Learn2Mix: Training Neural Networks Using Adaptive Data Integration
Not on the map. Why?
Abstract (arXiv)
Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strategy that adaptively adjusts class proportions within batches, focusing on classes with higher error rates. Unlike classical training methods that use static class proportions, learn2mix continually adapts class proportions during training, leading to faster convergence. Empirical evaluations on benchmark datasets show that neural networks trained with learn2mix converge faster than those trained with existing approaches, achieving improved results for classification, regression, and reconstruction tasks under limited training resources and with imbalanced classes. Our empirical findings are supported by theoretical analysis.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 21 Dec 2024.
Builds on
21 of 50 references.
References · 21
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2019Searching for MobileNetV3cited by 1,984
- 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
- 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
- 2015Cyclical Learning Rates for Training Neural Networkscited by 627
9 more
- 2013Generating Sequences With Recurrent Neural Networkscited by 549
- 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
- 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 323
- 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
- 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 252
- 2017Automated Curriculum Learning for Neural Networkscited by 251
- 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
- 2020learn2learn: A Library for Meta-Learning Researchcited by 69
- 2023Resilient Path Planning for UAVs in Data Collection under Adversarial Attackscited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.