首页期刊导航|中国科学：信息科学（英文版）
期刊信息/Journal information
中国科学：信息科学（英文版）
中国科学：信息科学（英文版）

周光召

月刊

1674-733X

informatics@scichina.org

010-64015683

100717

北京东黄城根北街16号

中国科学：信息科学（英文版）/Journal Science China Information SciencesCSCDCSTPCDEISCI
查看更多>>《中国科学》是中国科学院主办、中国科学杂志社出版的自然科学专业性学术刊物。《中国科学》任务是反映中国自然科学各学科中的最新科研成果，以促进国内外的学术交流。《中国科学》以论文形式报道中国基础研究和应用研究方面具有创造性的、高水平的和有重要意义的科研成果。在国际学术界，《中国科学》作为代表中国最高水平的学术刊物也受到高度重视。国际上最具有权威的检索刊物SCI，多年来一直收录《中国科学》的论文。1999年《中国科学》夺得国家期刊奖的第一名。
正式出版
收录年代

    Deep learning for code generation:a survey

    Huangzhao ZHANGKechi ZHANGZhuo LIJia LI...
    1-36页
    查看更多>>摘要：In the past decade,thanks to the powerfulness of deep-learning techniques,we have witnessed a whole new era of automated code generation.To sort out developments,we have conducted a comprehensive review of solutions to deep learning-based code generation.In this survey,we generally formalize the pipeline and procedure of code generation and categorize existing solutions according to taxonomy from perspectives of architecture,model-agnostic enhancing strategy,metrics,and tasks.In addition,we outline the challenges faced by current dominant large models and list several plausible directions for future research.We hope that this survey may provide handy guidance to understanding,utilizing,and developing deep learning-based code-generation techniques for researchers and practitioners.
      原文链接:
    • 万方数据

    Fairness in machine learning:definition,testing,debugging,and application

    Xuanqi GAOChao SHENWeipeng JIANGChenhao LIN...
    37-57页
    查看更多>>摘要：In recent years,artificial intelligence technology has been widely used in many fields,such as computer vision,natural language processing and autonomous driving.Machine learning algorithms,as the core technique of AI,have significantly facilitated people's lives.However,underlying fairness issues in machine learning systems can pose risks to individual fairness and social security.Studying fairness definitions,sources of problems,and testing and debugging methods of fairness can help ensure the fairness of machine learning systems and promote the wide application of artificial intelligence technology in various fields.This paper introduces relevant definitions of machine learning fairness and analyzes the sources of fairness problems.Besides,it provides guidance on fairness testing and debugging methods and summarizes popular datasets.This paper also discusses the technical advancements in machine learning fairness and highlights future challenges in this area.
      原文链接:
    • 万方数据

    LOL:a highly flexible framework for designing stream ciphers

    Dengguo FENGLin JIAOYonglin HAOQunxiong ZHENG...
    58-71页
    查看更多>>摘要：In this paper,we propose LOL,a general framework for designing blockwise stream ciphers.The proposed framework achieves ultrafast software implementations for ubiquitous virtual networks in 5G/6G environments and high-security levels for post-quantum cryptography.The LOL framework is structurally strong;furthermore,this framework and all its components enjoy high flexibility with various extensions.On the basis of the LOL framework,we propose new stream-cipher designs called LOL-MINI and LOL-DOUBLE with the support of the AES-NI and single instruction multiple data instructions.The former applies the basic LOL single mode,while the latter uses the extended parallel-dual mode.LOL-MINI and LOL-DOUBLE support 256-bit key length.Our thorough evaluations revealed that these cipher designs have 256-bit security margins against all existing cryptanalysis methods,including differential,linear,and integral.The software performances of LOL-MINI and LOL-DOUBLE can reach 89 and 135 Gbps.In addition to pure encryptions,the LOL-MINI and LOL-DOUBLE stream ciphers can be applied in a stream-cipher-then-MAC strategy to make AEAD schemes.
      原文链接:
    • 万方数据

