no code implementations • 28 Sep 2023 • Jiashi Gao, Changwu Huang, Ming Tang, Shin Hwei Tan, Xin Yao, Xuetao Wei
Recent advances in federated learning (FL) enable collaborative training of machine learning (ML) models from large-scale and widely dispersed clients while protecting their privacy.
1 code implementation • 24 Aug 2023 • Mai Peng, Zeneng She, Delaram Yazdani, Danial Yazdani, Wenjian Luo, Changhe Li, Juergen Branke, Trung Thanh Nguyen, Amir H. Gandomi, Yaochu Jin, Xin Yao
In this paper, to assist researchers in performing experiments and comparing their algorithms against several EDOAs, we develop an open-source MATLAB platform for EDOAs, called Evolutionary Dynamic Optimization LABoratory (EDOLAB).
no code implementations • 19 Jun 2023 • Gan Ruan, Leandro L. Minku, Stefan Menzel, Bernhard Sendhoff, Xin Yao
Different from most other dynamic multi-objective optimization problems (DMOPs), DMOPs with a changing number of objectives usually result in expansion or contraction of the Pareto front or Pareto set manifold.
1 code implementation • 23 May 2023 • Chengpeng Hu, ZiMing Wang, Jialin Liu, Junyi Wen, Bifei Mao, Xin Yao
Experimental results on the problem instances demonstrate the outstanding performance of our proposed approach compared with eight state-of-the-art constrained and non-constrained reinforcement learning algorithms, and widely used dispatching rules for material handling.
no code implementations • 11 May 2023 • Weijie Zheng, Xin Yao
We prove that except for some small and positive time-linkage effects (that is, for weights $0$ and $1$), randomized local search (RLS) and (1+1)EA cannot converge to the global optimum with a positive probability.
no code implementations • 3 May 2023 • Jiyuan Pei, Hao Tong, Jialin Liu, Yi Mei, Xin Yao
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.
1 code implementation • 19 Apr 2023 • Chengpeng Hu, Jiyuan Pei, Jialin Liu, Xin Yao
Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration efficiency.
3 code implementations • 17 Apr 2023 • Yiming Cui, Ziqing Yang, Xin Yao
While several large language models, such as LLaMA, have been open-sourced by the community, these predominantly focus on English corpora, limiting their usefulness for other languages.
1 code implementation • 9 Apr 2023 • Xunzhao Yu, Yan Wang, Ling Zhu, Dimitar Filev, Xin Yao
Our experimental results on expensive multi-objective and constrained optimization problems demonstrate that experiences gained from related tasks are beneficial for the saving of evaluation budgets on the target problem.
no code implementations • 8 Apr 2023 • Dashan Gao, Yunce Zhao, Yinghua Yao, Zeqi Zhang, Bifei Mao, Xin Yao
In this paper, we study the robustness of deep learning models against joint perturbations by proposing a novel attack mechanism named Semantic-Preserving Adversarial (SPA) attack, which can then be used to enhance adversarial training.
1 code implementation • 3 Apr 2023 • Xin Yao, Ziqing Yang, Yiming Cui, Shijin Wang
In natural language processing, pre-trained language models have become essential infrastructures.
no code implementations • 16 Mar 2023 • Miqing Li, Manuel López-Ibáñez, Xin Yao
Such an archive can be solely used to store high-quality solutions presented to the decision maker, but in many cases may participate in the search process (e. g., as the population in evolutionary computation).
no code implementations • ICCV 2023 • Yuhui Quan, Xin Yao, Hui Ji
Single image defocus deblurring (SIDD) is a challenging task due to the spatially-varying nature of defocus blur, characterized by per-pixel point spread functions (PSFs).
