|
|
历史文章列表 网站https://www.arxivdaily.com/
注：含中英文摘要速递见公众号【arXiv每日学术速递】,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。 cs.AI人工智能，共计53篇
【1】 FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization
标题：FedFOR：一阶正则化的无状态异质联邦学习
链接：https://arxiv.org/abs/2209.10537
作者：Junjiao Tian,James Seale Smith,Zsolt Kira
机构：Georgia Institute of Technology
【2】 Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces
标题：基于客户数据子空间主角的集群联合学习中高效的分布相似性识别
链接：https://arxiv.org/abs/2209.10526
作者：Saeed Vahidian,Mahdi Morafah,Weijia Wang,Vyacheslav Kungurtsev,Chen Chen,Mubarak Shah,Bill Lin
机构：UC San Diego, Czech Technical University, UCF
【3】 Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
标题：摘要程序：基于神经模块树的可解释抽象摘要
链接：https://arxiv.org/abs/2209.10492
作者：Swarnadeep Saha,Shiyue Zhang,Peter Hase,Mohit Bansal
机构：Department of Computer Science, University of North Carolina at Chapel Hill
备注：24 pages (10 figures, 7 tables)
【4】 Towards a Standardised Performance Evaluation Protocol for Cooperative MARL
标题：一种标准化的协作Marl性能评估协议
链接：https://arxiv.org/abs/2209.10485
作者：Rihab Gorsane,Omayma Mahjoub,Ruan de Kock,Roland Dubb,Siddarth Singh,Arnu Pretorius
机构：InstaDeep, National School of Computer Science, Tunisia, University of Cape Town, South Africa
备注：Published at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). Website: see this https URL . 43 Pages, 21 Figures, 8 Tables
【5】 Hierarchical Decision Transformer
标题：分层决策转换器
链接：https://arxiv.org/abs/2209.10447
作者：André Correia,Luís A. Alexandre
机构：NOVA LINCS, Universidade da Beira Interior, Covilhã, Portugal
【6】 Off-Policy Risk Assessment in Markov Decision Processes
标题：马尔可夫决策过程中的非政策风险评估
链接：https://arxiv.org/abs/2209.10444
作者：Audrey Huang,Liu Leqi,Zachary Chase Lipton,Kamyar Azizzadenesheli
机构：Department of Computer Science, University of Illinois Urbana-Champaign, Machine Learning Department, Carnegie Mellon University, Department of Computer Science, Purdue University
【7】 Partial Information Decomposition Reveals the Structure of Neural Representations
标题：部分信息分解揭示了神经表示的结构
链接：https://arxiv.org/abs/2209.10438
作者：David A. Ehrlich,Andreas C. Schneider,Michael Wibral,Viola Priesemann,Abdullah Makkeh
机构：Goettingen Campus Institute for Dynamics of Biological Networks, Goettingen, Max Planck Institute for Dynamics and Self-Organization, Goettingen
备注：18 pages, 5 figures
【8】 Sar Ship Detection based on Swin Transformer and Feature Enhancement Feature Pyramid Network
标题：基于Swin变换和特征增强特征金字塔网络的SAR舰船检测
链接：https://arxiv.org/abs/2209.10421
作者：Xiao Ke,Xiaoling Zhang,Tianwen Zhang,Jun Shi,Shunjun Wei
机构：School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
【9】 An Information-Theoretic and Contrastive Learning-based Approach for Identifying Code Statements Causing Software Vulnerability
标题：一种基于信息论和对比学习的软件漏洞代码语句识别方法
链接：https://arxiv.org/abs/2209.10414
作者：Van Nguyen,Trung Le,Chakkrit Tantithamthavorn,John Grundy,Hung Nguyen,Seyit Camtepe,Paul Quirk,Dinh Phung
机构：Adelaide University, Australia, Monash University, Australia, CSIRO Data, Australia, Defence Science and Technology Group, Australia
【10】 Cross Project Software Vulnerability Detection via Domain Adaptation and Max-Margin Principle
标题：基于域自适应和最大裕度原理的跨项目软件漏洞检测
链接：https://arxiv.org/abs/2209.10406
作者：Van Nguyen,Trung Le,Chakkrit Tantithamthavorn,John Grundy,Hung Nguyen,Dinh Phung
机构：Adelaide University, Australia, Monash University, Australia
【11】 Incremental Updates of Generalized Hypertree Decompositions
标题：广义超树分解的增量更新
链接：https://arxiv.org/abs/2209.10375
作者：Georg Gottlob,Matthias Lanzinger,Davide Mario Longo,Cem Okulmus
机构： University of Oxford
【12】 WeLM: A Well-Read Pre-trained Language Model for Chinese
标题：WELM：一种精读的汉语预训练语言模型
链接：https://arxiv.org/abs/2209.10372
作者：Hui Su,Xiao Zhou,Houjing Yu,Yuwen Chen,Zilin Zhu,Yang Yu,Jie Zhou
机构：WeChat AI
【13】 Safety Metrics and Losses for Object Detection in Autonomous Driving
标题：自动驾驶中目标检测的安全度量和损失
链接：https://arxiv.org/abs/2209.10368
作者：Hsuan-Cheng Liao,Chih-Hong Cheng,Hasan Esen,Alois Knoll
机构：be accessible.