    OpBench:an operator-level GPU benchmark for deep learning

    Qingwen GUBo FANZhengning LIUKaicheng CAO...
    72-83页
    查看更多>>摘要：Operators(such as Conv and ReLU)play an important role in deep neural networks.Every neural network is composed of a series of differentiable operators.However,existing AI benchmarks mainly focus on accessing model training and inference performance of deep learning systems on specific models.To help GPU hardware find computing bottlenecks and intuitively evaluate GPU performance on specific deep learning tasks,this paper focuses on evaluating GPU performance at the operator level.We statistically analyze the information of operators on 12 representative deep learning models from six prominent AI tasks and provide an operator dataset to show the different importance of various types of operators in different networks.An operator-level benchmark,OpBench,is proposed on the basis of this dataset,allowing users to choose from a given range of models and set the input sizes according to their demands.This benchmark offers a detailed operator-level performance report for AI and hardware developers.We also evaluate four GPU models on OpBench and find that their performances differ on various types of operators and are not fully consistent with the performance metric FLOPS(floating point operations per second).
      原文链接:
    • 万方数据

    An efficient schedulability analysis based on worst-case interference time for real-time systems

    Hongbiao LIUMengfei YANGLei QIAOXi CHEN...
    84-100页
    查看更多>>摘要：Real-time systems are widely implemented in the Internet of Things(IoT)and safety-critical systems,both of which have generated enormous social value.Aiming at the classic schedulability analysis problem in real-time systems,we proposed an exact Boolean analysis based on interference(EBAI)for schedulability analysis in real-time systems.EBAI is based on worst-case interference time(WCIT),which considers both the release jitter and blocking time of the task.We improved the efficiency of the three existing tests and provided a comprehensive summary of related research results in the field.Abundant experiments were conducted to compare EBAI with other related results.Our evaluation showed that in certain cases,the runtime gain achieved using our analysis method may exceed 73％compared to the state-of-the-art schedulability test.Furthermore,the benefits obtained from our tests grew with the number of tasks,reaching a level suitable for practical application.EBAI is oriented to the five-tuple real-time task model with stronger expression ability and possesses a low runtime overhead.These characteristics make it applicable in various real-time systems such as spacecraft,autonomous vehicles,industrial robots,and traffic command systems.
      原文链接:
    • 万方数据

    SDCC:software-defined collective communication for distributed training

    Xin JINZhen ZHANGYunshan JIAYun MA...
    101-121页
    查看更多>>摘要：Communication is crucial to the performance of distributed training.Today's solutions tightly couple the control and data planes and lack flexibility,generality,and performance.In this study,we present SDCC,a software-defined collective communication framework for distributed training.SDCC is based on the principle of modern systems design to effectively decouple the control plane from the data plane.SDCC abstracts the operations for collective communication in distributed training with dataflow operations and unifies computing and communication with a single dataflow graph.The abstraction,together with the unification,is powerful:it enables users to easily express new and existing collective communication algorithms and optimizations,simplifies the integration with different computing engines(e.g.,PyTorch and TensorFlow)and network transports(e.g.,Linux TCP and kernel bypass),and allows the system to improve performance by exploiting parallelism exposed by the dataflow graph.We further demonstrate the benefits of SDCC in four use cases.
      原文链接:
    • 万方数据

    Relative difficulty distillation for semantic segmentation

    Dong LIANGYue SUNYun DUSongcan CHEN...
    122-141页
    查看更多>>摘要：Current knowledge distillation(KD)methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network.However,introducing too many additional optimization objectives may lead to unstable training,such as gradient conflicts.Moreover,these methods ignored the guidelines of relative learning difficulty between the teacher and student networks.Inspired by human cognitive science,in this paper,we redefine knowledge from a new perspective-the student and teacher networks'relative difficulty of samples,and propose a pixel-level KD paradigm for semantic segmentation named relative difficulty distillation(RDD).We propose a two-stage RDD framework:teacher-full evaluated RDD(TFE-RDD)and teacher-student evaluated RDD(TSE-RDD).RDD allows the teacher network to provide effective guidance on learning focus without additional optimization goals,thus avoiding adjusting learning weights for multiple losses.Extensive experimental evaluations using a general distillation loss function on popular datasets such as Cityscapes,CamVid,Pascal VOC,and ADE20k demonstrate the effectiveness of RDD against state-of-the-art KD methods.Additionally,our research showcases that RDD can integrate with existing KD methods to improve their upper performance bound.Codes are available at https://github.com/sunyueue/RDD.git.
      原文链接:
    • 万方数据

