重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问http://arxivdaily.com每日更新更及时。

cs.AI人工智能，共计73篇

【1】 TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving
标题：TransFser：模拟基于Transformer的传感器融合实现自动驾驶
链接：https://arxiv.org/abs/2205.15997
作者：Kashyap Chitta,Aditya Prakash,Bernhard Jaeger,Zehao Yu,Katrin Renz,Andreas Geiger
备注：arXiv admin note: text overlap with arXiv:2104.09224

【2】 You Can't Count on Luck: Why Decision Transformers Fail in Stochastic Environments
标题：你不能指望运气：为什么决策Transformer在随机环境中失败
链接：https://arxiv.org/abs/2205.15967
作者：Keiran Paster,Sheila McIlraith,Jimmy Ba
机构：Department of Computer Science, University of Toronto, Vector Institute

【3】 Knowledge Graph -- Deep Learning: A Case Study in Question Answering in Aviation Safety Domain
标题：知识图谱--深度学习--以航空安全领域答疑为例
链接：https://arxiv.org/abs/2205.15952
作者：Ankush Agarwal,Raj Gite,Shreya Laddha,Pushpak Bhattacharyya,Satyanarayan Kar,Asif Ekbal,Prabhjit Thind,Rajesh Zele,Ravi Shankar
机构：IIT Bombay,Honeywell,IIT Patna

【4】 Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learning
标题：深度学习中基于自我注意和软标记的二维量子材料识别
链接：https://arxiv.org/abs/2205.15948
作者：Xuan Bac Nguyen,Apoorva Bisht,Hugh Churchill,Khoa Luu
机构： Department of CSCE, University of Arkansas, Fayetteville, AR, USA, Department of Physics, University of Arkansas, Fayetteville, AR, USA

【5】 Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems
标题：捉迷藏：关于深度学习系统攻击的隐蔽性
链接：https://arxiv.org/abs/2205.15944
作者：Zeyan Liu,Fengjun Li,Jingqiang Lin,Zhu Li,Bo Luo
机构： and Bo Luo 1 1 University of Kansas, edu 2 University of Science and Technology of China, cn 3 University of Missouri–Kansas City

【6】 A Competitive Method for Dog Nose-print Re-identification
标题：一种竞争性的犬鼻纹重新识别方法
链接：https://arxiv.org/abs/2205.15934
作者：Fei Shen,Zhe Wang,Zijun Wang,Xiaode Fu,Jiayi Chen,Xiaoyu Du
机构： Nanjing University of Science and Technology, DeepBlue Technology Co.,Ltd, Guangdong University of Technology
备注：Technique report of 3rd solution to 2022 Pet Biometric Challenge (CVPRW)

【7】 Uzbek Sentiment Analysis based on local Restaurant Reviews
标题：基于当地餐馆评论的乌兹别克人情绪分析
链接：https://arxiv.org/abs/2205.15930
作者：Sanatbek Matlatipov,Hulkar Rahimboeva,Jaloliddin Rajabov,Elmurod Kuriyozov
机构：National University of Uzbekistan named after Mirzo Ulugbek, Universitet St, Tashkent, Uzbekistan, Universidade da Corua, CITIC, Grupo LYS, Depto. de Computación y Tecnologías de la Información, Facultade de, Informática, Campus de Elvia, A Corua , Spain
备注：The International Conference on Agglutinative Language Technologies as a challenge of Natural Language Processing (ALTNLP) 2022, Koper, Slovenia

【8】 Enhanced Teaching-Learning-based Optimization for 3D Path Planning of Multicopter UAVs
标题：基于增强型教学的多无人机三维航迹规划优化
链接：https://arxiv.org/abs/2205.15913
作者：Van Truong Hoang,Manh Duong Phung
机构： Naval Academy, Viet Nam, University of Technology Sydney (UTS), Australia
备注：None

