Explore the vast range of titles available.

The leading approaches in Machine Learning are notoriously data-hungry. Unfortunately, many application domains do not have access to big data because acquiring data involves a process that is expensive or time-consuming. This has triggered a serious debate in both the industrial and academic communities calling for more data-efficient models that harness the power of artificial learners while achieving good results with less training data and in particular less human supervision. In light of this debate, this work investigates the issue of algorithms’ data hungriness. First, it surveys the issue from different perspectives. Then, it presents a comprehensive review of existing data-efficient methods and systematizes them into four categories. Specifically, the survey covers solution strategies that handle data-efficiency by (i) using non-supervised algorithms that are, by nature, more data-efficient, by (ii) creating artificially more data, by (iii) transferring knowledge from rich-data domains into poor-data domains, or by (iv) altering data-hungry algorithms to reduce their dependency upon the amount of samples, in a way they can perform well in small samples regime. Each strategy is extensively reviewed and discussed. In addition, the emphasis is put on how the four strategies interplay with each other in order to motivate exploration of more robust and data-efficient algorithms. Finally, the survey delineates the limitations, discusses research challenges, and suggests future opportunities to advance the research on data-efficiency in machine learning.

Sports injuries significantly impact athletes’ health and performance, yet existing prediction methods struggle to capture complex athlete interactions and to generalize across sports with limited data. This study proposes a novel injury risk prediction framework integrating temporal graph encoding with graph neural networks and cross-sport transfer learning. The approach transforms multivariate training data into graph structures using Gramian Angular Fields and Markov Transition Fields, enabling spatiotemporal feature extraction through parallel graph convolution and temporal convolution pathways. A domain adaptation mechanism facilitates knowledge transfer from data-rich source sports to data-scarce target sports. Evaluated on a dataset of 312 athletes across five sports, the framework achieved an AUC of 0.826 ± 0.025, outperforming state-of-the-art baselines, including GAT (0.781) by 5.8%. Transfer learning experiments demonstrated remarkable small-sample performance, maintaining 0.80 AUC with only 50 target domain samples. Feature importance analysis revealed training load (0.182), load variability (0.156), and recovery time (0.138) as primary risk factors. The attention mechanism identified notable athlete interactions (weights > 0.7), providing interpretable insights for coaches. This framework demonstrates a promising approach for injury prevention in the evaluated sports contexts, particularly benefiting sports with limited historical data, and contributes to advancing sports health management systems.

The lack of labeled samples severely restricts the classification performance of deep learning on hyperspectral image classification. To solve this problem, Generative Adversarial Networks (GAN) are usually used for data augmentation. However, GAN have several problems with this task, such as the poor quality of the generated samples and an unstable training process. Thereby, knowing how to construct a GAN to generate high-quality hyperspectral training samples is meaningful for the small-sample classification task of hyperspectral data. In this paper, an Auxiliary Classifier based Wasserstein GAN with Gradient Penalty (AC-WGAN-GP) was proposed. The framework includes AC-WGAN-GP, an online generation mechanism, and a sample selection algorithm. The proposed method has the following distinctive advantages. First, the input of the generator is guided by prior knowledge and a separate classifier is introduced to the architecture of AC-WGAN-GP to produce reliable labels. Second, an online generation mechanism ensures the diversity of generated samples. Third, generated samples that are similar to real data are selected. Experiments on three public hyperspectral datasets show that the generated samples follow the same distribution as the real samples and have enough diversity, which effectively expands the training set. Compared to other competitive methods, the proposed framework achieved better classification accuracy with a small number of labeled samples.

Predicting energy consumption in large exposition centers presents a significant challenge, primarily due to the limited datasets and fluctuating electricity usage patterns. This study introduces a cutting-edge algorithm, the contrastive transformer network (CTN), to address these issues. By leveraging self-supervised learning, the CTN employs contrastive learning techniques across both temporal and contextual dimensions. Its transformer-based architecture, tailored for efficient feature extraction, allows the CTN to excel in predicting energy consumption in expansive structures, especially when data samples are scarce. Rigorous experiments on a proprietary dataset underscore the potency of the CTN in this domain.

Detailed urban landuse information plays a fundamental role in smart city management. A sufficient sample size has been identified as a very crucial pre-request in machine learning algorithms for urban landuse classification. However, it is often difficult to recognize and label landuse categories from remote sensing images alone. Alternatively, field investigation is time-consuming with a high demand in human resources and monetary cost. Therefore, previous studies on urban landuse classification have often relied on a small size of labeled samples with very uneven spatial distribution. This study aims to explore the effectiveness of a semi-supervised classification framework with multi-source data for detailed urban landuse classification with a few labeled samples. A disagreement-based semi-supervised learning approach, the Co-Forest, was employed and compared with traditional supervised methods (e.g., random forest and XGBoost). Multi-source geospatial data were utilized including optical and nighttime light remote sensing and geospatial big data, which present the physical and socio-economic features of landuse categories. Taking urban landuse classification in Shenzhen City as a case, results show that the classification accuracy of the semi-supervised method are generally on par with that of traditional supervised methods, and less labeled samples are needed to achieve a comparable result under different training set ratios. Given a small sample size, the accuracy tends to be stable with training samples no less than 5% in total. Our results also indicate that the classification accuracy by using multi-source data is significantly higher than that with any single data source being applied. Among these data, map POI and high-resolution optical remote sensing data make larger contributions on the classification, followed by mobile data and nighttime light remote sensing data.