    Physics-informed deep Koopman operator for Lagrangian dynamic systems

    Xuefeng WANGYang CAOShaofeng CHENYu KANG...
    142-159页
    查看更多>>摘要：Accurate mechanical system models are crucial for safe and stable control.Unlike linear systems,Lagrangian systems are highly nonlinear and difficult to optimize because of their unknown system model.Recent research thus used deep neural networks to generate linear models of original systems by mapping nonlinear dynamic systems into a linear space with a Koopman observable function encoder.The controller then relies on the Koopman linear model.However,without physical information constraints,ensuring con-trol consistency between the original nonlinear system and the Koopman system is tough,as the learning process of the Koopman observation function is unsupervised.This paper thus proposes a two-stage learning algorithm that uses structural subnetworks to build a physics-informed network topology to simultaneously learn the Koopman observable functions and the system energy representation.In the Koopman matrix learning session,a quadratic-constrained optimization problem is solved to ensure that the Koopman rep-resentation satisfies the energy difference matching hard constraint.The proposed energy-preserving deep Lagrangian Koopman(EPDLK)framework effectively represents the dynamics of the Lagrangian system while ensuring control consistency.The effectiveness of EPDLK is compared with those of various Koopman observable function construction methods in multistep prediction and trajectory tracking tasks.EPDLK achieves better control consistency by guaranteeing energy difference matching,which facilitates the appli-cation of the control law generated on the Koopman system directly to the original nonlinear Lagrangian system.
      原文链接:
    • 万方数据

    Deterministic learning-based neural output-feedback control for a class of nonlinear sampled-data systems

    Yu ZENGFukai ZHANGTianrui CHENCong WANG...
    160-179页
    查看更多>>摘要：This study investigates the deterministic learning(DL)-based output-feedback neural control for a class of nonlinear sampled-data systems with prescribed performance(PP).Specifically,first,a sampled-data observer is employed to estimate the unavailable system states for the Euler discretization model of the transformed system dynamics.Then,based on the observations and backstepping method,a discrete neural network(NN)controller is constructed to ensure system stability and achieve the desired tracking performance.The noncausal problem encountered during the controller deduction process is resolved using a command filter.Moreover,the regression characteristics of the NN input signals are demonstrated with the observed states.This ensures that the radial basis function NN,based on DL theory,meets the partial persistent excitation condition.Subsequently,a class of discrete linear time-varying systems is proven to be exponentially stable,achieving partial convergence of neural weights to their optimal/actual values.Conse-quently,accurate modeling of unknown closed-loop dynamics is achieved along the system trajectory from the output-feedback control.Finally,a knowledge-based controller is developed using the modeling results.This controller not only enhances the control performance but also ensures the PP of the tracking error.The effectiveness of the scheme is illustrated through simulation results.
      原文链接:
    • 万方数据

    Nonsingularity of grain-like cascade feedback shift registers subject to fault attacks

    Haitao LIZhaoqi LIUWenrong LI
    180-191页
    查看更多>>摘要：Feedback shift registers(FSRs)are pivotal in generating pseudorandom sequences for stream ciphers and play a crucial role in error detection and code correction.This paper investigates the resilience of grain-like cascade FSRs(GLC-FSRs)against two types of fault attacks:hard and soft.First,we introduce a new criterion for assessing the nonsingularity of GLC-FSRs using the structure matrices of feedback functions,which enable the measurement of the number of nonsingular GLC-FSRs.Second,we demonstrate that GLC-FSRs subject to hard fault attacks become singular as determined by this new criterion.Ultimately,by constructing a soft fault bit set,we discuss the resilience of GLC-FSRs to soft fault attacks.Results demonstrate that singular GLC-FSRs remain singular after being injected by soft fault attacks.Conversely,for nonsingular GLC-FSRs,suitable soft fault attacks are designed to maintain their nonsingular status.
      原文链接:
    • 万方数据