期刊,机器智能研究（英文） 2024年卷2期_国家学术搜索

期刊信息/Journal information

机器智能研究（英文）

主　　编：谭铁牛　刘国平　胡豁生

出版周期：双月刊

国际刊号：2731-538X

电子邮箱：ijac@ia.ac.cn

电　　话：010-62655893

邮政编码：100190

地　　址：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

Editorial for Special Issue on Commonsense Knowledge and Reasoning:Representation,Acquisition and Applications

Kang LiuYangqiu SongJeff Z.Pan

215-216页

原文链接:

NETL
NSTL
万方数据

The Life Cycle of Knowledge in Big Language Models:A Survey

Boxi CaoHongyu LinXianpei HanLe Sun...

217-238页

查看更多>>摘要：Knowledge plays a critical role in artificial intelligence.Recently,the extensive success of pre-trained language models(PLMs)has raised significant attention about how knowledge can be acquired,maintained,updated and used by language models.Des-pite the enormous amount of related studies,there is still a lack of a unified view of how knowledge circulates within language models throughout the learning,tuning,and application processes,which may prevent us from further understanding the connections between current progress or realizing existing limitations.In this survey,we revisit PLMs as knowledge-based systems by dividing the life circle of knowledge in PLMs into five critical periods,and investigating how knowledge circulates when it is built,maintained and used.To this end,we systematically review existing studies of each period of the knowledge life cycle,summarize the main challenges and current limitations,and discuss future directions1.

原文链接:

NETL
NSTL
万方数据

A Comprehensive Overview of CFN From a Commonsense Perspective

Ru LiYunxiao ZhaoZhiqiang WangXuefeng Su...

239-256页

查看更多>>摘要：Chinese FrameNet(CFN)is a scenario commonsense knowledge base(CKB)that plays an important role in research on Chinese language understanding.It is based on the theory of frame semantics and English FrameNet(FN).The CFN knowledge base contains a wealth of scenario commonsense knowledge,including frames,frame elements,and frame relations,as well as annotated in-stances with rich scenario-related labels on Chinese sentences and discourses.In this paper,we conduct a comprehensive overview of CFN from a commonsense perspective,covering topics such as scenario commonsense representation,CFN resources,and its applica-tions.We also summarize recent breakthroughs and identify future research directions.First,we introduce the concept of scenario com-monsense,including its definitions,examples,and representation methods,with a focus on the relationship between scenario common-sense and the frame concept in CFN.In addition,we provide a comprehensive overview of CFN resources and their applications,high-lighting the newly proposed frame-based discourse representation and a human-machine collaboration framework for expanding the CFN corpus.Furthermore,we explore emerging topics such as expanding the CFN resource,improving the interpretability of machine reading comprehension,and using scenario CKBs for text generation.

原文链接:

NETL
NSTL
万方数据

Corporate Credit Ratings Based on Hierarchical Heterogeneous Graph Neural Networks

Bo-Jing FengXi ChengHao-Nan XuWen-Fang Xue...

257-271页

查看更多>>摘要：In order to help investors understand the credit status of target corporations and reduce investment risks,the corporate credit rating model has become an important evaluation tool in the financial market.These models are based on statistical learning,ma-chine learning and deep learning especially graph neural networks(GNNs).However,we found that only few models take the hierarchy,heterogeneity or unlabeled data into account in the actual corporate credit rating process.Therefore,we propose a novel framework named hierarchical heterogeneous graph neural networks(HHGNN),which can fully model the hierarchy of corporate features and the heterogeneity of relationships between corporations.In addition,we design an adversarial learning block to make full use of the rich un-labeled samples in the financial data.Extensive experiments conducted on the public-listed corporate rating dataset prove that HHGNN achieves SOTA compared to the baseline methods.

原文链接:

NETL
NSTL
万方数据

GraphFlow+:Exploiting Conversation Flow in Conversational Machine Comprehension with Graph Neural Networks

Jing HuLingfei WuYu ChenPo Hu...

272-282页

查看更多>>摘要：The conversation machine comprehension(MC)task aims to answer questions in the multi-turn conversation for a single passage.However,recent approaches don't exploit information from historical conversations effectively,which results in some references and ellipsis in the current question cannot be recognized.In addition,these methods do not consider the rich semantic relationships between words when reasoning about the passage text.In this paper,we propose a novel model GraphFlow+,which constructs a context graph for each conversation turn and uses a unique recurrent graph neural network(GNN)to model the temporal dependencies between the context graphs of each turn.Specifically,we exploit three different ways to construct text graphs,including the dynamic graph,stat-ic graph,and hybrid graph that combines the two.Our experiments on CoQA,QuAC and DoQA show that the GraphFlow+model can outperform the state-of-the-art approaches.

原文链接:

NETL
NSTL
万方数据

Text Difficulty Study:Do Machines Behave the Same as Humans Regarding Text Difficulty?

Bowen ChenXiao DingYi ZhaoBo Fu...

283-293页

查看更多>>摘要：With the emergence of pre-trained models,current neural networks are able to give task performance that is comparable to humans.However,we know little about the fundamental working mechanism of pre-trained models in which we do not know how they approach such performance and how the task is solved by the model.For example,given a task,human learns from easy to hard,where-as the model learns randomly.Undeniably,difficulty-insensitive learning leads to great success in natural language processing(NLP),but little attention has been paid to the effect of text difficulty in NLP.We propose a human learning matching index(HLM Index)to investigate the effect of text difficulty.Experiment results show:1)LSTM gives more human-like learning behavior than BERT.Addi-tionally,UID-SuperLinear gives the best evaluation of text difficulty among four text difficulty criteria.Among nine tasks,some tasks'performance is related to text difficulty,whereas others are not.2)Model trained on easy data performs best in both easy and medium test data,whereas trained on hard data only performs well on hard test data.3)Train the model from easy to hard,leading to quicker convergence.