1 code implementation • 15 Dec 2022 • Ziqing Yang, Yiming Cui, Xin Yao, Shijin Wang
In this work, we propose a structured pruning method GRAIN (Gradient-based Intra-attention pruning), which performs task-specific pruning with knowledge distillation and yields highly effective models.
no code implementations • 5 Dec 2022 • Fengxiao Tang, Yilin Yang, Xin Yao, Ming Zhao, Nei Kato
To further expand the resource pool of traffic offloading in SAGIN, we extend the single-layer satellite network into a double-layer satellite network composed of low-orbit satellites (LEO) and high-orbit satellites (GEO).
no code implementations • 5 Nov 2022 • Ke Li, Renzhi Chen, Xin Yao
Many real-world problems are usually computationally costly and the objective functions evolve over time.
no code implementations • 10 Oct 2022 • Dashan Gao, Xin Yao, Qiang Yang
Therefore, heterogeneous FL is proposed to address the problem of heterogeneity in FL.
no code implementations • 22 Sep 2022 • Shengcai Liu, Yu Zhang, Ke Tang, Xin Yao
Hopefully, this work would help with a better understanding of the strengths and weaknesses of NCO and provide a comprehensive evaluation protocol for further benchmarking NCO approaches in comparison to other approaches.
no code implementations • 14 Apr 2022 • Danny Weyns, Thomas Baeck, Rene Vidal, Xin Yao, Ahmed Nabil Belbachir
We motivate the need for self-evolving computing systems in light of the state of the art, outline a conceptual architecture of self-evolving computing systems, and illustrate the architecture for a future smart city mobility system that needs to evolve continuously with changing conditions.
1 code implementation • 8 Apr 2022 • Daniel Herring, Michael Kirley, Xin Yao
Our framework is based on an extension of PlatEMO, allowing for the reproduction of results and performance measurements across a range of dynamic settings and problems.
no code implementations • 6 Apr 2022 • Ke Li, Guiyu Lai, Xin Yao
Bearing this in mind, this paper develops a framework for designing preference-based EMO algorithms to find SOI in an interactive manner.
no code implementations • 14 Jan 2022 • ZiMing Wang, Xin Yao
We also analyzed how normalizing affected the indicator-based algorithm and observed that the normalized $I_{\epsilon+}$ indicator is better at finding extreme solutions and can reduce the influence of each objective's different extent of contribution to the indicator due to its different scope.
no code implementations • 12 Jan 2022 • Gan Ruan, Leandro L. Minku, Zhao Xu, Xin Yao
However, the existing problem formulation to solve this resource allocation problem is unsuitable as it defines the capacity utility of resource in an inappropriate way and tends to cause much delay.
no code implementations • 26 Nov 2021 • Yinghua Yao, Yuangang Pan, Ivor W. Tsang, Xin Yao
In particular, we simultaneously train two modules: a generator that translates an input image to the desired image with smooth subtle changes with respect to the interested attributes; and a ranker that ranks rival preferences consisting of the input image and the desired image.
no code implementations • 19 Sep 2021 • Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao
To investigate the number and distribution of local optima, we conduct a fitness landscape analysis on the sum rate maximization problems.
no code implementations • 19 Aug 2021 • Danny Weyns, Thomas Bäck, Renè Vidal, Xin Yao, Ahmed Nabil Belbachir
When detecting anomalies, novelties, new goals or constraints, a lifelong computing system activates an evolutionary self-learning engine that runs online experiments to determine how the computing-learning system needs to evolve to deal with the changes, thereby changing its architecture and integrating new computing elements from computing warehouses as needed.
1 code implementation • 23 Jul 2021 • Mohammad Nabi Omidvar, Danial Yazdani, Juergen Branke, XiaoDong Li, Shengxiang Yang, Xin Yao
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.