备注：Submitted to ICRA 2023
【14】 MulBot: Unsupervised Bot Detection Based on Multivariate Time Series
标题：MulBot：基于多变量时间序列的无监督机器人检测
链接：https://arxiv.org/abs/2209.10361
作者：Lorenzo Mannocci,Stefano Cresci,Anna Monreale,Athina Vakali,Maurizio Tesconi
机构： Institute for Informatics and Telematics, it]† Department of Computer Science, Aristotle University of Thessaloniki
【15】 Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
标题：动量对抗性蒸馏：在无数据知识蒸馏中处理大的分布变化
链接：https://arxiv.org/abs/2209.10359
作者：Kien Do,Hung Le,Dung Nguyen,Dang Nguyen,Haripriya Harikumar,Truyen Tran,Santu Rana,Svetha Venkatesh
机构：Applied Artificial Intelligence Institute (A,I,), Deakin University, Australia
备注：Accepted to NeurIPS 2022
【16】 Partially Observable Markov Decision Processes in Robotics: A Survey
标题：机器人学中的部分可观测马尔可夫决策过程：综述
链接：https://arxiv.org/abs/2209.10342
作者：Mikko Lauri,David Hsu,Joni Pajarinen
机构： Hsu is with the Department of Computer Science, National Universityof Singapore
备注：20 pages, 10 figures. Author version of paper. Accepted for publication in IEEE Transactions on Robotics
【17】 LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning
标题：LCRL：基于逻辑约束强化学习的认证策略合成
链接：https://arxiv.org/abs/2209.10341
作者：Hosein Hasanbeig,Daniel Kroening,Alessandro Abate
机构：Computer Science Department, University of Oxford, UK, Amazon Inc, London, UK
备注：Evaluated and Accepted by the 19th International Conference on Quantitative Evaluation of Systems 2022
【18】 Controller Synthesis for Timeline-based Games
标题：基于时间线游戏的控制器综合
链接：https://arxiv.org/abs/2209.10319
作者：Renato Acampora,Luca Geatti,Nicola Gigante,Angelo Montanari,Valentino Picotti
机构：University of Udine, Italy, Free University of Bozen-Bolzano, University of Southern Denmark
备注：None
【19】 Analyzing Robustness of Angluin's L* Algorithm in Presence of Noise
标题：安格鲁恩L*算法在噪声存在下的稳健性分析
链接：https://arxiv.org/abs/2209.10315
作者：Igor Khmelnitsky,Serge Haddad,Lina Ye,Benoît Barbot,Benedikt Bollig,Martin Leucker,Daniel Neider,Rajarshi Roy
机构：Université Paris-Saclay, INRIA, LMF, France, CentraleSupélec, LMF, France, Université Paris-Est Créteil, CNRS, ENS Paris-Saclay, LMF, France, Institute for Software Engineering and, Programming Languages, Universität zu Lübeck, Germany, Carl von Ossietzky
备注：None
【20】 Fast Few shot Self-attentive Semi-supervised Political Inclination Prediction
标题：快速、少射、自我关注、半监督的政治倾向预测
链接：https://arxiv.org/abs/2209.10292
作者：Souvic Chakraborty,Pawan Goyal,Animesh Mukherjee
机构：Indian Institute of Technology, Kharagpur, West Bengal, India
备注：Accepted to ICADL'22
【21】 Tree Methods for Hierarchical Classification in Parallel
标题：并行层次分类的树型方法
链接：https://arxiv.org/abs/2209.10288
作者：Franz A. Heinsen
备注：Source code and instructions for replicating our results are online at this https URL
【22】 Periodic Extrapolative Generalisation in Neural Networks
标题：神经网络中的周期外推推广
链接：https://arxiv.org/abs/2209.10280
作者：Peter Belcák,Roger Wattenhofer
机构：ETH Z¨urich, Z¨urich, Switzerland
备注：Accepted to IEEE Symposium on Deep Learning (IEEE DL) 2022, 8 pages, 7 figures