【9】 VQ-AR: Vector Quantized Autoregressive Probabilistic Time Series Forecasting
标题：VQ-AR：矢量量化自回归概率时间序列预测
链接：https://arxiv.org/abs/2205.15894
作者：Kashif Rasul,Young-Jin Park,Max Nihlén Ramstrm,Kyung-Min Kim
机构：NAVER CLOVA & NAVER AI Lab

【10】 Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games
标题：单纯形神经种群学习：对称零和对策中的任意混合贝叶斯最优性
链接：https://arxiv.org/abs/2205.15879
作者：Siqi Liu,Marc Lanctot,Luke Marris,Nicolas Heess
机构： search-ing the entire policy space quickly becomes intractable for 1University College London

【11】 FaIRCoP: Facial Image Retrieval using Contrastive Personalization
标题：FaIRCoP：基于对比个性化的人脸图像检索
链接：https://arxiv.org/abs/2205.15870
作者：Devansh Gupta,Aditya Saini,Drishti Bhasin,Sarthak Bhagat,Shagun Uppal,Rishi Raj Jain,Ponnurangam Kumaraguru,Rajiv Ratn Shah
机构：Indraprastha Institute of Information, Technology, Delhi, Indian Institute of Technology, Roorkee, International Institute of Information, Technology, Hyderabad

【12】 3D-model ShapeNet Core Classification using Meta-Semantic Learning
标题：基于元语义学习的3D模型ShapeNet核心分类
链接：https://arxiv.org/abs/2205.15869
作者：Farid Ghareh Mohammadi,Cheng Chen,Farzan Shenavarmasouleh,M. Hadi Amini,Beshoy Morkos,Hamid R. Arabnia
机构：Department of Computer Science, University of Georgia, Athens, GA, USA, Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, USA
备注：The 6th International Conference on Applied Cognitive Computing

【13】 Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware
标题：盲文字母阅读：神经形态硬件时空模式识别的基准
链接：https://arxiv.org/abs/2205.15864
作者：Simon F Muller-Cleve,Vittorio Fra,Lyes Khacef,Alejandro Pequeno-Zurro,Daniel Klepatsch,Evelina Forno,Diego G Ivanovich,Shavika Rastogi,Gianvito Urgese,Friedemann Zenke,Chiara Bartolozzi
机构：Istituto Italiano di Tecnologia, Event-driven perception in robotics, Genoa, Italy,Politecnico di Torino, EDA, Group, Torino, Italy,Bio-Inspired Circuits and Systems Lab, Zernike Institute for Advanced Materials
备注：20 pages, submitted to Frontiers in Neuroscience - Neuromorphic Engineering

【14】 Justifying Social-Choice Mechanism Outcome for Improving Participant Satisfaction
标题：提高参与者满意度的社会选择机制结果正当化
链接：https://arxiv.org/abs/2205.15863
作者：Sharadhi Alape Suryanarayana,David Sarne,Sarit Kraus
机构：Bar-Ilan University, Israel
备注：None

【15】 Snapture -- A Novel Neural Architecture for Combined Static and Dynamic Hand Gesture Recognition
标题：Snapture--一种结合静态和动态手势识别的新型神经结构
链接：https://arxiv.org/abs/2205.15862
作者：Hassan Ali,Doreen Jirak,Stefan Wermter
机构：Wermter, Received: date Accepted: date

【16】 Robust Anytime Learning of Markov Decision Processes
标题：马尔可夫决策过程的稳健随时学习
链接：https://arxiv.org/abs/2205.15827
作者：Marnix Suilen,Thiago D. Simo,Nils Jansen,David Parker
机构：Department of Software Science, Radboud University, Nijmegen, The Netherlands, School of Computer Science, University of Birmingham, Birmingham, United Kingdom

【17】 Unsupervised Image Representation Learning with Deep Latent Particles
标题：基于深度隐含粒子的无监督图像表示学习
链接：https://arxiv.org/abs/2205.15821
作者：TalDaniel,Aviv Tamar
机构： contrast the position 1Department of Electrical and Computer Engineering, Technion- Israel Institute of Technology
备注：ICML 2022. Project webpage and code: this https URL

