Xiaoyu He

Xiaoyu He

Auto-generated profile, based on publicly available information

Xiaoyu He

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 August 2022 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
CCChunjiang Che
Chunjiang Che
XLXiaoli Li
Xiaoli Li
CCChuan Chen
Chuan Chen
XHXiaoyu He
Xiaoyu He
ZZZibin Zheng
Zibin Zheng
Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training method is prone to attacks from Byzantine clients, which interfere with the training of the global model by modifying the model or uploading the false gradient. In this article, we propose a novel serverless federated learning framework Committee Mechanism based Federated Learning (CMFL), which can ensure the robustness of the algorithm with convergence guarantee. In CMFL, a committee system is set up to screen the uploaded local gradients. The committee system selects the local gradients rated by the elected members for the aggregation procedure through the selection strategy, and replaces the committee member through the election strategy. Based on the different considerations of model performance and defense, two opposite selection strategies are designed for the sake of both accuracy and robustness. Extensive experiments illustrate that CMFL achieves faster convergence and better accuracy than the typical Federated Learning, in the meanwhile obtaining better robustness than the traditional Byzantine-tolerant algorithms, in the manner of a decentralized approach. In addition, we theoretically analyze and prove the convergence of CMFL under different election and selection strategies, which coincides with the experimental results.

15 August 2018 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
XHXiaoyu He
Xiaoyu He
YZYuren Zhou
Yuren Zhou
ZCZefeng Chen
Zefeng Chen
QZQingfu Zhang
Qingfu Zhang
Decomposition-based many-objective evolutionary algorithms generally decompose the objective space into multiple subregions with the help of a set of reference vectors. The resulting subregions are fixed since the reference vectors are usually pre-defined. When the optimization problem has a complicated Pareto front, this decomposition may decrease the algorithm performance. To deal with this problem, this paper proposes a dynamical decomposition strategy. Instead of using pre-defined reference vectors, solution themselves are used as reference vectors. Thus, they are adapted to the shape of Pareto front automatically. Besides, the subregions are produced one by one through successively bipartitioning the objective space. The resulting subregions are not fixed but dynamically determined by the population solutions as well as the subregions produced previously. Based on this strategy, a solution ranking method, named DDR, is proposed which can be employed in the mating selection and environmental selection in commonly used algorithm frameworks. Compared with those in the other decomposition-based algorithms, DDR has the following properties: (1) no pre-defined reference vectors are required; (2) less parameters are involved and (3) the ranking results can not only be utilized directly to select solutions but also serve as a secondary criterion in traditional Pareto-based algorithms. In this paper, DDR is equipped in two algorithm frameworks for handling many-objective optimization problems. Comparisons with five state-of-the-art algorithms on 31 widely used test problems are carried out to test the performance of the proposed approach. The experimental results have shown the effectiveness of the proposed approach in keeping a good trade-off between convergence and diversity.

27 July 2020 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
YZYuren Zhou
Yuren Zhou
YXYi Xiang
Yi Xiang
XHXiaoyu He
Xiaoyu He
Constrained multi-objective optimization abounds in practical applications and is gaining growing attention in the evolutionary computation community. Artificial test problems are critical to the progress in this research area. Nevertheless, many of them lack important characteristics such as scalability and variable dependencies, which may be essential in benchmarking modern evolutionary algorithms. This paper firstly proposes a new framework for constrained test problem construction. This framework splits a decision vector into position and distance variables, and forces their optimal values to lie on a non-linear hypersurface such that the inter-dependencies can be introduced among the position ones and among the distance ones individually. In this framework, two kinds of constraints are designed to introduce convergence-hardness and diversity-hardness respectively. The first kind introduces infeasible barriers in approaching the optima, and at the same time, makes the position and distance variables inter-relate with each other. The second kind restricts the feasible optimal regions such that different shapes of Pareto fronts can be obtained. Based on this framework, we construct 16 scalable and constrained test problems covering a variety of difficulties. Then, in the second part of this paper, we evaluate the performance of some state of the art on the proposed test problems, showing that they are quite challenging and there is room for further enhancement of existing algorithms. Finally, we discuss in detail the source of difficulties presented in these new problems.

