Predictive Autoscaling is used to forecast the workloads of servers and prepare the resources in advance to ensure service level objectives (SLOs) in dynamic cloud environments. However, in practice, its prediction task often suffers from performance degradation under abnormal traffics caused by external events (such as sales promotional activities and applications re-configurations), for which a common solution is to re-train the model with data of a long historical period, but at the expense of high computational and storage costs. To better address this problem, we propose a replay-based continual learning method, i.e., Density-based Memory Selection and Hint-based Network Learning Model (DMSHM), using only a small part of the historical log to achieve accurate predictions. First, we discover the phenomenon of sample overlap when applying replay-based continual learning in prediction tasks. In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set. Then we implement hint-based network learning based on hint representation to optimize the parameters. Finally, we conduct experiments on public and industrial datasets to demonstrate that our proposed method outperforms state-of-the-art continual learning methods in terms of memory capacity and prediction accuracy. Furthermore, we demonstrate remarkable practicability of DMSHM in real industrial applications.
Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation of Predictive Models
Peoples' Friendship University of Russia (RUDN University)(俄罗斯人民友谊大学(RUDN大学));Joint Institute for Nuclear Research(联合核研究所);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);University of Skövde(舍夫德大学);University of Pisa(比萨大学)
To Retain or to Adapt? Generalizing Continual Learning
ETH AI Center, Department of Computer Science, ETH Zürich(苏黎世联邦理工学院人工智能中心,计算机科学系);Mila - Quebec AI Institute, School of Computer Science, McGill University(魁北克人工智能研究所,麦吉尔大学计算机科学系);University of Technology Nuremberg(纽伦堡技术大学)
The Gentle Collapse: Distributional Metrics for Continual Learning
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));RPTU University Kaiserslautern-Landau(凯泽斯劳滕-兰道大学);Hochschule Karlsruhe University of Applied Sciences(卡尔斯鲁厄应用技术大学)
Complementary Learning System Empowers Online Continual Learning of Vehicle Motion Forecasting in Smart Cities
The School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China(北京理工大学机械工程学院);The Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, China(同济大学道路与交通工程重点实验室);The School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore(南洋理工大学机械与航空航天工程学院)
Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance
Department of Computer Science & Engineering, International Institute of Information Technology (IIIT), Bhubaneswar, India(计算机科学与工程系,国际信息学院(IIIT),巴赫拉瓦尔)
A Conformal Predictive Measure for Assessing Catastrophic Forgetting
Communication Systems Department, EURECOM, France(EURECOM通信系统部);Andalusian Institute of Data Science and Computational Intelligence (DaSCI)(安达卢西亚数据科学与计算智能研究所);Department of Computer Science and Artificial Intelligence, University of Granada, Spain(格拉纳达大学计算机科学与人工智能系)
World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges
Ritsumeikan University(立命馆大学);Keio University(庆应义塾大学);The University of Tokyo(东京大学);Università Milano-Bicocca(米兰比可卡大学);University of Essex(埃塞克斯大学);Donders Institute for Brain, Cognition and Behaviour(唐德斯脑、认知与行为研究所);Cajal International Neuroscience Center, Spanish National Research Council(西班牙国家研究委员会卡哈尔国际神经科学中心);Bogazici University(博阿齐奇大学);Queen Mary University of London(伦敦玛丽女王大学);The University of Electro-Communications(电气通信大学);National Autonomous University of Mexico(墨西哥国立自治大学);Universidad Autónoma del Estado de Morelos(莫雷洛斯州自治大学);Institute of Cognitive Sciences and Technologies, National Research Council of Italy(意大利国家研究委员会认知科学与技术研究所)
Towards a Deep Learning-based Online Quality Prediction System for Welding Processes
Institute for Technologies and Management of Digital Transformation (TMDT)(数字化转型技术与管理研究所(TMDT));University of Wuppertal(伍珀塔尔大学);Forschungs- und Entwicklungsgesellschaft Fügetechnik GmbH (FEF)(连接技术研发有限公司(FEF))
Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules
Centre for Artificial Intelligence Driven Drug Discovery, Macao Polytechnic University(人工智能驱动药物发现中心,澳门理工学院);Key Laboratory of Short-Range Radio Equipment Testing and Evaluation, Ministry of Industry and Information Technology Terahertz Science Application Center (TSAC), Beijing Institute of Technology(工业和信息化部短距离无线电设备测试与评估重点实验室,太赫兹科学应用中心(TSAC),北京理工大学);Department of Critical Care Medicine, Yantai Yuhuangding Hospital, Qingdao University(重症医学科,烟台友谊医院,青岛大学);Faculty of Education, The University of Hong Kong(教育学院,香港大学);College of Information Engineering, Dalian University(信息工程学院,大连大学)