【18】 GateNLP-UShef at SemEval-2022 Task 8: Entity-Enriched Siamese Transformer for Multilingual News Article Similarity
标题：GateNLP-UShef在SemEval-2022年任务8：多语言新闻文章相似度的实体丰富暹罗转换器
链接：https://arxiv.org/abs/2205.15812
作者：Iknoor Singh,Yue Li,Melissa Thong,Carolina Scarton
机构：Department of Computer Science, University of Sheffield (UK)
备注：SemEval-2022 Task 8: Multilingual News Article Similarity (co-located with NAACL 2022)

【19】 A Survey of Deep Fake Detection for Trial Courts
标题：浅谈庭审中的深度假冒检测
链接：https://arxiv.org/abs/2205.15792
作者：Naciye Celebi,Qingzhong Liu,Muhammed Karatoprak
机构：Department of Computer Science, Sam Houston State University, Huntsville, TX, USA, Department LLM in US Law, The University. Of Houston, Houston, TX, USA
备注：12 Pages, 1 Table

【20】 Knowledge Enhanced Neural Networks for relational domains
标题：关系域中的知识增强型神经网络
链接：https://arxiv.org/abs/2205.15762
作者：Alessandro Daniele,Luciano Serafini
机构：Data and Knowledge Managemen Research Unit, Fondazione Bruno Kessler, Trento, Italy
备注：arXiv admin note: text overlap with arXiv:2009.06087

【21】 Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark
标题：研究图像检索在视觉定位中的作用--一个详尽的基准
链接：https://arxiv.org/abs/2205.15761
作者：Martin Humenberger,Yohann Cabon,Noé Pion,Philippe Weinzaepfel,Donghwan Lee,Nicolas Guérin,Torsten Sattler,Gabriela Csurka
机构：Noe Pion, Nicolas Guerin, NAVER LABS Europe, France, NAVER LABS, Republic of Korea, Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, The work has been done during an appointment at NAVER LABS Europe.
备注：International Journal of Computer Vision (2022). arXiv admin note: text overlap with arXiv:2011.11946

【22】 Hierarchically Constrained Adaptive Ad Exposure in Feeds
标题：提要中分层约束的自适应广告曝光
链接：https://arxiv.org/abs/2205.15759
作者：Dagui Chen,Qi Yan,Chunjie Chen,Zhenzhe Zheng,Yangsu Liu,Zhenjia Ma,Chuan Yu,Jian Xu,Bo Zheng
机构：Alibaba Group,Shanghai Jiao Tong University

【23】 Hierarchies of Reward Machines
标题：奖励机的层次结构
链接：https://arxiv.org/abs/2205.15752
作者：Daniel Furelos-Blanco,Mark Law,Anders Jonsson,Krysia Broda,Alessandra Russo
机构：Imperial College London, ILASP Limited, Universitat Pompeu Fabra

【24】 Variable importance without impossible data
标题：没有不可能的数据的可变重要性
链接：https://arxiv.org/abs/2205.15750
作者：Masayoshi Mase,Art B. Owen,Benjamin B. Seiler
机构：Hitachi, Ltd., Stanford University

【25】 Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
标题：用于自监督图表示学习的全粒度自我语义传播
链接：https://arxiv.org/abs/2205.15746
作者：Ling Yang,Shenda Hong
机构： 1National Institute of Health Data Science, China 2Institute of Medical Technology, Health ScienceCenter of Peking University
备注：Accepted by ICML 2022

【26】 HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks
标题：HyperMAML：深度模型与超网络的Few-Shot适配
链接：https://arxiv.org/abs/2205.15745
作者：M. Przewilikowski,P. Przybysz,J. Tabor,M. Ziba,P. Spurek
机构：Jagiellonian University, Kraków, Poland

【27】 Mixture GAN For Modulation Classification Resiliency Against Adversarial Attacks
标题：混合遗传算法在调制分类抗攻击中的应用
链接：https://arxiv.org/abs/2205.15743
作者：Eyad Shtaiwi,Ahmed El Ouadrhiri,Majid Moradikia,Salma Sultana,Ahmed Abdelhadi,Zhu Han
机构：Electrical and Computer Engineering Department, University of Houston, Houston, TX, USA., Department of Engineering Technology, University of Houston, Houston, TX, USA.