【23】 Dynamic Time-Alignment of Dimensional Annotations of Emotion using Recurrent Neural Networks
标题：基于递归神经网络的情感维度标注的动态时间对齐
链接：https://arxiv.org/abs/2209.10223
作者：Sina Alisamir,Fabien Ringeval,Francois Portet
机构：Atos & LIG, Grenoble, France, Grenoble INP, LIG, Univ. Grenoble Alpes, Inria, CNRS, François Portet
【24】 Fairness Reprogramming
标题：公平重新规划
链接：https://arxiv.org/abs/2209.10222
作者：Guanhua Zhang,Yihua Zhang,Yang Zhang,Wenqi Fan,Qing Li,Sijia Liu,Shiyu Chang
机构：UC Santa Barbara, Michigan State University, IBM Research, The Hong Kong Polytechnic University
【25】 Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning
标题：基于强化学习的前瞻性经济调度评估
链接：https://arxiv.org/abs/2209.10207
作者：Zekuan Yu,Guangchun Ruan,Xinyue Wang,Guanglun Zhang,Yiliu He,Haiwang Zhong
机构：Department of Electrical Engineering, Tsinghua University, Beijing , China, Sichuan Energy Internet Research Institute
备注：This paper has 6 pages and 2 figures. This paper has been accepted by 2022 IEEE Conference on Energy Internet and Energy System Integration (EI2 2022)
【26】 Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
标题：通过数据增强提高图异常检测模型的泛化能力
链接：https://arxiv.org/abs/2209.10168
作者：Shuang Zhou,Xiao Huang,Ninghao Liu,Fu-Lai Chung,Long-Kai Huang
机构：∗The Hong Kong Polytechnic University, †University of Georgia, ‡Tencent AI Lab
【27】 DDGHM: Dual Dynamic Graph with Hybrid Metric Training for Cross-Domain Sequential Recommendation
标题：DDGHM：支持跨域顺序推荐的混合度量训练对偶动态图
链接：https://arxiv.org/abs/2209.10163
作者：Xiaolin Zheng,Jiajie Su,Weiming Liu,Chaochao Chen
机构：College of Computer Science, Zhejiang University, Hangzhou, China
【28】 PePe: Personalized Post-editing Model utilizing User-generated Post-edits
标题：PEPE：利用用户生成的后期编辑的个性化后期编辑模型
链接：https://arxiv.org/abs/2209.10139
作者：Jihyeon Lee,Taehee Kim,Yunwon Tae,Cheonbok Park,Jaegul Choo
【29】 A Systematic Literature Review of Soft Computing Techniques for Software Maintainability Prediction: State-of-the-Art, Challenges and Future Directions
标题：用于软件维护性预测的软计算技术的系统文献综述：现状、挑战和未来方向
链接：https://arxiv.org/abs/2209.10131
作者：Gokul Yenduri,Thippa Reddy Gadekallu
机构：School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, Tamilnadu, India
备注：Submitted for peer review
【30】 A Comprehensive Survey on Trustworthy Recommender Systems
标题：值得信赖的推荐系统综述
链接：https://arxiv.org/abs/2209.10117
作者：Wenqi Fan,Xiangyu Zhao,Xiao Chen,Jingran Su,Jingtong Gao,Lin Wang,Qidong Liu,Yiqi Wang,Han Xu,Lei Chen,Qing Li
机构： The Hong Kong Polytechnic University, City University of Hong Kong, The Hong Kong PolytechnicUniversity
【31】 Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
标题：多智能体强化学习中的异步执行者-批评者
链接：https://arxiv.org/abs/2209.10113
作者：Yuchen Xiao,Weihao Tan,Christopher Amato
机构：Khoury College of Computer Sciences, Northeastern University, Boston, MA
【32】 Flashlight: Scalable Link Prediction with Effective Decoders
标题：Flashlight：使用高效解码器进行可伸缩链接预测
链接：https://arxiv.org/abs/2209.10100
作者：Yiwei Wang,Bryan Hooi,Yozen Liu,Tong Zhao,Zhichun Guo,Neil Shah
机构： National University of Singapore, Snap Inc.