1 code implementation • 14 Jul 2021 • Yinghua Yao, Yuangang Pan, Ivor W. Tsang, Xin Yao
This paper proposes Differential-Critic Generative Adversarial Network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property.
no code implementations • 14 Jun 2021 • Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao
We formulate a multiobjective off-grid DOA estimation model to realize this idea, by which the source number can be automatically identified together with DOA estimation.
no code implementations • 14 Jun 2021 • Bai Yan, Qi Zhao, Jin Zhang, J. Andrew Zhang, Xin Yao
To overcome the above shortcomings of relaxation, we propose a novel idea of simultaneously estimating the frequencies and model order by means of the atomic $l_0$ norm.
2 code implementations • 11 Jun 2021 • Danial Yazdani, Juergen Branke, Mohammad Nabi Omidvar, XiaoDong Li, Changhe Li, Michalis Mavrovouniotis, Trung Thanh Nguyen, Shengxiang Yang, Xin Yao
This document describes the Generalized Moving Peaks Benchmark (GMPB) that generates continuous dynamic optimization problem instances.
1 code implementation • 7 May 2021 • Yuan Pu, Shaochen Wang, Xin Yao, Bin Li
The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics.
1 code implementation • 14 Apr 2021 • Hao Tong, Leandro L. Minku, Stefan Menzel, Bernhard Sendhoff, Xin Yao
The few existing studies are limited by the dynamic scenarios considered, and by overly complicated algorithms that are unable to benefit from the wealth of contributions provided by the existing CARP literature.
1 code implementation • 14 Apr 2021 • Yuan Pu, Shaochen Wang, Rui Yang, Xin Yao, Bin Li
Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks.
Ranked #1 on
SMAC+
on Off_Superhard_parallel
Multi-agent Reinforcement Learning
reinforcement-learning
+4
no code implementations • 14 Apr 2021 • Weijie Zheng, Qiaozhi Zhang, Huanhuan Chen, Xin Yao
However, only two elitist algorithms (1+1)EA and ($\mu$+1)EA are analyzed, and it is unknown whether the non-elitism mechanism could help to escape the local optima existed in OneMax$_{(0, 1^n)}$.
1 code implementation • 12 Nov 2020 • Shengcai Liu, Ke Tang, Xin Yao
The Vehicle Routing Problem with Simultaneous Pickup-Delivery and Time Windows (VRPSPDTW) has attracted much research interest in the last decade, due to its wide application in modern logistics.
1 code implementation • 11 Nov 2020 • Chengpeng Hu, Ziqi Wang, Tianye Shu, Hao Tong, Julian Togelius, Xin Yao, Jialin Liu
Our proposed technique is implemented with three state-of-the-art reinforcement learning algorithms and tested on the game set of the 2020 General Video Game AI Learning Competition.
no code implementations • 1 Jul 2020 • Ke Tang, Shengcai Liu, Peng Yang, Xin Yao
In the context of heuristic search, such a paradigm could be implemented as configuring the parameters of a parallel algorithm portfolio (PAP) based on a set of training problem instances, which is often referred to as PAP construction.
no code implementations • 27 Jun 2020 • Han Zhang, Jialin Liu, Xin Yao
The reliable facility location problem (RFLP) is an important research topic of operational research and plays a vital role in the decision-making and management of modern supply chain and logistics.
2 code implementations • 26 May 2020 • Xin Yao, Lifeng Sun
Federated learning (FL) refers to the learning paradigm that trains machine learning models directly in the decentralized systems consisting of smart edge devices without transmitting the raw data, which avoids the heavy communication costs and privacy concerns.
1 code implementation • 23 May 2020 • Ke Li, Haifeng Nie, Huifu Gao, Xin Yao
Knee points, characterised as their smallest trade-off loss at all objectives, are attractive to decision makers in multi-criterion decision-making.
3 code implementations • 13 May 2020 • Tianye Shu, Ziqi Wang, Jialin Liu, Xin Yao
However, defective levels with illegal patterns may be generated due to the violation of constraints for level design.
no code implementations • 26 Apr 2020 • Weijie Zheng, Huanhuan Chen, Xin Yao
In real-world applications, many optimization problems have the time-linkage property, that is, the objective function value relies on the current solution as well as the historical solutions.