【28】 Multi-Agent Learning of Numerical Methods for Hyperbolic PDEs with Factored Dec-MDP
标题：DEC-MDP分解的双曲型偏微分方程组数值方法的多智能体学习
链接：https://arxiv.org/abs/2205.15716
作者：Yiwei Fu,Dheeraj S. K. Kapilavai,Elliot Way
机构：com 2 Binghamton University
备注：Submitted to 20th International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS 2022)

【29】 Attribute Exploration with Multiple Contradicting Partial Experts
标题：多个相互矛盾的部分专家的属性探索
链接：https://arxiv.org/abs/2205.15714
作者：Maximilian Felde,Gerd Stumme
机构： Knowledge & Data Engineering Group, University of Kassel, Germany, Interdisciplinary Research Center for Information System Design
备注：22 pages (14 pages + 8 pages appendix)

【30】 Provable General Function Class Representation Learning in Multitask Bandits and MDPs
标题：多任务Bitts和MDP中可证明的一般函数类表示学习
链接：https://arxiv.org/abs/2205.15701
作者：Rui Lu,Andrew Zhao,Simon S. Du,Gao Huang
机构：Department of Automation, BNRist, Tsinghua University, Paul G. Allen School of Computer Science and Engineering, University of Washington

【31】 An Informational Space Based Semantic Analysis for Scientific Texts
标题：一种基于信息空间的科技文本语义分析
链接：https://arxiv.org/abs/2205.15696
作者：Neslihan Suzen,Alexander N. Gorban,Jeremy Levesley,Evgeny M. Mirkes
机构：School of Computing and Mathematical Sciences, University of Leicester, Leicester, UK
备注：None

【32】 Fast-Spanning Ant Colony Optimisation (FaSACO) for Mobile Robot Coverage Path Planning
标题：移动机器人覆盖路径规划的快速生成蚁群算法
链接：https://arxiv.org/abs/2205.15691
作者：Christopher Carr,Peng Wang
机构：Department of Computing and Mathematics, Manchester Metropolitan University, Manchester, UK
备注：6 pages

【33】 Self-Supervised Learning for Building Damage Assessment from Large-scale xBD Satellite Imagery Benchmark Datasets
标题：基于大比例尺XBD卫星影像基准数据集的自监督学习
链接：https://arxiv.org/abs/2205.15688
作者：Zaishuo Xia,Zelin Li,Yanbing Bai,Jinze Yu,Bruno Adriano
机构： Center for Applied Statistics, School of Statistics, Renmin University of China, Department of Artificial Intelligent, Connected Robotics Inc., Japan, RIKEN Center for Advanced Intelligence Project (AIP), Japan
备注：14 pages, 7 figures, DEXA 2022

【34】 Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solvers
标题：为什么NLP模特在初等数学上笨手笨脚？基于深度学习的应用题解算器研究综述
链接：https://arxiv.org/abs/2205.15683
作者：Sowmya S Sundaram,Sairam Gurajada,Marco Fisichella,Deepak P,Savitha Sam Abraham
机构：L,S Research Center, Hannover, Germany, IBM Research, Almaden, USA, Queen’s University, Belfast, UK, University of rebro, Sweden

【35】 Automatic Relation-aware Graph Network Proliferation
标题：自动关系感知图网络扩散
链接：https://arxiv.org/abs/2205.15678
作者：Shaofei Cai,Liang Li,Xinzhe Han,Jiebo Luo,Zheng-Jun Zha,Qingming Huang
机构：Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS, Beijing, China, University of Chinese Academy of Sciences, Beijing, China,University of Rochester, University of Science and Technology of China, China,Peng Cheng Laboratory, Shenzhen, China
备注：Accepted by CVPR2022 (Oral)