原文链接:

NETL
NSTL
万方数据

Automation and Orchestration of Zero Trust Architecture:Potential Solutions and Challenges

Yang CaoShiva Raj PokhrelYe ZhuRobin Doss...

294-317页

查看更多>>摘要：Zero trust architecture(ZTA)is a paradigm shift in how we protect data,stay connected and access resources.ZTA is non-perimeter-based defence,which has been emerging as a promising revolution in the cyber security field.It can be used to continuously maintain security by safeguarding against attacks both from inside and outside of the network system.However,ZTA automation and orchestration,towards seamless deployment on real-world networks,has been limited to be reviewed in the existing literature.In this pa-per,we first identify the bottlenecks,discuss the background of ZTA and compare it with traditional perimeter-based security architec-tures.More importantly,we provide an in-depth analysis of state-of-the-art AI techniques that have the potential in the automation and orchestration of ZTA.Overall,in this review paper,we develop a foundational view on the challenges and potential enablers for the automation and orchestration of ZTA.

原文链接:

NETL
NSTL
万方数据

Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data

Yu-Cheng ChouBowen LiDeng-Ping FanAlan Yuille...

318-330页

查看更多>>摘要：Creating large-scale and well-annotated datasets to train AI algorithms is crucial for automated tumor detection and local-ization.However,with limited resources,it is challenging to determine the best type of annotations when annotating massive amounts of unlabeled data.To address this issue,we focus on polyps in colonoscopy videos and pancreatic tumors in abdominal CT scans;Both ap-plications require significant effort and time for pixel-wise annotation due to the high dimensional nature of the data,involving either temporary or spatial dimensions.In this paper,we develop a new annotation strategy,termed Drag&Drop,which simplifies the annota-tion process to drag and drop.This annotation strategy is more efficient,particularly for temporal and volumetric imaging,than other types of weak annotations,such as per-pixel,bounding boxes,scribbles,ellipses and points.Furthermore,to exploit our Drag&Drop an-notations,we develop a novel weakly supervised learning method based on the watershed algorithm.Experimental results show that our method achieves better detection and localization performance than alternative weak annotations and,more importantly,achieves sim-ilar performance to that trained on detailed per-pixel annotations.Interestingly,we find that,with limited resources,allocating weak an-notations from a diverse patient population can foster models more robust to unseen images than allocating per-pixel annotations for a small set of images.In summary,this research proposes an efficient annotation strategy for tumor detection and localization that is less accurate than per-pixel annotations but useful for creating large-scale datasets for screening tumors in various medical modalities.Project Page:https://github.com/johnson111788/Drag-Drop.

原文链接:

NETL
NSTL
万方数据

Adaptively Enhancing Facial Expression Crucial Regions via a Local Non-local Joint Network

Guanghui ShiShasha MaoShuiping GouDandan Yan...

331-348页

查看更多>>摘要：Facial expression recognition(FER)is still challenging due to the small interclass discrepancy in facial expression data.In view of the significance of facial crucial regions for FER,many existing studies utilize the prior information from some annotated crucial points to improve the performance of FER.However,it is complicated and time-consuming to manually annotate facial crucial points,especially for vast wild expression images.Based on this,a local non-local joint network is proposed to adaptively enhance the facial cru-cial regions in feature learning of FER in this paper.In the proposed method,two parts are constructed based on facial local and non-loc-al information,where an ensemble of multiple local networks is proposed to extract local features corresponding to multiple facial local regions and a non-local attention network is addressed to explore the significance of each local region.In particular,the attention weights obtained by the non-local network are fed into the local part to achieve interactive feedback between the facial global and local information.Interestingly,the non-local weights corresponding to local regions are gradually updated and higher weights are given to more crucial regions.Moreover,U-Net is employed to extract the integrated features of deep semantic information and low hierarchical detail information of expression images.Finally,experimental results illustrate that the proposed method achieves more competitive performance than several state-of-the-art methods on five benchmark datasets.

原文链接:

NETL
NSTL
万方数据

Enhancing Multi-agent Coordination via Dual-channel Consensus

Qingyang ZhangKaishen WangJingqing RuanYiming Yang...

349-368页

查看更多>>摘要：Successful coordination in multi-agent systems requires agents to achieve consensus.Previous works propose methods through information sharing,such as explicit information sharing via communication protocols or exchanging information implicitly via behavior prediction.However,these methods may fail in the absence of communication channels or due to biased modeling.In this work,we propose to develop dual-channel consensus(DuCC)via contrastive representation learning for fully cooperative multi-agent systems,which does not need explicit communication and avoids biased modeling.DuCC comprises two types of consensus:temporally extended consensus within each agent(inner-agent consensus)and mutual consensus across agents(inter-agent consensus).To achieve DuCC,we design two objectives to learn representations of slow environmental features for inner-agent consensus and to realize cognitive consist-ency as inter-agent consensus.Our DuCC is highly general and can be flexibly combined with various MARL algorithms.The extensive experiments on StarCraft multi-agent challenge and Google research football demonstrate that our method efficiently reaches consensus and performs superiorly to state-of-the-art MARL algorithms.

原文链接:

NETL
NSTL
万方数据