Photovoltaic (PV) clusters in deserts such as the Gobi and other regions are frequently affected by sand and dust, which causes great deviation in power prediction and seriously threatens the safe operation of new power systems. For this reason, this paper proposes a short-term cluster PV power prediction method based on statistical upscaling, considering the effect of sand and dust. Firstly, the sand and dust events are identified, and then time series generative adversarial networks (TimeGANs) are used to solve the problem of small sample scarcity in sand and dust and construct a power correction model for sand and dust scenes. Secondly, for different weather scenes, a combination of conventional prediction and correction prediction is used to solve the problem of large differences in the predictability of a single model. Finally, a statistical upscaling method is utilized to calculate the cluster prediction power to solve the prediction difficulties of large-scale newly installed PV field stations. Through a case study and comparison with other models and methods, the cluster prediction method established in this paper effectively improves the prediction accuracy of the power of large-scale PV clusters affected by sand and dust, with the RMSE reduced by 8.28%.

With the remarkable development of deep learning in the field of science, deep neural networks provide a new way to solve the Stefan problem. In this paper, deep neural networks combined with small sample learning and a general deep learning framework are proposed to solve the two-dimensional Stefan problem. In the case of adding less sample data, the model can be modified and the prediction accuracy can be improved. In addition, by solving the forward and inverse problems of the two-dimensional single-phase Stefan problem, it is verified that the improved method can accurately predict the solutions of the partial differential equations of the moving boundary and the dynamic interface.

The mortality of skin pigmented malignant lesions is very high, especially melanoma. Due to the limitation of marking means, the large-scale annotation data of skin lesions are generally more difficult to obtain. When the deep learning model is trained on a small dataset, its generalization performance is limited. Using prior knowledge to expand small sample data is a general model method of learning classification, which is difficult to deal with complex skin problems. On the basis of a small amount of labeled skin lesion image data, this paper uses the improved Relational Network for measurement learning to realize the classification of skin disease. This method uses relative position network (RPN) and relative mapping network (RMN), in which RPN captures and extracts feature information by attention mechanism, and RMN obtains the similarity of image classification by weighted sum of attention mapping distance. The average accuracy of classification is 85% on the public ISIC melanoma dataset, and the results show the effectiveness and applicability of the method.

An intelligent diagnosis method based on self-adaptive Wasserstein dual generative adversarial networks and feature fusion is proposed due to problems such as insufficient sample size and incomplete fault feature extraction, which are commonly faced by rolling bearings and lead to low diagnostic accuracy. Initially, dual models of the Wasserstein deep convolutional generative adversarial network incorporating gradient penalty (1D-2DWDCGAN) are constructed to augment the original dataset. A self-adaptive loss threshold control training strategy is introduced, and establishing a self-adaptive balancing mechanism for stable model training. Subsequently, a diagnostic model based on multidimensional feature fusion is designed, wherein complex features from various dimensions are extracted, merging the original signal waveform features, structured features, and time-frequency features into a deep composite feature representation that encompasses multiple dimensions and scales; thus, efficient and accurate small sample fault diagnosis is facilitated. Finally, an experiment between the bearing fault dataset of Case Western Reserve University and the fault simulation experimental platform dataset of this research group shows that this method effectively supplements the dataset and remarkably improves the diagnostic accuracy. The diagnostic accuracy after data augmentation reached 99.94% and 99.87% in two different experimental environments, respectively. In addition, robustness analysis is conducted on the diagnostic accuracy of the proposed method under different noise backgrounds, verifying its good generalization performance.

To address the challenge of bearing load monitoring in elastically supported marine shafting systems, a multi-data fusion-based prediction model is constructed. In view of the small-sample nature of measured bearing load data, transfer learning is adopted to migrate the physical relationships embedded in finite element simulations to the measurement domain. A limited number of actual samples are used to correct the simulation data, forming a high-fidelity hybrid training set. The system—supported by air-spring isolators mounted on the raft—is divided into multiple sub-regions according to their spatial layout, establishing local mappings from air-spring pressure variations to bearing load increments to reduce model complexity. On this basis, a Stacking ensemble learning framework is further incorporated into the prediction model to integrate multi-source information such as air-spring pressure and raft strain, thereby enriching the model’s information acquisition and improving prediction accuracy. Experimental results show that the proposed transfer learning-based multi-sub-region bearing load prediction model performs significantly better than the full-parameter input model. Furthermore, the strain-enhanced Stacking-based multi-data fusion bearing load prediction model improves the characterization of shafting features and reduces the maximum prediction error. The proposed multi-data fusion modeling strategy offers a viable approach for condition monitoring and intelligent maintenance of marine shafting systems.