首页期刊导航|机器智能研究（英文）
期刊信息/Journal information
机器智能研究（英文）
机器智能研究（英文）

谭铁牛　刘国平　胡豁生

双月刊

2731-538X

ijac@ia.ac.cn

010-62655893

100190

北京海淀区中关村东路95号2728信箱

机器智能研究（英文）/Journal Machine Intelligence ResearchCSCDCSTPCD北大核心EI
查看更多>>International Journal of Automation and computing is a publication of Institute of Automation, the Chinese Academy of Sciencs and Chinese Automation and computing Society in the United Kingdom. The Journal publishes papers on original theoretical and experimental research and development in automation and computing. The scope of the journal is extensive. Topics include; artificial intelligence, automatic control, bioinformatics, computer sciene, information technology, modeling and simulation, networks and communications, optimization and decision, pattern recognition, robotics, signal processing, and systems engineering.
正式出版
收录年代

    Distributed Deep Reinforcement Learning:A Survey and a Multi-player Multi-agent Learning Toolbox

    Qiyue YinTongtong YuShengqi ShenJun Yang...
    411-430页
    查看更多>>摘要：With the breakthrough of AlphaGo,deep reinforcement learning has become a recognized technique for solving sequential decision-making problems.Despite its reputation,data inefficiency caused by its trial and error learning mechanism makes deep rein-forcement learning difficult to apply in a wide range of areas.Many methods have been developed for sample efficient deep reinforce-ment learning,such as environment modelling,experience transfer,and distributed modifications,among which distributed deep rein-forcement learning has shown its potential in various applications,such as human-computer gaming and intelligent transportation.In this paper,we conclude the state of this exciting field,by comparing the classical distributed deep reinforcement learning methods and studying important components to achieve efficient distributed learning,covering single player single agent distributed deep reinforce-ment learning to the most complex multiple players multiple agents distributed deep reinforcement learning.Furthermore,we review re-cently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distrib-uted versions.By analysing their strengths and weaknesses,a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released,which is further validated on Wargame,a complex environment,showing the usability of the proposed tool-box for multiple players and multiple agents distributed deep reinforcement learning under complex games.Finally,we try to point out challenges and future trends,hoping that this brief review can provide a guide or a spark for researchers who are interested in distrib-uted deep reinforcement learning.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Parsing Objects at a Finer Granularity:A Survey

    Yifan ZhaoJia LiYonghong Tian
    431-451页
    查看更多>>摘要：Fine-grained visual parsing,including fine-grained part segmentation and fine-grained object recognition,has attracted considerable critical attention due to its importance in many real-world applications,e.g.,agriculture,remote sensing,and space techno-logies.Predominant research efforts tackle these fine-grained sub-tasks following different paradigms,while the inherent relations between these tasks are neglected.Moreover,given most of the research remains fragmented,we conduct an in-depth study of the ad-vanced work from a new perspective of learning the part relationship.In this perspective,we first consolidate recent research and bench-mark syntheses with new taxonomies.Based on this consolidation,we revisit the universal challenges in fine-grained part segmentation and recognition tasks and propose new solutions by part relationship learning for these important challenges.Furthermore,we conclude several promising lines of research in fine-grained visual parsing for future research.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Collective Movement Simulation:Methods and Applications

    Hua WangXing-Yu GuoHao TaoMing-Liang Xu...
    452-480页
    查看更多>>摘要：Collective movement simulations are challenging and important in many areas,including life science,mathematics,physics,information science and public safety.In this survey,we provide a comprehensive review of the state-of-the-art techniques for collective movement simulations.We start with a discussion on certain concepts to help beginners understand it more systematically.Then,we analyze the intelligence among different collective objects and the emphasis in different fields.Next,we classify existing collective move-ment simulation methods into four categories according to their effects,namely versatility,accuracy,dynamic adaptability,and assess-ment feedback capability.Furthermore,we introduce five applications of layout optimization,emergency control,dispatching,un-manned systems,and other derivative applications.Finally,we summarize possible future research directions.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Ripple Knowledge Graph Convolutional Networks for Recommendation Systems

