Training a classifier with high mean accuracy from a manifold-distributed dataset can be challenging. This problem is compounded further when there are only few labels available for training. For transfer learning to work, both the source and target datasets must have a similar manifold structure. As part of this study, we present a novel method for determining the similarity between two manifold structures. This method can be used to determine whether the target and source datasets have a similar manifold structure suitable for transfer learning.
We then present a few-shot learning method to classify manifold-distributed datasets with limited labels using transfer learning. Based on the base and target datasets, a similarity comparison is made to determine if the two datasets are suitable for transfer learning. A manifold structure and label distribution are learned from the base and target datasets. When the structures are similar, the manifold structure and its relevant label information from the richly labeled source dataset is transferred to target dataset. We use the transferred information, together with the labels and unlabeled data from the target dataset, to develop a few-shot classifier that produces high mean classification accuracy on manifold-distributed datasets.
In the final part of this article, we discuss the application of our manifold structure similarity measure to reinforcement learning and image recognition.
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
McGill University（麦吉尔大学）；Quebec AI Institute（魁北克人工智能研究所）；UC Berkeley（加州大学伯克利分校）；Google Brain（谷歌大脑）
强化学习（RL）代理被广泛用于解决复杂的顺序决策任务，但仍然表现出难以推广到训练过程中看不到的场景。虽然先前的在线方法表明，使用奖励函数之外的额外信号可以在RL代理中产生更好的泛化能力，即使用自监督学习（SSL），但它们在离线RL设置中挣扎，即从静态数据集学习。我们发现，在RL的泛化在线算法的性能可能会受到阻碍，由于观察之间的相似性估计不良的离线设置。我们提出了一个新的理论动机的框架，称为广义相似性函数（GSF），它使用对比学习训练离线RL代理聚合观察的基础上，他们的预期未来行为的相似性，在那里我们量化这种相似性使用\emph{generalized value functions}。我们表明，GSF是一般的，足以恢复现有的SSL目标，同时也提高了zero-shot泛化性能的一个复杂的离线RL基准测试，离线Procgen。
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
School of Informatics, Xiamen University（厦门大学信息学院）；Tsinghua University（清华大学）；Xiamen Unisound Intelligence Technology Co., Ltd（厦门Unisound智能科技有限公司）；Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室（厦门大学），中华人民共和国文化和旅游部，中国）
More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；MoonshotAI；Xiaomi AI Lab（小米AI实验室）；University of Electronic Science and Technology of China（电子科技大学）；Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed人工智能大学）；School of Artifcial Intelligence, Wuhan University（武汉大学人工智能学院）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MoE（下一代智能搜索与推荐工程技术研究中心，MoE）
Enhancing Few-Shot Learning with Integrated Data and GAN Model Approaches
Columbia University（哥伦比亚大学）；University of Michigan（密歇根大学）；Tulane University（杜兰大学）；Northeastern University（东北大学）；Dartmouth College（达特茅斯学院）；Shanghai Jiao Tong University（上海交通大学）
Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）
Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering
ST Engineering-SUTD Cyber Security Laboratory（ST Engineering-新加坡科技设计大学网络安全实验室）；Singapore University of Technology and Design（新加坡科技设计大学）；Ben-Gurion University（本-古里安大学）；University of Oslo（奥斯陆大学）
Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint
Institute of Medical Technology, Health Science Center of Peking University（北京大学健康科学中心医学技术研究所）；National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
Zero Shot Molecular Generation via Similarity Kernels
Engineering Laboratory, University of Cambridge, Trumpington St（剑桥大学工程实验室）；Institute for Computational Physics, University of Stuttgart, 70569 Stuttgart, Germany（斯图加特大学计算物理研究所）；Department of Energy Conversion and Storage, Technical University of Denmark, Anker Engelunds Vej 301, 2800 Kgs. Lyngby, Denmark（丹麦技术大学能源转换与存储系）
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；University of Liverpool（利物浦大学）；Faculty of Information Technology（信息技术学院）；Monash University（莫纳什大学）
Cross-modal Zero-shot Hashing by Label Attributes Embedding
Southwest University（西南大学）；Shandong University（山东大学）；Joint SDU-NTU Centre for Artificial Intelligence Research（山东大学-南洋理工大学人工智能联合研究中心）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；George Mason University（乔治梅森大学）
