arXiv subjects

Shengxiang Yang

Publications and source records attributed to Shengxiang Yang.

At least 19 recordsLinked to original sources

arXiv2026

Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts

Real-time strategy (RTS) games present significant AI challenges, characterized by expansive state-action spaces arising from multi-unit coordination in continuous battlefields, and sparse delayed rewards stemming from final win/lose signals. Existing approaches face a trade-off between managing the dimensionality explosion of joint actions and maintaining the interpretability of complex state representations. This complexity is further intensified by the limitation of traditional hierarchical structures in adaptively decomposing tasks into effective tactical modules. Such difficulties are compounded by the black-box nature of deep learning models and their reliance on sparse rewards, which together result in limited sample efficiency and a lack of decision-making transparency. To address these limitations, this paper proposes HRL-IM/CBS, a hierarchical reinforcement learning framework with influence map hashing and cluster-based scripts for StarCraft micromanagement. Influence map hashing encodes global battlefield situations into compact hexadecimal codes, capturing spatial control and relative advantage. Cluster-based scripts enable dynamic local coordination through adaptive unit partitioning. The hierarchical multi-Q-table architecture decomposes decision-making into upper-level clustering strategy selection and lower-level tactical execution, with reward allocation providing dense learning signals. Experiments across six asymmetric scenarios demonstrate competitive performance against deep RL baselines while offering advantages in sample efficiency and interpretability through transparent Q-table representations.

cs.AI↗

arXiv2026

Drift-Aware Online Dynamic Learning for Nonstationary Multivariate Time Series: Application to Sintering Quality Prediction

Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In practice, pronounced concept drift compounded by significant label verification latency rapidly degrades the performance of offline-trained models. Existing methods based on static architectures or passive update strategies struggle to simultaneously extract multi-scale spatiotemporal features and overcome the stability-plasticity dilemma without immediate supervision. To address these limitations, a Drift-Aware Multi-Scale Dynamic Learning (DA-MSDL) framework is proposed to maintain robust multi-output predictive performance via online adaptive mechanisms on nonstationary data streams. The framework employs a multi-scale bi-branch convolutional network as its backbone to disentangle local fluctuations from long-term trends, thereby enhancing representational capacity for complex dynamic patterns. To circumvent the label latency bottleneck, DA-MSDL leverages Maximum Mean Discrepancy (MMD) for unsupervised drift detection. By quantifying online statistical deviations in feature distributions, DA-MSDL proactively triggers model adaptation prior to inference. Furthermore, a drift-severity-guided hierarchical fine-tuning strategy is developed. Supported by prioritized experience replay from a dynamic memory queue, this approach achieves rapid distribution alignment while effectively mitigating catastrophic forgetting. Long-horizon experiments on real-world industrial sintering data and a public benchmark dataset demonstrate that DA-MSDL consistently outperforms representative baselines under severe concept drift. Exhibiting strong cross-domain generalization and predictive stability, the proposed framework provides an effective online dynamic learning paradigm for quality monitoring in nonstationary environments.

cs.LG↗

arXiv2026

Auto-Configured Networks for Multi-Scale Multi-Output Time-Series Forecasting

Industrial forecasting often involves multi-source asynchronous signals and multi-output targets, while deployment requires explicit trade-offs between prediction error and model complexity. Current practices typically fix alignment strategies or network designs, making it difficult to systematically co-design preprocessing, architecture, and hyperparameters in budget-limited training-based evaluations. To address this issue, we propose an auto-configuration framework that outputs a deployable Pareto set of forecasting models balancing error and complexity. At the model level, a Multi-Scale Bi-Branch Convolutional Neural Network (MS--BCNN) is developed, where short- and long-kernel branches capture local fluctuations and long-term trends, respectively, for multi-output regression. At the search level, we unify alignment operators, architectural choices, and training hyperparameters into a hierarchical-conditional mixed configuration space, and apply Player-based Hybrid Multi-Objective Evolutionary Algorithm (PHMOEA) to approximate the error--complexity Pareto frontier within a limited computational budget. Experiments on hierarchical synthetic benchmarks and a real-world sintering dataset demonstrate that our framework outperforms competitive baselines under the same budget and offers flexible deployment choices.

cs.LG↗

arXiv2026

Variable Search Stepsize for Randomized Local Search in Multi-Objective Combinatorial Optimization