1 code implementation • 20 Feb 2020 • Miqing Li, Tao Chen, Xin Yao
We then conduct an in-depth analysis of quality evaluation indicators/methods and general situations in SBSE, which, together with the identified issues, enables us to codify a methodological guidance for selecting and using evaluation methods in different SBSE scenarios.
no code implementations • 7 Feb 2020 • Daniel Herring, Michael Kirley, Xin Yao
A combined approach that mixes solution generation methods to provide a composite population in response to dynamic changes provides improved performance in some instances for the different dynamic TTP formulations.
no code implementations • 20 Jan 2020 • Tao Chen, Rami Bahsoon, Xin Yao
To promote engineering self-aware and self-adaptive software systems in a reusable manner, architectural patterns and the related methodology provide an unified solution to handle the recurring problems in the engineering process.
no code implementations • NeurIPS 2019 • Liangpeng Zhang, Ke Tang, Xin Yao
We argue that explicit planning for exploration can help alleviate such a problem, and propose a Value Iteration for Exploration Cost (VIEC) algorithm which computes the optimal exploration scheme by solving an augmented MDP.
no code implementations • 27 Nov 2019 • Jie Yang, Yu-Kai Wang, Xin Yao, Chin-Teng Lin
(c) The time complexity of the algorithm is quadratic, which is difficult to apply to large datasets.
no code implementations • 19 Nov 2019 • Shengcai Liu, Ke Tang, Yunwen Lei, Xin Yao
Over the last decade, research on automated parameter tuning, often referred to as automatic algorithm configuration (AAC), has made significant progress.
no code implementations • 24 Oct 2019 • Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun
Extensive experiments in several typical lifelong learning scenarios demonstrate that our method outperforms the state-of-the-art methods in both accuracies on new tasks and performance preservation on old tasks.
no code implementations • 18 Oct 2019 • Xin Yao, Tianchi Huang, Rui-Xiao Zhang, Ruiyu Li, Lifeng Sun
Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices.
no code implementations • 16 Oct 2019 • Peng Yang, Qi Yang, Ke Tang, Xin Yao
Empirical results show that the significant advantages of NCS over the compared state-of-the-art methods can be highly owed to the effective parallel exploration ability.
no code implementations • 30 Sep 2019 • Ke Li, Min-Hui Liao, Kalyanmoy Deb, Geyong Min, Xin Yao
The ultimate goal of multi-objective optimisation is to help a decision maker (DM) identify solution(s) of interest (SOI) achieving satisfactory trade-offs among multiple conflicting criteria.
no code implementations • 25 Sep 2019 • Tao Zheng, Ivor Tsang, Xin Yao
We propose an extendable and end-to-end deep representation approach for metric learning on multi-label data set that is based on neural networks able to operate on feature data or directly on raw image data.
2 code implementations • 16 Aug 2019 • Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun
Federated learning (FL) enables on-device training over distributed networks consisting of a massive amount of modern smart devices, such as smartphones and IoT (Internet of Things) devices.
1 code implementation • 6 Aug 2019 • Tianchi Huang, Chao Zhou, Rui-Xiao Zhang, Chenglei Wu, Xin Yao, Lifeng Sun
Using trace-driven and real-world experiments, we demonstrate significant improvements of Comyco's sample efficiency in comparison to prior work, with 1700x improvements in terms of the number of samples required and 16x improvements on training time required.
no code implementations • 31 Jul 2019 • Xiaofen Lu, Ke Tang, Stefan Menzel, Xin Yao
In this paper, a new framework of employing EAs in the context of dynamic optimization is explored.
1 code implementation • 22 Jul 2019 • Lukáš Adam, Xin Yao
Robust optimization over time (ROOT) refers to an optimization problem where its performance is evaluated over a period of future time.
no code implementations • 22 Apr 2019 • Hao Tong, Jialin Liu, Xin Yao
Surrogate-assisted evolutionary algorithms (SAEAs) are powerful optimisation tools for computationally expensive problems (CEPs).