18 November 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
ZCZefeng Chen
Zefeng Chen
YZYuren Zhou
Yuren Zhou
XHXiaoyu He
Xiaoyu He
JZJun Zhang
Jun Zhang
Multiobjective multifactorial optimization (MO-MFO), rooted in a multitasking environment, is an emerging paradigm wherein multiple distinct multiobjective optimization problems are solved together. This article proposes an evolutionary multitasking algorithm with learning task relationships (LTR) for MO-MFO. In the proposed algorithm, a procedure of LTR is well designed. The decision space of each task is treated as a manifold, and all decision spaces of different tasks are jointly modeled as a joint manifold. Then, through solving a generalized eigenvalue decomposition problem, the joint manifold is projected to a latent space while keeping the necessary features for all tasks and the topology of each manifold. Finally, the task relationships are represented as the joint mapping matrix, which is composed of multiple mapping functions, and they are utilized for information transfer across different decision spaces during the evolutionary process. In the empirical experiments, the performance of the proposed algorithm is verified and compared with several state-of-the-art solvers for MO-MFO on three suites of MO-MFO test problems. Empirical results demonstrate that the proposed algorithm surpasses other competitors on most test instances, and can well tackle complicated MO-MFO problems which involve distinct optimization tasks with heterogeneous decision spaces.

17 January 2025 in IEEE Computational Intelligence Magazine
Verified
Journal Article
Closed access
QDQianlong Dang
Qianlong Dang
GZGuanghui Zhang
Guanghui Zhang
LWLing Wang
Ling Wang
YYYang Yu
Yang Yu
SYShuai Yang
Shuai Yang
XHXiaoyu He
Xiaoyu He
Traditional multimodal multi-objective evolutionary algorithms (MMOEAs) usually adopt the reproduction strategy based on meta-heuristic and fail to make full use of changes of multi-generation population distribution, which can help the population to further evolve and improve the exploitation ability of algorithms. To address this issue, this paper proposes a deep learning-based evolutionary algorithm (DLEA), which converts historical population information into time series and uses deep neural networks to predict the population distribution. Specifically, a transformer-based prediction model is constructed to reproduce promising offspring by capturing changes of population distribution in adjacent generations. Moreover, many MMOEAs focus only on global Pareto optimal solution sets (PSs) and ignore local PSs. Although local PSs are inferior to global PSs in terms of objective values, the cost of obtaining global PSs in some practical applications is huge. Local PSs with similar objectives to global PSs are acceptable alternatives for decision makers. Therefore, a difference-based attention mechanism is designed for archive update, which saves solutions on the global PSs and local PSs by calculating the attention value. Experimental studies indicate that DLEA outperforms other six competitive MMOEAs.

29 October 2020 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
XHXiaoyu He
Xiaoyu He
ZZZibin Zheng
Zibin Zheng
YZYuren Zhou
Yuren Zhou
This work provides an efficient sampling method for the covariance matrix adaptation evolution strategy (CMAES) in large-scale settings. In contract to the Gaussian sampling in CMA-ES, the proposed method generates mutation vectors from a mixture model, which facilitates exploiting the rich variable correlations of the problem landscape within a limited time budget. We analyze the probability distribution of this mixture model and show that it approximates the Gaussian distribution of CMA-ES with a controllable accuracy. We use this sampling method, coupled with a novel method for mutation strength adaptation, to formulate the mixture model based evolution strategy (MMES) -a CMA-ES variant for large-scale optimization. The numerical simulations show that, while significantly reducing the time complexity of CMA-ES, MMES preserves the rotational invariance, is scalable to high dimensional problems, and is competitive against the state-of-the-arts in performing global optimization.