Over the past two decades, research in evolutionary multi-objective optimization has predominantly focused on continuous domains, with comparatively limited attention given to multi-objective combinatorial optimization problems (MOCOPs). Combinatorial problems differ significantly from continuous ones in terms of problem structure and landscape. Recent studies have shown that on MOCOPs multi-objective evolutionary algorithms (MOEAs) can even be outperformed by simple randomised local search. Starting with a randomly sampled solution in search space, randomised local search iteratively draws a random solution (from an archive) to perform local variation within its neighbourhood. However, in most existing methods, the local variation relies on a fixed neighbourhood, which limits exploration and makes the search easy to get trapped in local optima. In this paper, we present a simple yet effective local search method, called variable stepsize randomized local search (VS-RLS), which adjusts the stepsize during the search. VS-RLS transitions gradually from a broad, exploratory search in the early phases to a more focused, fine-grained search as the search progresses. We demonstrate the effectiveness and generalizability of VS-RLS through extensive evaluations against local search and MOEAs methods on diverse MOCOPs.

cs.NE↗

arXiv2025

Nearest-Better Network for Visualizing and Analyzing Combinatorial Optimization Problems: A Unified Tool

The Nearest-Better Network (NBN) is a powerful method to visualize sampled data for continuous optimization problems while preserving multiple landscape features. However, the calculation of NBN is very time-consuming, and the extension of the method to combinatorial optimization problems is challenging but very important for analyzing the algorithm's behavior. This paper provides a straightforward theoretical derivation showing that the NBN network essentially functions as the maximum probability transition network for algorithms. This paper also presents an efficient NBN computation method with logarithmic linear time complexity to address the time-consuming issue. By applying this efficient NBN algorithm to the OneMax problem and the Traveling Salesman Problem (TSP), we have made several remarkable discoveries for the first time: The fitness landscape of OneMax exhibits neutrality, ruggedness, and modality features. The primary challenges of TSP problems are ruggedness, modality, and deception. Two state-of-the-art TSP algorithms (i.e., EAX and LKH) have limitations when addressing challenges related to modality and deception, respectively. LKH, based on local search operators, fails when there are deceptive solutions near global optima. EAX, which is based on a single population, can efficiently maintain diversity. However, when multiple attraction basins exist, EAX retains individuals within multiple basins simultaneously, reducing inter-basin interaction efficiency and leading to algorithm's stagnation.

cs.AI↗

arXiv2024

An Evolutionary Network Architecture Search Framework with Adaptive Multimodal Fusion for Hand Gesture Recognition

Hand gesture recognition (HGR) based on multimodal data has attracted considerable attention owing to its great potential in applications. Various manually designed multimodal deep networks have performed well in multimodal HGR (MHGR), but most of existing algorithms require a lot of expert experience and time-consuming manual trials. To address these issues, we propose an evolutionary network architecture search framework with the adaptive multimodel fusion (AMF-ENAS). Specifically, we design an encoding space that simultaneously considers fusion positions and ratios of the multimodal data, allowing for the automatic construction of multimodal networks with different architectures through decoding. Additionally, we consider three input streams corresponding to intra-modal surface electromyography (sEMG), intra-modal accelerometer (ACC), and inter-modal sEMG-ACC. To automatically adapt to various datasets, the ENAS framework is designed to automatically search a MHGR network with appropriate fusion positions and ratios. To the best of our knowledge, this is the first time that ENAS has been utilized in MHGR to tackle issues related to the fusion position and ratio of multimodal data. Experimental results demonstrate that AMF-ENAS achieves state-of-the-art performance on the Ninapro DB2, DB3, and DB7 datasets.

cs.CV↗

arXiv2024

Benchmark for CEC 2024 Competition on Multiparty Multiobjective Optimization

The competition focuses on Multiparty Multiobjective Optimization Problems (MPMOPs), where multiple decision makers have conflicting objectives, as seen in applications like UAV path planning. Despite their importance, MPMOPs remain understudied in comparison to conventional multiobjective optimization. The competition aims to address this gap by encouraging researchers to explore tailored modeling approaches. The test suite comprises two parts: problems with common Pareto optimal solutions and Biparty Multiobjective UAV Path Planning (BPMO-UAVPP) problems with unknown solutions. Optimization algorithms for the first part are evaluated using Multiparty Inverted Generational Distance (MPIGD), and the second part is evaluated using Multiparty Hypervolume (MPHV) metrics. The average algorithm ranking across all problems serves as a performance benchmark.