    Chen LiYang CaoYe ZhuDebo Cheng...
    481-494页
    查看更多>>摘要：Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to ef-fectively improve the model's interpretability and accuracy.This paper introduces an end-to-end deep learning model,named represent-ation-enhanced knowledge graph convolutional networks(RKGCN),which dynamically analyses each user's preferences and makes a re-commendation of suitable items.It combines knowledge graphs on both the item side and user side to enrich their representations to maximize the utilization of the abundant information in knowledge graphs.RKGCN is able to offer more personalized and relevant re-commendations in three different scenarios.The experimental results show the superior effectiveness of our model over 5 baseline mod-els on three real-world datasets including movies,books,and music.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    On Robust Cross-view Consistency in Self-supervised Monocular Depth Estimation

    Haimei ZhaoJing ZhangZhuo ChenBo Yuan...
    495-513页
    查看更多>>摘要：Remarkable progress has been made in self-supervised monocular depth estimation(SS-MDE)by exploring cross-view con-sistency,e.g.,photometric consistency and 3D point cloud consistency.However,they are very vulnerable to illumination variance,oc-clusions,texture-less regions,as well as moving objects,making them not robust enough to deal with various scenes.To address this challenge,we study two kinds of robust cross-view consistency in this paper.Firstly,the spatial offset field between adjacent frames is obtained by reconstructing the reference frame from its neighbors via deformable alignment,which is used to align the temporal depth features via a depth feature alignment(DFA)loss.Secondly,the 3D point clouds of each reference frame and its nearby frames are calcu-lated and transformed into voxel space,where the point density in each voxel is calculated and aligned via a voxel density alignment(VDA)loss.In this way,we exploit the temporal coherence in both depth feature space and 3D voxel space for SS-MDE,shifting the"point-to-point"alignment paradigm to the"region-to-region"one.Compared with the photometric consistency loss as well as the rigid point cloud alignment loss,the proposed DFA and VDA losses are more robust owing to the strong representation power of deep fea-tures as well as the high tolerance of voxel density to the aforementioned challenges.Experimental results on several outdoor bench-marks show that our method outperforms current state-of-the-art techniques.Extensive ablation study and analysis validate the effect-iveness of the proposed losses,especially in challenging scenes.The code and models are available at https://github.com/sunnyHelen/RCVC-depth.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Structural Dependence Learning Based on Self-attention for Face Alignment

    Biying LiZhiwei LiuWei ZhouHaiyun Guo...
    514-525页
    查看更多>>摘要：Self-attention aggregates similar feature information to enhance the features.However,the attention covers nonface areas in face alignment,which may be disturbed in challenging cases,such as occlusions,and fails to predict landmarks.In addition,the learned feature similarity variance is not large enough in the experiment.To this end,we propose structural dependence learning based on self-attention for face alignment(SSFA).It limits the self-attention learning to the facial range and adaptively builds the significant landmark structure dependency.Compared with other state-of-the-art methods,SSFA effectively improves the performance on several standard facial landmark detection benchmarks and adapts more in challenging cases.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Overhead-free Noise-tolerant Federated Learning:A New Baseline

    Shiyi LinDeming ZhaiFeilong ZhangJunjun Jiang...
    526-537页
    查看更多>>摘要：Federated learning(FL)is a promising decentralized machine learning approach that enables multiple distributed clients to train a model jointly while keeping their data private.However,in real-world scenarios,the supervised training data stored in local cli-ents inevitably suffer from imperfect annotations,resulting in subjective,inconsistent and biased labels.These noisy labels can harm the collaborative aggregation process of FL by inducing inconsistent decision boundaries.Unfortunately,few attempts have been made to-wards noise-tolerant federated learning,with most of them relying on the strategy of transmitting overhead messages to assist noisy la-bels detection and correction,which increases the communication burden as well as privacy risks.In this paper,we propose a simple yet effective method for noise-tolerant FL based on the well-established co-training framework.Our method leverages the inherent discrep-ancy in the learning ability of the local and global models in FL,which can be regarded as two complementary views.By iteratively ex-changing samples with their high confident predictions,the two models"teach each other"to suppress the influence of noisy labels.The proposed scheme enjoys the benefit of overhead cost-free and can serve as a robust and efficient baseline for noise-tolerant federated learning.Experimental results demonstrate that our method outperforms existing approaches,highlighting the superiority of our meth-od.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Dual Frequency Transformer for Efficient SDR-to-HDR Translation