备注：arXiv admin note: text overlap with arXiv:2112.02936 by other authors
【33】 On the benefits of self-taught learning for brain decoding
标题：论自学学习对大脑解码的益处
链接：https://arxiv.org/abs/2209.10099
作者：Elodie Germani,Elisa Fromont,Camille Maumet
机构：Univ Rennes, Inria, CNRS, Inserm, Rennes, France, Univ Rennes, IUF, Inria, CNRS, IRISA
【34】 Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
标题：基于预训练模型的联合学习：一种对比学习方法
链接：https://arxiv.org/abs/2209.10083
作者：Yue Tan,Guodong Long,Jie Ma,Lu Liu,Tianyi Zhou,Jing Jiang
机构：Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney, Google Research,University of Washington,University of Maryland
【35】 Generalized Gloves of Neural Additive Models: Pursuing transparent and accurate machine learning models in finance
标题：神经加性模型的广义手套：在金融学中追求透明和准确的机器学习模型
链接：https://arxiv.org/abs/2209.10082
作者：Dangxing Chen,Weicheng Ye
机构：† Zu Chongzhi Center for Mathematics and Computational Sciences, Duke Kunshan University, Kunshan, Jiangsu, China
【36】 Revisiting Discrete Soft Actor-Critic
标题：重温离散的软演员--评论家
链接：https://arxiv.org/abs/2209.10081
作者：Haibin Zhou,Zichuan Lin,Junyou Li,Deheng Ye,Qiang Fu,Wei Yang
机构：Tencent AI Lab, Shenzhen, China
【37】 A Reinforcement Learning Framework with Description Language for Critical Driving Scenario Generation
标题：一种基于描述语言的关键驾驶场景生成强化学习框架
链接：https://arxiv.org/abs/2209.10078
作者：Shuting Kang,Heng Guo,Yunzhi Xue
机构：Institute of Software Chinese Academy of Sciences
【38】 On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies
标题：个性化策略元强化学习的收敛理论研究
链接：https://arxiv.org/abs/2209.10072
作者：Haozhi Wang,Qing Wang,Yunfeng Shao,Dong Li,Jianye Hao,Yinchuan Li
机构： Qing Wang and Jianye Hao are with School of Electricaland Information Engineering, Tianjin University
【39】 Generate rather than Retrieve: Large Language Models are Strong Context Generators
标题：生成而不是检索：大型语言模型是强大的上下文生成器
链接：https://arxiv.org/abs/2209.10063
作者：Wenhao Yu,Dan Iter,Shuohang Wang,Yichong Xu,Mingxuan Ju,Soumya Sanyal,Chenguang Zhu,Michael Zeng,Meng Jiang
机构：University of Notre Dame, Notre Dame, IN, Microsoft Cognitive Services Research, Redmond, WA, University of Southern California, Los Angeles, CA
备注：Preprint, 24 pages
【40】 Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games
标题：拉马克平台：将进化强化学习的边界推向异步商业博弈
链接：https://arxiv.org/abs/2209.10055
作者：Hui Bai,Ruimin Shen,Yue Lin,Botian Xu,Ran Cheng
机构： Department of Computer Scienceand Engineering, Southern University of Science and Technology
【41】 Learning-Based Radiomic Prediction of Type 2 Diabetes Mellitus Using Image-Derived Phenotypes
标题：基于学习的图像衍生表型对2型糖尿病的放射学预测
链接：https://arxiv.org/abs/2209.10043
作者：Michael S. Yao,Allison Chae,Matthew T. MacLean,Anurag Verma,Jeffrey Duda,James Gee,Drew A. Torigian,Daniel Rader,Charles Kahn,Walter R. Witschey,Hersh Sagreiya
机构：Department of Bioengineering, University of Pennsylvania, Perelman School of Medicine, University of Pennsylvania, Department of Radiology, University of Pennsylvania, Department of Medicine, University of Pennsylvania
备注：9 pages
【42】 Setting the rhythm scene: deep learning-based drum loop generation from arbitrary language cues
标题：设置节奏场景：基于深度学习的任意语言提示的鼓循环生成
链接：https://arxiv.org/abs/2209.10016
作者：Ignacio J. Tripodi
机构：Independent Researcher
【43】 Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
标题：元数据考古：利用训练动态挖掘数据子集
链接：https://arxiv.org/abs/2209.10015
作者：Shoaib Ahmed Siddiqui,Nitarshan Rajkumar,Tegan Maharaj,David Krueger,Sara Hooker
机构：University of Cambridge, University of Toronto, Cohere for AI
