A Survey of Learning on Small Data: Generalization, Optimization, and Challenge

• URL: http://arxiv.org/abs/2207.14443v2
• Date: Tue, 6 Jun 2023 15:44:14 GMT
• Title: A Survey of Learning on Small Data: Generalization, Optimization, and Challenge
• Authors: Xiaofeng Cao, Weixin Bu, Shengjun Huang, Minling Zhang, Ivor W. Tsang, Yew Soon Ong, and James T. Kwok
• Abstract summary: Learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI. This survey follows the active sampling theory under a PAC framework to analyze the generalization error and label complexity of learning on small data. Multiple data applications that may benefit from efficient small data representation are surveyed.
• Score: 101.27154181792567
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning on big data brings success for artificial intelligence (AI), but the annotation and training costs are expensive. In future, learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI, which requires machines to recognize objectives and scenarios relying on small data as humans. A series of learning topics is going on this way such as active learning and few-shot learning. However, there are few theoretical guarantees for their generalization performance. Moreover, most of their settings are passive, that is, the label distribution is explicitly controlled by finite training resources from known distributions. This survey follows the agnostic active sampling theory under a PAC (Probably Approximately Correct) framework to analyze the generalization error and label complexity of learning on small data in model-agnostic supervised and unsupervised fashion. Considering multiple learning communities could produce small data representation and related topics have been well surveyed, we thus subjoin novel geometric representation perspectives for small data: the Euclidean and non-Euclidean (hyperbolic) mean, where the optimization solutions including the Euclidean gradients, non-Euclidean gradients, and Stein gradient are presented and discussed. Later, multiple learning communities that may be improved by learning on small data are summarized, which yield data-efficient representations, such as transfer learning, contrastive learning, graph representation learning. Meanwhile, we find that the meta-learning may provide effective parameter update policies for learning on small data. Then, we explore multiple challenging scenarios for small data, such as the weak supervision and multi-label. Finally, multiple data applications that may benefit from efficient small data representation are surveyed.

Related papers

• Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data [54.934578742209716]
  In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets. LLKD is an adaptive sample selection method that incorporates signals from both the teacher and student. Our comprehensive experiments show that LLKD achieves superior performance across various datasets with higher data efficiency.
  arXiv  Detail & Related papers  (2024-11-12T18:57:59Z)
• Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First [13.37867275976255]
  We propose a novel strategy to incorporate more edges into training according to their difficulty from easy to hard. We demonstrate the strength of our proposed method in improving the generalization ability and robustness of learned representations.
  arXiv  Detail & Related papers  (2023-10-28T15:35:34Z)
• Exploring the Boundaries of Semi-Supervised Facial Expression Recognition using In-Distribution, Out-of-Distribution, and Unconstrained Data [23.4909421082857]
  We present a study on 11 of the most recent semi-supervised methods, in the context of facial expression recognition (FER) Our investigation covers semi-supervised learning from in-distribution, out-of-distribution, unconstrained, and very small unlabelled data. With an equal number of labelled samples, semi-supervised learning delivers a considerable improvement over supervised learning.
  arXiv  Detail & Related papers  (2023-06-02T01:40:08Z)
• Zero-shot meta-learning for small-scale data from human subjects [10.320654885121346]
  We develop a framework to rapidly adapt to a new prediction task with limited training data for out-of-sample test data. Our model learns the latent treatment effects of each intervention and, by design, can naturally handle multi-task predictions. Our model has implications for improved generalization of small-size human studies to the wider population.
  arXiv  Detail & Related papers  (2022-03-29T17:42:04Z)
• Learning from Few Examples: A Summary of Approaches to Few-Shot Learning [3.6930948691311016]
  Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. Deep learning solutions suffer from data hunger and extensively high computation time and resources. Few-shot learning that could drastically reduce the turnaround time of building machine learning applications emerges as a low-cost solution.
  arXiv  Detail & Related papers  (2022-03-07T23:15:21Z)
• CvS: Classification via Segmentation For Small Datasets [52.821178654631254]
  This paper presents CvS, a cost-effective classifier for small datasets that derives the classification labels from predicting the segmentation maps. We evaluate the effectiveness of our framework on diverse problems showing that CvS is able to achieve much higher classification results compared to previous methods when given only a handful of examples.
  arXiv  Detail & Related papers  (2021-10-29T18:41:15Z)
• Enhancing ensemble learning and transfer learning in multimodal data analysis by adaptive dimensionality reduction [10.646114896709717]
  In multimodal data analysis, not all observations would show the same level of reliability or information quality. We propose an adaptive approach for dimensionality reduction to overcome this issue. We test our approach on multimodal datasets acquired in diverse research fields.
  arXiv  Detail & Related papers  (2021-05-08T11:53:12Z)
• Relation-Guided Representation Learning [53.60351496449232]
  We propose a new representation learning method that explicitly models and leverages sample relations. Our framework well preserves the relations between samples. By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
  arXiv  Detail & Related papers  (2020-07-11T10:57:45Z)
• Learning to Count in the Crowd from Limited Labeled Data [109.2954525909007]
  We focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples. Specifically, we propose a Gaussian Process-based iterative learning mechanism that involves estimation of pseudo-ground truth for the unlabeled data.
  arXiv  Detail & Related papers  (2020-07-07T04:17:01Z)
• Prototypical Contrastive Learning of Unsupervised Representations [171.3046900127166]
  Prototypical Contrastive Learning (PCL) is an unsupervised representation learning method. PCL implicitly encodes semantic structures of the data into the learned embedding space. PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks.
  arXiv  Detail & Related papers  (2020-05-11T09:53:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.