【36】 Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
标题：用于数据高效GAN训练的增强感知自我监控
链接：https://arxiv.org/abs/2205.15677
作者：Liang Hou,Qi Cao,Huawei Shen,Siyuan Pan,Xiaoshuang Li,Xueqi Cheng

【37】 Generalised Implicit Neural Representations
标题：广义隐式神经表示法
链接：https://arxiv.org/abs/2205.15674
作者：Daniele Grattarola,Pierre Vandergheynst
机构：EPFL

【38】 Multi-task Optimization Based Co-training for Electricity Consumption Prediction
标题：基于多任务优化的联合训练用电量预测
链接：https://arxiv.org/abs/2205.15663
作者：Hui Song,A. K. Qin,Chenggang Yan
机构：School of Engineering, RMIT University, Melbourne, Australia, Department of Computing Technologies, Swinburne University of Technology, Hawthorn, Australia, School of Automation, Hangzhou Dianzi University, Hangzhou, China
备注：accepted by the 2022 IEEE International Joint Conference on Neural Networks (IJCNN 2022)

【39】 Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
标题：Meta-Ticket：在随机初始化的神经网络中寻找最优子网络进行少机会学习
链接：https://arxiv.org/abs/2205.15619
作者：Daiki Chijiwa,Shin'ya Yamaguchi,Atsutoshi Kumagai,Yasutoshi Ida
机构：Shin’ya Yamaguchi, NTT Computer and Data Science Laboratories, NTT Corporation, Kyoto University
备注：Code will be available at this https URL

【40】 Communication-Efficient Distributionally Robust Decentralized Learning
标题：通信高效的分布式稳健分散学习
链接：https://arxiv.org/abs/2205.15614
作者：Matteo Zecchin,Marios Kountouris,David Gesbert
备注：Manuscript submitted for publication

【41】 Weakly-supervised Action Transition Learning for Stochastic Huma Motion Prediction
标题：用于随机人体运动预测的弱监督动作转移学习
链接：https://arxiv.org/abs/2205.15608
作者：Wei Mao,Miaomiao Liu,Mathieu Salzmann
机构：Australian National University; ,CVLab, EPFL; ,ClearSpace, Switzerland, Drink, Pass
备注：CVPR2022 (Oral)

【42】 Individual health-disease phase diagrams for disease prevention based on machine learning
标题：基于机器学习的疾病预防个体健康-疾病相图
链接：https://arxiv.org/abs/2205.15598
作者：Kazuki Nakamura,Eiichiro Uchino,Noriaki Sato,Ayano Araki,Kei Terayama,Ryosuke Kojima,Koichi Murashita,Ken Itoh,Tatsuya Mikami,Yoshinori Tamada,Yasushi Okuno
机构： Department of Biomedical Data Intelligence, Graduate School of Medicine, Kyoto University, Kyoto,-, Japan., Research and Business Development Department, Kyowa Hakko Bio Co., Ltd., Tokyo,-, Japan.

【43】 Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling
标题：基于提升自适应小波的分层球形CNN的池化和解池化
链接：https://arxiv.org/abs/2205.15571
作者：Mingxing Xu,Chenglin Li,Wenrui Dai,Siheng Chen,Junni Zou,Pascal Frossard,Hongkai Xiong
机构：Shanghai Jiao Tong University, cole Polytechnique Fédérale de Lausanne (EPFL)

【44】 GSR: A Generalized Symbolic Regression Approach
标题：GSR：广义符号回归方法
链接：https://arxiv.org/abs/2205.15569
作者：Tony Tohme,Dehong Liu,Kamal Youcef-Toumi
机构：Massachusetts Institute of Technology, Mitsubishi Electric Research Laboratories

【45】 Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Model
标题：基于多语言模型的语言解缠提炼低资源无监督翻译
链接：https://arxiv.org/abs/2205.15544
作者：Xuan-Phi Nguyen,Shafiq Joty,Wu Kui,Ai Ti Aw
机构：Nanyang Technological University, Salesforce Research, Institute for Infocomm Research (I,R), ASTAR, Singapore

