crossover operator to harness the interplay between tree-based and linear representations. Empirical results show that navigating the learned knowledge between basic tree-based and linear representations successfully improves the effectiveness of GP with solely tree-based or linear representation in solving symbolic regression and dynamic job shop scheduling problems.

cs.NE↗

arXiv2024

Learning from Offline and Online Experiences: A Hybrid Adaptive Operator Selection Framework

In many practical applications, usually, similar optimisation problems or scenarios repeatedly appear. Learning from previous problem-solving experiences can help adjust algorithm components of meta-heuristics, e.g., adaptively selecting promising search operators, to achieve better optimisation performance. However, those experiences obtained from previously solved problems, namely offline experiences, may sometimes provide misleading perceptions when solving a new problem, if the characteristics of previous problems and the new one are relatively different. Learning from online experiences obtained during the ongoing problem-solving process is more instructive but highly restricted by limited computational resources. This paper focuses on the effective combination of offline and online experiences. A novel hybrid framework that learns to dynamically and adaptively select promising search operators is proposed. Two adaptive operator selection modules with complementary paradigms cooperate in the framework to learn from offline and online experiences and make decisions. An adaptive decision policy is maintained to balance the use of those two modules in an online manner. Extensive experiments on 170 widely studied real-value benchmark optimisation problems and a benchmark set with 34 instances for combinatorial optimisation show that the proposed hybrid framework outperforms the state-of-the-art methods. Ablation study verifies the effectiveness of each component of the framework.

cs.NE↗

arXiv2024

Improving Critical Node Detection Using Neural Network-based Initialization in a Genetic Algorithm

The Critical Node Problem (CNP) is concerned with identifying the critical nodes in a complex network. These nodes play a significant role in maintaining the connectivity of the network, and removing them can negatively impact network performance. CNP has been studied extensively due to its numerous real-world applications. Among the different versions of CNP, CNP-1a has gained the most popularity. The primary objective of CNP-1a is to minimize the pair-wise connectivity in the remaining network after deleting a limited number of nodes from a network. Due to the NP-hard nature of CNP-1a, many heuristic/metaheuristic algorithms have been proposed to solve this problem. However, most existing algorithms start with a random initialization, leading to a high cost of obtaining an optimal solution. To improve the efficiency of solving CNP-1a, a knowledge-guided genetic algorithm named K2GA has been proposed. Unlike the standard genetic algorithm framework, K2GA has two main components: a pretrained neural network to obtain prior knowledge on possible critical nodes, and a hybrid genetic algorithm with local search for finding an optimal set of critical nodes based on the knowledge given by the trained neural network. The local search process utilizes a cut node-based greedy strategy. The effectiveness of the proposed knowledgeguided genetic algorithm is verified by experiments on 26 realworld instances of complex networks. Experimental results show that K2GA outperforms the state-of-the-art algorithms regarding the best, median, and average objective values, and improves the best upper bounds on the best objective values for eight realworld instances.

cs.NE↗

arXiv2024

Distance-aware Attention Reshaping: Enhance Generalization of Neural Solver for Large-scale Vehicle Routing Problems

Neural solvers based on attention mechanism have demonstrated remarkable effectiveness in solving vehicle routing problems. However, in the generalization process from small scale to large scale, we find a phenomenon of the dispersion of attention scores in existing neural solvers, which leads to poor performance. To address this issue, this paper proposes a distance-aware attention reshaping method, assisting neural solvers in solving large-scale vehicle routing problems. Specifically, without the need for additional training, we utilize the Euclidean distance information between current nodes to adjust attention scores. This enables a neural solver trained on small-scale instances to make rational choices when solving a large-scale problem. Experimental results show that the proposed method significantly outperforms existing state-of-the-art neural solvers on the large-scale CVRPLib dataset.

cs.AI↗

arXiv2023

XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks

Convolutional Neural Networks (CNNs) continue to achieve great success in classification tasks as innovative techniques and complex multi-path architecture topologies are introduced. Neural Architecture Search (NAS) aims to automate the design of these complex architectures, reducing the need for costly manual design work by human experts. Cellular Encoding (CE) is an evolutionary computation technique which excels in constructing novel multi-path topologies of varying complexity and has recently been applied with NAS to evolve CNN architectures for various classification tasks. However, existing CE approaches have severe limitations. They are restricted to only one domain, only partially implement the theme of CE, or only focus on the micro-architecture search space. This paper introduces a new CE representation and algorithm capable of evolving novel multi-path CNN architectures of varying depth, width, and complexity for image and text classification tasks. The algorithm explicitly focuses on the macro-architecture search space. Furthermore, by using a surrogate model approach, we show that the algorithm can evolve a performant CNN architecture in less than one GPU day, thereby allowing a sufficient number of experiment runs to be conducted to achieve scientific robustness. Experiment results show that the approach is highly competitive, defeating several state-of-the-art methods, and is generalisable to both the image and text domains.

cs.NE↗

arXiv2023

Local Optima Correlation Assisted Adaptive Operator Selection

For solving combinatorial optimisation problems with metaheuristics, different search operators are applied for sampling new solutions in the neighbourhood of a given solution. It is important to understand the relationship between operators for various purposes, e.g., adaptively deciding when to use which operator to find optimal solutions efficiently. However, it is difficult to theoretically analyse this relationship, especially in the complex solution space of combinatorial optimisation problems. In this paper, we propose to empirically analyse the relationship between operators in terms of the correlation between their local optima and develop a measure for quantifying their relationship. The comprehensive analyses on a wide range of capacitated vehicle routing problem benchmark instances show that there is a consistent pattern in the correlation between commonly used operators. Based on this newly proposed local optima correlation metric, we propose a novel approach for adaptively selecting among the operators during the search process. The core intention is to improve search efficiency by preventing wasting computational resources on exploring neighbourhoods where the local optima have already been reached. Experiments on randomly generated instances and commonly used benchmark datasets are conducted. Results show that the proposed approach outperforms commonly used adaptive operator selection methods.

cs.AI↗