cs.AI↗

arXiv2023

An Evolving Population Approach to Data-Stream Classification with Extreme Verification Latency

Recognising and reacting to change in non-stationary data-streams is a challenging task. The majority of research in this area assumes that the true class label of incoming points are available, either at each time step or intermittently with some latency. In the worse case this latency approaches infinity and we can assume that no labels are available beyond the initial training set. When change is expected and no further training labels are provided the challenge of maintaining a high classification accuracy is very great. The challenge is to propagate the original training information through several timesteps, possibly indefinitely, while adapting to underlying change in the data-stream. In this paper we conduct an initial study into the effectiveness of using an evolving, population-based approach as the mechanism for adapting to change. An ensemble of one-class-classifiers is maintained for each class. Each classifier is considered as an agent in the sub-population and is subject to selection pressure to find interesting areas of the feature space. This selection pressure forces the ensemble to adapt to the underlying change in the data-stream.

cs.NE↗

arXiv2023

Vector Autoregressive Evolution for Dynamic Multi-Objective Optimisation

Dynamic multi-objective optimisation (DMO) handles optimisation problems with multiple (often conflicting) objectives in varying environments. Such problems pose various challenges to evolutionary algorithms, which have popularly been used to solve complex optimisation problems, due to their dynamic nature and resource restrictions in changing environments. This paper proposes vector autoregressive evolution (VARE) consisting of vector autoregression (VAR) and environment-aware hypermutation to address environmental changes in DMO. VARE builds a VAR model that considers mutual relationship between decision variables to effectively predict the moving solutions in dynamic environments. Additionally, VARE introduces EAH to address the blindness of existing hypermutation strategies in increasing population diversity in dynamic scenarios where predictive approaches are unsuitable. A seamless integration of VAR and EAH in an environment-adaptive manner makes VARE effective to handle a wide range of dynamic environments and competitive with several popular DMO algorithms, as demonstrated in extensive experimental studies. Specially, the proposed algorithm is computationally 50 times faster than two widely-used algorithms (i.e., TrDMOEA and MOEA/D-SVR) while producing significantly better results.

cs.NE↗

arXiv2023

EDOLAB: An Open-Source Platform for Education and Experimentation with Evolutionary Dynamic Optimization Algorithms

Many real-world optimization problems exhibit dynamic characteristics, posing significant challenges for traditional optimization techniques. Evolutionary Dynamic Optimization Algorithms (EDOAs) are designed to address these challenges effectively. However, in existing literature, the reported results for a given EDOA can vary significantly. This inconsistency often arises because the source codes for many EDOAs, which are typically complex, have not been made publicly available, leading to error-prone re-implementations. To support researchers in conducting experiments and comparing their algorithms with various EDOAs, we have developed an open-source MATLAB platform called the Evolutionary Dynamic Optimization LABoratory (EDOLAB). This platform not only facilitates research but also includes an educational module designed for instructional purposes. The education module allows users to observe: a) a 2-dimensional problem space and its morphological changes following each environmental change, b) the behaviors of individuals over time, and c) how the EDOA responds to environmental changes and tracks the moving optimum. The current version of EDOLAB features 25 EDOAs and four fully parametric benchmark generators. The MATLAB source code for EDOLAB is publicly available and can be accessed from [https://github.com/Danial-Yazdani/EDOLAB-MATLAB].

cs.NE↗

arXiv2022

Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely on the abundance of labelled observations to train a prospective model. These models are composed of millions of parameters to estimate, increasing the need of more training observations. Frequently it is expensive to gather labelled observations of data, making the usage of deep learning models not ideal, as the model might over-fit data. In a semi-supervised setting, unlabelled data is used to improve the levels of accuracy and generalization of a model with small labelled datasets. Nevertheless, in many situations different unlabelled data sources might be available. This raises the risk of a significant distribution mismatch between the labelled and unlabelled datasets. Such phenomena can cause a considerable performance hit to typical semi-supervised deep learning frameworks, which often assume that both labelled and unlabelled datasets are drawn from similar distributions. Therefore, in this paper we study the latest approaches for semi-supervised deep learning for image recognition. Emphasis is made in semi-supervised deep learning models designed to deal with a distribution mismatch between the labelled and unlabelled datasets. We address open challenges with the aim to encourage the community to tackle them, and overcome the high data demand of traditional deep learning pipelines under real-world usage settings.

