Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels

Abdali, Sara; Mukherjee, Subhabrata; Papalexakis, Evangelos E.

doi:10.1007/978-3-031-26390-3_33

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The scientific literature describes many experiments in which data augmentation is used in various domains, including sentiment analysis [12][13][14][15], text recognition [16][17][18][19], computer vision tasks [20][21][22][23], medical image analysis [24][25][26], face recognition [27][28][29], pose estimation [30][31][32][33], and even the formative assessment of trainees [34,35].…”

mentioning

confidence: 99%

A Method for Extrapolating Continuous Functions by Generating New Training Samples for Feedforward Artificial Neural Networks

Yotov

Hadzhikolev

Hadzhikoleva

et al. 2023

Axioms

View full text Add to dashboard Cite

The goal of the present study is to find a method for improving the predictive capabilities of feedforward neural networks in cases where values distant from the input–output sample interval are predicted. This paper proposes an iterative prediction algorithm based on two assumptions. One is that predictions near the statistical sample have much lower error than those distant from the sample. The second is that a neural network can generate additional training samples and use them to train itself in order to get closer to a distant prediction point. This paper presents the results of multiple experiments with different univariate and multivariate functions and compares the predictions made by neural networks before and after their training with the proposed iterative algorithm. The results show that, having passed through the stages of the algorithm, artificial neural networks significantly improve their interpolation performance in long-term forecasting. The present study demonstrates that neural networks are capable of creating additional samples for their own training, thus increasing their approximating efficiency.

show abstract