【46】 MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation
标题：MACE：一种有效的模型不可知性反事实解释框架
链接：https://arxiv.org/abs/2205.15540
作者：Wenzhuo Yang,Jia Li,Caiming Xiong,Steven C. H. Hoi
机构：Salesforce Research
备注：9 pages, 2 figures

【47】 Gluing Neural Networks Symbolically Through Hyperdimensional Computing
标题：通过超维计算符号化地粘合神经网络
链接：https://arxiv.org/abs/2205.15534
作者：Peter Sutor,Dehao Yuan,Douglas Summers-Stay,Cornelia Fermuller,Yiannis Aloimonos
机构：Department of Computer Science, University of Maryland, College Park, Maryland, USA, Comp. and Info. Sciences Directorate, CCDC Army Research Laboratory, Adelphi, Maryland, USA, Cornelia Ferm¨uller
备注：10 pages, 3 figures, 6 tables, accepted to IJCNN 2022 / IEEE WCCI 2022

【48】 Variational Transfer Learning using Cross-Domain Latent Modulation
标题：基于跨域潜伏调制的变分转移学习
链接：https://arxiv.org/abs/2205.15523
作者：Jinyong Hou,Jeremiah D. Deng,Stephen Cranefield,Xuejie Din
机构：Department of Information Science, University of Otago, Clyde Street, Dunedin, New Zealand
备注：Under review. arXiv admin note: substantial text overlap with arXiv:2012.11727

【49】 A Unified Framework for Emotion Identification and Generation in Dialogues
标题：对话中情感识别与生成的统一框架
链接：https://arxiv.org/abs/2205.15513
作者：Avinash Madasu,Mauajama Firdaus,Asif Eqbal
机构：Asif Ekbal, Department of Computer Science and Engineering, Indian Institute of Technology Patna, India

【50】 ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
标题：适应：视觉-语言导航和与通道对齐的动作提示
链接：https://arxiv.org/abs/2205.15509
作者：Bingqian Lin,Yi Zhu,Zicong Chen,Xiwen Liang,Jianzhuang Liu,Xiaodan Liang
机构：Shenzhen Campus of Sun Yat-sen University ,Huawei Noah’s Ark Lab
备注：Accepted to CVPR 2022

【51】 Leveraging Pre-Trained Language Models to Streamline Natural Language Interaction for Self-Tracking
标题：利用预先训练的语言模型简化自然语言交互以进行自我跟踪
链接：https://arxiv.org/abs/2205.15503
作者：Young-Ho Kim,Sungdong Kim,Minsuk Chang,Sang-Woo Lee
机构：NAVER AI Lab, NAVER CLOVA, Google Research, Exercise tracker (User’s DB), Natural Language Prom, pt, Represented as ,-shot learning, Sorted Sam, ples, Nearest, Farthest, Synthetic sam, ple store, Sim, ilarity, Sorting, GPT-, Sleep, Type, Repetitions Intensity, Phrase, Bench press |
备注：Accepted to NAACL '22 2nd Workshop on Bridging Human-Computer Interaction and Natural Language Processing. 10 pages including appendix, 2 figures, and 1 table

【52】 Post-hoc Concept Bottleneck Models
标题：后自组织概念瓶颈模型
链接：htts://arxiv.org/abs/2205.15480
作者：Mert Yuksekgonul,Maggie Wang,James Zou
机构：Stanford University
备注：An earlier version was published in the ICLR 2022 PAIR2Struct Workshop

【53】 Learning to Represent Programs with Code Hierarchies
标题：学习用代码层次结构表示程序
链接：https://arxiv.org/abs/2205.15479
作者：Minh Nguyen,Nghi D. Q. Bui
机构：Ho Chi Minh City University of Technology, && FSoft AI Lab, School of Information Systems, Singapore Management University