1 code implementation • 15 Feb 2019 • Guoji Fu, Chengbin Hou, Xin Yao
To tackle this issue, we propose a new NRL framework, named HSRL, to help existing NRL methods capture both the local and global topological information of a network.
Ranked #1 on
Link Prediction
on Douban
1 code implementation • 29 Jan 2019 • Guoji Fu, Bo Yuan, Qiqi Duan, Xin Yao
Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space.
Ranked #1 on
Link Prediction
on IMDb
1 code implementation • 17 Jan 2019 • Hao Tong, Changwu Huang, Jialin Liu, Xin Yao
A performance selector is designed to switch the search dynamically and automatically between the global and local search stages.
no code implementations • 6 Dec 2018 • Peng Yang, Ke Tang, Xin Yao
Large-scale optimization problems that involve thousands of decision variables have extensively arisen from various industrial areas.
no code implementations • 11 Oct 2018 • Chao Qian, Chao Bian, Yang Yu, Ke Tang, Xin Yao
In noisy evolutionary optimization, sampling is a common strategy to deal with noise.
no code implementations • 7 Jun 2018 • Liangli Zhen, Miqing Li, Ran Cheng, Dezhong Peng, Xin Yao
The redundancy of some objectives can lead to the multiobjective problem having a degenerate Pareto front, i. e., the dimension of the Pareto front of the $m$-objective problem be less than (m-1).
no code implementations • 17 Apr 2018 • Shengcai Liu, Ke Tang, Xin Yao
Simultaneously utilizing several complementary solvers is a simple yet effective strategy for solving computationally hard problems.
3 code implementations • 1 Mar 2018 • Chaoyue Wang, Chang Xu, Xin Yao, DaCheng Tao
In this paper, we propose a novel GAN framework called evolutionary generative adversarial networks (E-GAN) for stable GAN training and improved generative performance.
no code implementations • 2 Jan 2018 • Ke Li, Renzhi Chen, Dragan Savic, Xin Yao
In the preference elicitation session, the preference information learned in the consultation module is translated into the form that can be used in a decomposition-based EMO algorithm, i. e., a set of reference points that are biased toward to the ROI.
no code implementations • NeurIPS 2017 • Liangpeng Zhang, Ke Tang, Xin Yao
Under/overestimation of state/action values are harmful for reinforcement learning agents.
no code implementations • 21 Nov 2017 • Ke Li, Renzhi Chen, Guangtao Fu, Xin Yao
When solving constrained multi-objective optimization problems, an important issue is how to balance convergence, diversity and feasibility simultaneously.
no code implementations • 20 Nov 2017 • Chao Qian, Yang Yu, Ke Tang, Xin Yao, Zhi-Hua Zhou
To provide a general theoretical explanation of the behavior of EAs, it is desirable to study their performance on general classes of combinatorial optimization problems.
no code implementations • 8 Sep 2017 • Miqing Li, Xin Yao
A set of weights distributed uniformly in a simplex often lead to a set of well-distributed solutions on a Pareto front with a simplex-like shape, but may fail on other Pareto front shapes.
no code implementations • 28 Jul 2017 • Shuo Wang, Leandro L. Minku, Nitesh Chawla, Xin Yao
It provides a forum for international researchers and practitioners to share and discuss their original work on addressing new challenges and research issues in class imbalance learning, concept drift, and the combined issues of class imbalance and concept drift.
no code implementations • 12 Jun 2017 • Bingshui Da, Yew-Soon Ong, Liang Feng, A. K. Qin, Abhishek Gupta, Zexuan Zhu, Chuan-Kang Ting, Ke Tang, Xin Yao
In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously.