cs.CV↗

arXiv2022

Benchmark Functions for CEC 2022 Competition on Seeking Multiple Optima in Dynamic Environments

Dynamic and multimodal features are two important properties and widely existed in many real-world optimization problems. The former illustrates that the objectives and/or constraints of the problems change over time, while the latter means there is more than one optimal solution (sometimes including the accepted local solutions) in each environment. The dynamic multimodal optimization problems (DMMOPs) have both of these characteristics, which have been studied in the field of evolutionary computation and swarm intelligence for years, and attract more and more attention. Solving such problems requires optimization algorithms to simultaneously track multiple optima in the changing environments. So that the decision makers can pick out one optimal solution in each environment according to their experiences and preferences, or quickly turn to other solutions when the current one cannot work well. This is very helpful for the decision makers, especially when facing changing environments. In this competition, a test suit about DMMOPs is given, which models the real-world applications. Specifically, this test suit adopts 8 multimodal functions and 8 change modes to construct 24 typical dynamic multimodal optimization problems. Meanwhile, the metric is also given to measure the algorithm performance, which considers the average number of optimal solutions found in all environments. This competition will be very helpful to promote the development of dynamic multimodal optimization algorithms.

cs.NE↗

arXiv2021

Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities

In the context of the global coronavirus pandemic, different deep learning solutions for infected subject detection using chest X-ray images have been proposed. However, deep learning models usually need large labelled datasets to be effective. Semi-supervised deep learning is an attractive alternative, where unlabelled data is leveraged to improve the overall model's accuracy. However, in real-world usage settings, an unlabelled dataset might present a different distribution than the labelled dataset (i.e. the labelled dataset was sampled from a target clinic and the unlabelled dataset from a source clinic). This results in a distribution mismatch between the unlabelled and labelled datasets. In this work, we assess the impact of the distribution mismatch between the labelled and the unlabelled datasets, for a semi-supervised model trained with chest X-ray images, for COVID-19 detection. Under strong distribution mismatch conditions, we found an accuracy hit of almost 30\%, suggesting that the unlabelled dataset distribution has a strong influence in the behaviour of the model. Therefore, we propose a straightforward approach to diminish the impact of such distribution mismatch. Our proposed method uses a density approximation of the feature space. It is built upon the target dataset to filter out the observations in the source unlabelled dataset that might harm the accuracy of the semi-supervised model. It assumes that a small labelled source dataset is available together with a larger source unlabelled dataset. Our proposed method does not require any model training, it is simple and computationally cheap. We compare our proposed method against two popular state of the art out-of-distribution data detectors, which are also cheap and simple to implement. In our tests, our method yielded accuracy gains of up to 32\%, when compared to the previous state of the art methods.

cs.CV↗

arXiv2021

A Real Use Case of Semi-Supervised Learning for Mammogram Classification in a Local Clinic of Costa Rica

The implementation of deep learning based computer aided diagnosis systems for the classification of mammogram images can help in improving the accuracy, reliability, and cost of diagnosing patients. However, training a deep learning model requires a considerable amount of labeled images, which can be expensive to obtain as time and effort from clinical practitioners is required. A number of publicly available datasets have been built with data from different hospitals and clinics. However, using models trained on these datasets for later work on images sampled from a different hospital or clinic might result in lower performance. This is due to the distribution mismatch of the datasets, which include different patient populations and image acquisition protocols. The scarcity of labeled data can also bring a challenge towards the application of transfer learning with models trained using these source datasets. In this work, a real world scenario is evaluated where a novel target dataset sampled from a private Costa Rican clinic is used, with few labels and heavily imbalanced data. The use of two popular and publicly available datasets (INbreast and CBIS-DDSM) as source data, to train and test the models on the novel target dataset, is evaluated. The use of the semi-supervised deep learning approach known as MixMatch, to leverage the usage of unlabeled data from the target dataset, is proposed and evaluated. In the tests, the performance of models is extensively measured, using different metrics to assess the performance of a classifier under heavy data imbalance conditions. It is shown that the use of semi-supervised deep learning combined with fine-tuning can provide a meaningful advantage when using scarce labeled observations. We make available the novel dataset for the benefit of the community.