【54】 Introduction of a tree-based technique for efficient and real-time label retrieval in the object tracking system
标题：在目标跟踪系统中引入一种基于树的高效和实时的标签检索技术
链接：https://arxiv.org/abs/2205.15477
作者：Ala-Eddine Benrazek,Zineddine Kouahla,Brahim Farou,Hamid Seridi,Imane Allele
机构：Department of Computer Science, Ziane Achour University, Djelfa, Algeria., Guelma, Algeria., Labstic Laboratory, Guelma, Corresponding author(s). E-mail(s):
备注：29 pages, 15 figures, 6 tables

【55】 A Unifying Framework for Causal Explanation of Sequential Decision Making
标题：序贯决策因果解释的统一框架
链接：https://arxiv.org/abs/2205.15462
作者：Samer B. Nashed,Saaduddin Mahmud,Claudia V. Goldman,Shlomo Zilberstein
机构：University of Massachusetts Amherst, General Motors
备注：9 pages, 4 figures, conference

【56】 GLDQN: Explicitly Parameterized Quantile Reinforcement Learning for Waste Reduction
标题：GLDQN：用于减少浪费的显式参数分位数强化学习
链接：https://arxiv.org/abs/2205.15455
作者：Sami Jullien,Mozhdeh Ariannezhad,Paul Groth,Maarten de Rijke
机构：AI for Retail Lab, University of Amsterdam, Amsterdam, The Netherlands
备注：10 pages, 1 figure, 2 tables

【57】 HeatER: An Efficient and Unified Network for Human Reconstruction via Heatmap-based TransformER
标题：HEARTER：一种基于热图变换的高效统一人体重建网络
链接：https://arxiv.org/abs/2205.15448
作者：Ce Zheng,Matias Mendieta,Taojiannan Yang,Chen Chen
机构：Center for Research in Computer Vision, University of Central Florida

【58】 Learning Risk-Averse Equilibria in Multi-Agent Systems
标题：学习多智能体系统中的风险厌恶均衡
链接：https://arxiv.org/abs/2205.15434
作者：Oliver Slumbers,David Henry Mguni,Stephen McAleer,Jun Wang,Yaodong Yang
机构：University College London, Huawei U.K., Carnegie Mellon University, Institute for AI, Peking University

【59】 A portfolio-based analysis method for competition results
标题：一种基于投资组合的竞赛成绩分析方法
链接：https://arxiv.org/abs/2205.15414
作者：Nguyen Dang
机构：University of St Andrews, United Kingdom
备注：10 pages

【60】 Painful intelligence: What AI can tell us about human suffering
标题：痛苦的情报：人工智能能告诉我们什么关于人类苦难
链接：https://arxiv.org/abs/2205.15409
作者：Aapo Hyvrinen
机构：University of Helsinki, Version ,.
备注：Book with 231 pages

【61】 Designing Rewards for Fast Learning
标题：为快速学习设计奖励
链接：https://arxiv.org/abs/2205.15400
作者：Henry Sowerby,Zhiyuan Zhou,Michael L. Littman
机构：Department of Computer Science, Brown University, Providence, RI
备注：To appear at the 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2022)

【62】 Truly Deterministic Policy Optimization
标题：真正确定的策略优化
链接：https://arxiv.org/abs/2205.15379
作者：Ehsan Saleh,Saba Ghaffari,Timothy Bretl,Matthew West
机构：Department of Computer Science, Department of Aerospace Engineering, Department of Mechanical Science and Engineering, University of Illinois Urbana-Champaign

【63】 Reinforcement Learning with a Terminator
标题：带终结器的强化学习
链接：https://arxiv.org/abs/2205.15376
作者：Guy Tennenholtz,Nadav Merlis,Lior Shani,Shie Mannor,Uri Shalit,Gal Chechik,Assaf Hallak,Gal Dalal
机构： Israel institute of technologyNvidia Research, IsraelBar Ilan University

【64】 Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data
标题：Guided-TTS 2：一种高质量非转录数据自适应文语转换扩散模型
链接：https://arxiv.org/abs/2205.15370
作者：Sungwon Kim,Heeseung Kim,Sungroh Yoon
机构：Data Science & AI Lab., seoul National University

