Neural ODE Processes approach the problem of meta-learning for dynamics using a latent variable model, which permits a flexible aggregation of contextual information. This flexibility is inherited from the Neural Process framework and allows the model to aggregate sets of context observations of arbitrary size into a fixed-length representation. In the physical sciences, we often have access to structured knowledge in addition to raw observations of a system, such as the value of a conserved quantity or a description of an understood component. Taking advantage of the aggregation flexibility, we extend the Neural ODE Process model to use additional information within the Learning Using Privileged Information setting, and we validate our extension with experiments showing improved accuracy and calibration on simulated dynamics tasks.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
Universidad Autónoma de Madrid(马德里自治大学);Institute of Science and Technology Austria(奥地利科学技术研究所);Technische Universität Dortmund(多特蒙德工业大学);University of Sussex(萨塞克斯大学)
OCKELM+: Kernel Extreme Learning Machine based One-class Classification using Privileged Information (or KOC+: Kernel Ridge Regression or Least Square SVM with zero bias based One-class Classification using Privileged Information)
Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models
Delft University of Technology(代尔夫特理工大学);Research Institute of Sweden(瑞典研究院);Massachusetts Institute of Technology(麻省理工学院);University of Toronto(多伦多大学);Chalmers University of Technology(查尔姆斯理工大学)
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Cambridge(剑桥大学);Facebook AI Research(Facebook人工智能研究院);Columbia University(哥伦比亚大学)
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Google AI(谷歌人工智能)
监督学习数据集通常具有特权信息,其形式为在训练时可用但在测试时不可用的特征,例如提供标签的注释者的ID。我们认为,特权信息是有用的解释远离标签噪音,从而减少噪音标签的有害影响。我们开发了一个简单而有效的方法,监督学习与神经网络:它通过权重共享知识学习特权信息和近似边缘化特权信息在测试时。我们的方法,TRAM(TRansfer and Marginalize),具有最小的训练时间开销,并且具有与不使用特权信息相同的测试时间成本。TRAM在CIFAR-10 H、ImageNet和Civil Comments基准测试中表现强劲。
许多机器学习算法假设所有输入样本独立且相同地分布于输入空间X(在无监督学习的情况下)或输入和输出空间X X Y(在监督和半监督学习的情况下)上的某个公共分布。在过去的几年里,人们已经探索了这种假设的放松,并且在机器学习算法中并入附加信息的重要性变得更加明显。传统上,这种信息融合是半监督学习的领域。最近,Vapnik提出将来自不同假设空间的知识纳入监督设置。在这项工作中,我们有兴趣探索Vapnik的大师级学习的想法和相关的学习使用特权信息,但在无监督的设置。采用先进的监督学习范式的无监督设置煽动调查特权和技术数据之间的差异。通过我们提出的aRi-MAX方法,提高了KMeans算法的稳定性,并在人工数据集上实现了最佳聚类解的识别。在此基础上,提出了一种基于信息论点积的P-Dot算法。该方法能够单独或组合地利用各种聚类技术,同时融合特权和技术数据以改进聚类。将P-Dot方法应用于数字识别任务证实了我们在现实场景中的发现。
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
School of Computer Science, University of Beihang, Beijing, China(北京航空航天大学计算机学院);School of Computer Science, Chinese University of Hong Kong, Hongkong, China(香港中文大学计算机学院);JD Explore Academy, Beijing, China(京东探索研究院);North Automatic Control Institute, Taiyuan, China(太原北自动控制研究所)
Sequential Minimal Optimization Algorithm for One-Class Support Vector Machines With Privileged Information
Skolkovo Institute of Science and Technology (Skoltech)(斯科尔科沃科学技术研究所);Institute for Information Transmission Problems of Russian Academy of Sciences (IITP RAS)(俄罗斯科学院信息传输问题研究所);Artificial Intelligence Research Institute (AIRI)(人工智能研究所)
Coupled Training with Privileged Information and Unlabeled Data
Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电子与计算机工程系);Department of Operations Research and Financial Engineering, Princeton University(普林斯顿大学运筹学与金融工程系)
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
Department of Computer Science, The University of Texas at Dallas, Richardson TX 75080, USA(德克萨斯大学达拉斯分校计算机科学系);Computer Science Department and Centre for Cognitive Science, TU Darmstadt, Germany(德累斯顿技术大学计算机科学系和认知科学中心)
$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院);Meituan(美团);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach
Department of Artificial Intelligence, Faculty of Information and Communications Technology, University of Malta(人工智能系,信息与通讯技术学院,马耳他大学);Department of Communications and Computer Engineering, Faculty of Information and Communications Technology, University of Malta(通讯与计算机工程系,信息与通讯技术学院,马耳他大学);Department of Criminology, Faculty of Social Wellbeing, University of Malta(犯罪学系,社会福祉学院,马耳他大学)
Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective
Shanghai Jiao Tong University(上海交通大学);Hong Kong University of Science and Technology(香港科技大学);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院(TeleAI));Northwestern University(西北大学);Tsinghua University(清华大学)
本文将仿真到现实的差距表述为信息瓶颈问题,提出 Historical Information Bottleneck (HIB) 方法,通过从历史轨迹中学习特权知识表示来减少策略间的价值差异,有效提升了机器人在现实场景中的泛化能力。