no code implementations • 15 May 2017 • Liangli Zhen, Dezhong Peng, Wei Wang, Xin Yao
Our method has the advantages of a closed-form solution and the capacity of clustering data points that lie on nonlinear subspaces.
no code implementations • 30 Apr 2017 • Miqing Li, Liangli Zhen, Xin Yao
In this paper, we make some observations of the parallel coordinates plot, in terms of comparing the quality of solution sets, understanding the shape and distribution of a solution set, and reflecting the relation between objectives.
no code implementations • 29 Mar 2017 • Shengcai Liu, Ke Tang, Xin Yao
The idea behind LiangYi is to promote the population-based solver by training it (with the training module) to improve its performance on those instances (discovered by the sampling module) on which it performs badly, while keeping the good performances obtained by it on previous instances.
no code implementations • 20 Mar 2017 • Shuo Wang, Leandro L. Minku, Xin Yao
As an emerging research topic, online class imbalance learning often combines the challenges of both class imbalance and concept drift.
no code implementations • 12 Feb 2017 • Yu Sun, Ke Tang, Zexuan Zhu, Xin Yao
Incremental learning with concept drift has often been tackled by ensemble methods, where models built in the past can be re-trained to attain new models for the current data.
no code implementations • 1 Feb 2017 • Miqing Li, Xin Yao
In this paper, we propose a quality measure, called dominance move (DoM), to compare solution sets generated by multiobjective optimizers.
no code implementations • 20 Jan 2017 • Ke Li, Kalyanmoy Deb, Xin Yao
Extensive experiments, both proof-of-principle and on a variety of problems with 3 to 10 objectives, fully demonstrate the effectiveness of our proposed method for approximating the preferred solutions in the region of interest.
no code implementations • 26 Dec 2016 • Tian Guo, Zhao Xu, Xin Yao, Haifeng Chen, Karl Aberer, Koichi Funaya
Time series forecasting for streaming data plays an important role in many real applications, ranging from IoT systems, cyber-networks, to industrial systems and healthcare.
no code implementations • 2 Dec 2016 • Liangpeng Zhang, Ke Tang, Xin Yao
We then provide empirical results to verify our approach, and demonstrate how the success probability of exploration can be used to analyse and predict the behaviours and possible outcomes of exploration, which are the keys to the answer of the important questions of exploration.
no code implementations • 18 Sep 2016 • Bingbing Jiang, Chang Li, Maarten de Rijke, Xin Yao, Huanhuan Chen
The proposed method, called probabilistic feature selection and classification vector machine (PFCVMLP ), is able to simultaneously select relevant features and samples for classification tasks.
no code implementations • 23 Aug 2016 • Renzhi Chen, Ke Li, Xin Yao
Existing studies on dynamic multi-objective optimization focus on problems with time-dependent objective functions, while the ones with a changing number of objectives have rarely been considered in the literature.
no code implementations • 11 Mar 2016 • Peng Yang, Ke Tang, Xin Yao
Divide and Conquer (DC) is conceptually well suited to high-dimensional optimization by decomposing a problem into multiple small-scale sub-problems.
no code implementations • 20 Apr 2015 • Ke Tang, Peng Yang, Xin Yao
This paper presents a new EA, namely Negatively Correlated Search (NCS), which maintains multiple individual search processes in parallel and models the search behaviors of individual search processes as probability distributions.
no code implementations • 9 Dec 2013 • Jun He, Feidun He, Xin Yao
The convergence, convergence rate and expected hitting time play fundamental roles in the analysis of randomised search heuristics.
no code implementations • 14 Aug 2013 • Jun He, Xin Yao
Population scalability is the ratio of the expected hitting time between a benchmark algorithm and an algorithm using a larger population size.
no code implementations • 28 Mar 2012 • Jun He, Tianshi Chen, Xin Yao
The aim of this paper is to answer the following research questions: Given a fitness function class, which functions are the easiest with respect to an evolutionary algorithm?