【65】 Non-Markovian Reward Mdelling from Trajectory Labels via Interpretable Multiple Instance Learning
标题：基于可解释多实例学习的轨迹标签非马尔可夫奖励建模
链接：https://arxiv.org/abs/2205.15367
作者：Joseph Early,Tom Bewley,Christine Evers,Sarvapali Ramchurn
备注：20 pages (9 main content; 2 references; 9 appendix). 11 figures (8 main content; 3 appendix)

【66】 Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training
标题：多张票叠加成一张：稀疏神经网络训练的性能助推器
链接：https://arxiv.org/abs/2205.15322
作者：Lu Yin,Vlado Menkovski,Meng Fang,Tianjin Huang,Yulong Pei,Mykola Pechenizkiy,Decebal Constantin Mocanu,Shiwei Liu
机构：Eindhoven University of Technology , Eindhoven, the Netherlands, University of Twente, Enschede, the Netherlands
备注：17 pages, 5 figures, accepted by the 38th Conference on Uncertainty in Artificial Intelligence (UAI)

【67】 Learning Adaptive Propagation for Knowledge Graph Reasoning
标题：用于知识图推理的学习自适应传播算法
链接：https://arxiv.org/abs/2205.15319
作者：Yongqi Zhang,Zhanke Zhou,Quanming Yao,Xiaowen Chu,Bo Han
机构：Paradigm Inc., Beijing, China, Department of Computer Science, Hong Kong Baptist University, Hong Kong, China, Department of Electronic Engineering, Tsinghua University, Beijing, China, Data Science and Analytics Thrust, HKUST (Guangzhou), Guangzhou, China
备注：under review

【68】 Chefs' Random Tables: Non-Trigonometric Random Features
标题：厨师随机表：非三角随机特征
链接：https://arxiv.org/abs/2205.15317
作者：Valerii Likhosherstov,Krzysztof Choromanski,Avinava Dubey,Frederick Liu,Tamas Sarlos,Adrian Weller
机构：Google Research & Columbia University, University of Cambridge &, The Alan Turing Institute

【69】 Mean Field inference of CRFs based on GAT
标题：基于GAT的CRF平均场推断
链接：https://arxiv.org/abs/2205.15312
作者：LingHong Xing,XiangXiang Ma,GuangSheng Luo
机构： Shanghai in China 3School of Electronic and Electrical Engineering, Shanghai University Of Engineering Science

【70】 Parameter-Efficient and Student-Friendly Knowledge Distillation
标题：参数高效和学生友好的知识精馏
链接：https://arxiv.org/abs/2205.15308
作者：Jun Rao,Xv Meng,Liang Ding,Shuhan Qi,Dacheng Tao
机构：Harbin Institute of Technology, Shenzhen, JD Explore Academy, Peng Cheng Laboratory

【71】 A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks
标题：一种统一的端卷积神经网络权值初始化模型
链接：https://arxiv.org/abs/2205.15307
作者：Yu Pan,Zeyong Su,Ao Liu,Jingquan Wang,Nannan Li,Zenglin Xu
机构： 3 Tokyo Institute of Technology, Institute of Automation
备注：Accepted in ICML 2022

【72】 Feature Learning in $L_{2}$-regularized DNNs: Attraction/Repulsion and Sparsity
标题：$L_{2}$正则DNN的特征学习：吸引/排斥和稀疏性
链接：https://arxiv.org/abs/2205.15809
作者：Arthur Jacot,Eugene Golikov,Clément Hongler,Franck Gabriel
机构：Chair of Statistical Field Theory, cole Polytechnique Fédérale de Lausanne

【73】 Robust Projection based Anomaly Extraction (RPE) in Univariate Time-Series
标题：基于稳健投影的单变量时间序列异常提取
链接：https://arxiv.org/abs/2205.15548
作者：Mostafa Rahmani,Anoop Deoras,Laurent Callot

机器翻译，仅供参考

重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问http://arxivdaily.com每日更新更及时。