    Gang XuQibin HouMing-Ming Cheng
    538-548页
    查看更多>>摘要：The SDR-to-HDR translation technique can convert the abundant standard-dynamic-range(SDR)media resources to high-dynamic-range(HDR)ones,which can represent high-contrast scenes,providing more realistic visual experiences.While recent vision Transformers have achieved promising performance in many low-level vision tasks,there are few works attempting to leverage Trans-formers for SDR-to-HDR translation.In this paper,we are among the first to investigate the performance of Transformers for SDR-to-HDR translation.We find that directly using the self-attention mechanism may involve artifacts in the results due to the inappropriate way to model long-range dependencies between the low-frequency and high-frequency components.Taking this into account,we ad-vance the self-attention mechanism and present a dual frequency attention(DFA),which leverages the self-attention mechanism to sep-arately encode the low-frequency structural information and high-frequency detail information.Based on the proposed DFA,we further design a multi-scale feature fusion network,named dual frequency Transformer(DFT),for efficient SDR-to-HDR translation.Extens-ive experiments on the HDRTV1K dataset demonstrate that our DFT can achieve better quantitative and qualitative performance than the recent state-of-the-art methods.The code of our DFT is made publicly available at https://github.com/CS-GangXu/DFT.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    An Empirical Study on Google Research Football Multi-agent Scenarios

    Yan SongHe JiangZheng TianHaifeng Zhang...
    549-570页
    查看更多>>摘要：Few multi-agent reinforcement learning(MARL)researches on Google research football(GRF)[1]focus on the 11-vs-11 multi-agent full-game scenario and to the best of our knowledge,no open benchmark on this scenario has been released to the public.In this work,we fill the gap by providing a population-based MARL training pipeline and hyperparameter settings on multi-agent football scenario that outperforms the bot with difficulty 1.0 from scratch within 2 million steps.Our experiments serve as a reference for the ex-pected performance of independent proximal policy optimization(IPPO)[2],a state-of-the-art multi-agent reinforcement learning al-gorithm where each agent tries to maximize its own policy independently across various training configurations.Meanwhile,we release our training framework Light-MALib which extends the MALib[3]codebase by distributed and asynchronous implementation with addi-tional analytical tools for football games.Finally,we provide guidance for building strong football AI with population-based training[4]and release diverse pretrained policies for benchmarking.The goal is to provide the community with a head start for whoever experi-ment their works on GRF and a simple-to-use population-based training framework for further improving their agents through self-play.The implementation is available at https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football.
      原文链接:
    • NETL
    • NSTL
    • 万方数据

    Generalized Embedding Machines for Recommender Systems

    Enneng YangXin XinLi ShenYudong Luo...
    571-584页
    查看更多>>摘要：Factorization machine(FM)is an effective model for feature-based recommendation that utilizes inner products to capture second-order feature interactions.However,one of the major drawbacks of FM is that it cannot capture complex high-order interaction signals.A common solution is to change the interaction function,such as stacking deep neural networks on the top level of FM.In this work,we propose an alternative approach to model high-order interaction signals at the embedding level,namely generalized embed-ding machine(GEM).The embedding used in GEM encodes not only the information from the feature itself but also the information from other correlated features.Under such a situation,the embedding becomes high-order.Then we can incorporate GEM with FM and even its advanced variants to perform feature interactions.More specifically,in this paper,we utilize graph convolution networks(GCN)to generate high-order embeddings.We integrate GEM with several FM-based models and conduct extensive experiments on two real-world datasets.The results demonstrate significant improvement of GEM over the corresponding baselines.
      原文链接:
    • NETL
    • NSTL
    • 万方数据