【44】 Macro-Action-Based Multi-Agent/Robot Deep Reinforcement Learning under Partial Observability
标题：部分可观测下基于宏观动作的多智能体/机器人深度强化学习
链接：https://arxiv.org/abs/2209.10003
作者：Yuchen Xiao
机构：Khoury College of Computer Sciences in partial fulfillment, of the requirements for the degree of, Doctor of Philosophy, Northeastern University, Boston, Massachusetts, Aug , arXiv:,.,v, [cs.AI] , Sep
备注：PhD thesis
【45】 Optimizing Crop Management with Reinforcement Learning and Imitation Learning
标题：基于强化学习和模仿学习的作物优化管理
链接：https://arxiv.org/abs/2209.09991
作者：Ran Tao,Pan Zhao,Jing Wu,Nicolas F. Martin,Matthew T. Harrison,Carla Ferreira,Zahra Kalantari,Naira Hovakimyan
机构： University of Illinois at Urbana-Champaign, Tasmanian Institute of Agriculture, Stockholm University, KTH Royal Institute of Technology
【46】 jsdp: a Java Stochastic Dynamic Programming Library
标题：JSDP：一个Java随机动态规划库
链接：https://arxiv.org/abs/2209.09979
作者：Roberto Rossi
机构：Business School, University of Edinburgh, Edinburgh, UK
备注：8 pages
【47】 Comparative analysis of real bugs in open-source Machine Learning projects -- A Registered Report
标题：开源机器学习项目中真实错误的比较分析--注册报告
链接：https://arxiv.org/abs/2209.09932
作者：Tuan Dung Lai,Anj Simmons,Scott Barnett,Jean-Guy Schneider,Rajesh Vasa
机构：Applied Artificial Intelligence Inst., Deakin University, Geelong, VIC , Australia
备注：6 pages, 3 figures, registered report, conference paper, accepted at ESEM -- the International Symposium on Empirical Software Engineering and Measurement
【48】 Improved Marginal Unbiased Score Expansion (MUSE) via Implicit Differentiation
标题：改进的边际无偏分数扩展(MUSE)
链接：https://arxiv.org/abs/2209.10512
作者：Marius Millea
机构：Department of Physics, University of California, Berkeley, CA , USA, Department of Physics, University of California, Davis, CA , USA
备注：Code to reproduce our results available at this https URL
【49】 Approximating the full-field temperature evolution in 3D electronic systems from randomized "Minecraft" systems
链接：https://arxiv.org/abs/2209.10369
作者：Monika Stipsitz,Helios Sanchis-Alepuz
机构： Silicon Austria Labs GmbH, Inffeldgasse , Graz, Austria, Key words: ,D geometries, Convolutional Neural Network, Transient heat equation, Image-, based physics-informed loss
【50】 The ReturnZero System for VoxCeleb Speaker Recognition Challenge 2022
标题：VoxCeleb说话人识别挑战赛2022的ReturnZero系统
链接：https://arxiv.org/abs/2209.10147
作者：Sangwon Suh,Sunjong Park
机构：Return Zero Inc., Seoul, Korea
备注：4 pages, 4 tables, technical report
【51】 Interpretable Selective Learning in Credit Risk
标题：信用风险中的可解释选择性学习
链接：https://arxiv.org/abs/2209.10127
作者：Dangxing Chen,Weicheng Ye,Jiahui Ye
【52】 Boosting Star-GANs for Voice Conversion with Contrastive Discriminator
标题：利用对比度判别器增强STAR-GANS语音转换
链接：https://arxiv.org/abs/2209.10088
作者：Shijing Si,Jianzong Wang,Xulong Zhang,Xiaoyang Qu,Ning Cheng,Jing Xiao
机构： Ping An Technology (Shenzhen) Co., Ltd., China, School of Economics and Finance, Shanghai International Studies University, China
备注：12 pages, 3 figures, Accepted by ICONIP 2022. arXiv admin note: text overlap with arXiv:1907.12279 by other authors
【53】 A Demonstration of Over-the-Air Computation for Federated Edge Learning
标题：联合边缘学习的空中计算演示
链接：https://arxiv.org/abs/2209.09954
作者：Alphan Sahin
机构： University of South Carolina
备注：9 Figures, 7 Pages. Accepted to GLOBECOM'2022 Workshops: Edge Learning over 5G Mobile Networks and Beyond
机器翻译由腾讯交互翻译提供，仅供参考
历史文章列表 网站https://www.arxivdaily.com/
注：含中英文摘要速递见公众号【arXiv每日学术速递】,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。 |
|
发表于 2022-9-22 12:31:13