eess.IV↗

arXiv2021

Generating Large-scale Dynamic Optimization Problem Instances Using the Generalized Moving Peaks Benchmark

This document describes the generalized moving peaks benchmark (GMPB) and how it can be used to generate problem instances for continuous large-scale dynamic optimization problems. It presents a set of 15 benchmark problems, the relevant source code, and a performance indicator, designed for comparative studies and competitions in large-scale dynamic optimization. Although its primary purpose is to provide a coherent basis for running competitions, its generality allows the interested reader to use this document as a guide to design customized problem instances to investigate issues beyond the scope of the presented benchmark suite. To this end, we explain the modular structure of the GMPB and how its constituents can be assembled to form problem instances with a variety of controllable characteristics ranging from unimodal to highly multimodal, symmetric to highly asymmetric, smooth to highly irregular, and various degrees of variable interaction and ill-conditioning.

math.OC↗

arXiv2021

Competition on Dynamic Optimization Problems Generated by Generalized Moving Peaks Benchmark (GMPB)

The Generalized Moving Peaks Benchmark (GMPB) is a tool for generating continuous dynamic optimization problem instances with controllable dynamic and morphological characteristics. GMPB has been used in recent Competitions on Dynamic Optimization at prestigious conferences, such as the IEEE Congress on Evolutionary Computation (CEC). This dynamic benchmark generator can create a wide variety of landscapes, ranging from simple unimodal to highly complex multimodal configurations and from symmetric to asymmetric forms. It also supports diverse surface textures, from smooth to highly irregular, and can generate varying levels of variable interaction and conditioning. This document provides an overview of GMPB, emphasizing how its parameters can be adjusted to produce landscapes with customizable characteristics. The MATLAB implementation of GMPB is available on the EDOLAB Platform.

cs.NE↗

arXiv2021

A Multiobjective State Transition Algorithm Based on Decomposition

Aggregation functions largely determine the convergence and diversity performance of multi-objective evolutionary algorithms in decomposition methods. Nevertheless, the traditional Tchebycheff function does not consider the matching relationship between the weight vectors and candidate solutions. In this paper, the concept of matching degree is proposed which employs vectorial angles between weight vectors and candidate solutions. Based on the matching degree, a new modified Tchebycheff aggregation function is proposed, which integrates matching degree into the Tchebycheff aggregation function. Moreover, the proposed decomposition method has the same functionality with the Tchebycheff aggregation function. Based on the proposed decomposition approach, a new multiobjective optimization algorithm named decomposition-based multi-objective state transition algorithm is proposed. Relevant experimental results show that the proposed algorithm is highly competitive in comparison with other state-of-the-art multiobjetive optimization algorithms.

math.OC↗

arXiv2020

MixMOOD: A systematic approach to class distribution mismatch in semi-supervised learning using deep dataset dissimilarity measures

In this work, we propose MixMOOD - a systematic approach to mitigate effect of class distribution mismatch in semi-supervised deep learning (SSDL) with MixMatch. This work is divided into two components: (i) an extensive out of distribution (OOD) ablation test bed for SSDL and (ii) a quantitative unlabelled dataset selection heuristic referred to as MixMOOD. In the first part, we analyze the sensitivity of MixMatch accuracy under 90 different distribution mismatch scenarios across three multi-class classification tasks. These are designed to systematically understand how OOD unlabelled data affects MixMatch performance. In the second part, we propose an efficient and effective method, called deep dataset dissimilarity measures (DeDiMs), to compare labelled and unlabelled datasets. The proposed DeDiMs are quick to evaluate and model agnostic. They use the feature space of a generic Wide-ResNet and can be applied prior to learning. Our test results reveal that supposed semantic similarity between labelled and unlabelled data is not a good heuristic for unlabelled data selection. In contrast, strong correlation between MixMatch accuracy and the proposed DeDiMs allow us to quantitatively rank different unlabelled datasets ante hoc according to expected MixMatch accuracy. This is what we call MixMOOD. Furthermore, we argue that the MixMOOD approach can aid to standardize the evaluation of different semi-supervised learning techniques under real world scenarios involving out of distribution data.

cs.LG↗