paper-with-me

홈 › Papers

Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning

2022-11-28 · Witold Sosnowski, Karolina Seweryn, Anna Wróblewska, Piotr Gawrysiak

This paper presents an analysis regarding an influence of the Distance Metric Learning (DML) loss functions on the supervised fine-tuning of the language models for classification tasks. We experimented with known datasets from SentEval Transfer Tasks. Our experiments show that applying the DML loss function can increase performance on downstream classification tasks of RoBERTa-large models in few-shot scenarios. Models fine-tuned with the use of SoftTriple loss can achieve better results than models with a standard categorical cross-entropy loss function by about 2.89 percentage points from 0.04 to 13.48 percentage points depending on the training dataset. Additionally, we accomplished a comprehensive analysis with explainability techniques to assess the models' reliability and explain their results.

📄 PDF Abstract BibTeX arXiv:2211.15195

Code (0)

등록된 구현이 없습니다.

Tasks

Metric Learning

Similar Papers 제목 키워드 기반

Assessing two novel distance-based loss functions for few-shot image classification

2021-09-29 · Mauricio Mendez Ruiz, Gilberto Ochoa Ruiz, Andres Mendez Vazquez, Jorge Gonzalez-Zapata

Few-shot learning is a challenging area of research which aims to learn new concepts with only a few labeled samples of data. Recent works based on metric-learning approaches benefit from the meta-learning process in whi…

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification+3

SuSana Distancia is all you need: Enforcing class separability in metric learning via two novel distance-based loss functions for few-shot image classification

2023-05-15 · Mauricio Mendez-Ruiz, Jorge Gonzalez-Zapata, Ivan Reyes-Amezcua, Daniel Flores-Araiza 외

Few-shot learning is a challenging area of research that aims to learn new concepts with only a few labeled samples of data. Recent works based on metric-learning approaches leverage the meta-learning approach, which is …

AllFew-Shot Image ClassificationFew-Shot Learningimage-classification+4

Constellation Loss: Improving the efficiency of deep metric learning loss functions for optimal embedding

2019-05-25 · Alfonso Medela, Artzai Picon

Metric learning has become an attractive field for research on the latest years. Loss functions like contrastive loss, triplet loss or multi-class N-pair loss have made possible generating models capable of tackling comp…

Few-Shot LearningMetric LearningTriplet

Revisiting Distance Metric Learning for Few-Shot Natural Language Classification

2022-11-28 · Witold Sosnowski, Anna Wróblewska, Karolina Seweryn, Piotr Gawrysiak

Distance Metric Learning (DML) has attracted much attention in image processing in recent years. This paper analyzes its impact on supervised fine-tuning language models for Natural Language Processing (NLP) classificati…

Few-Shot LearningLanguage ModelingLanguage ModellingMetric Learning

Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey

2022-01-23 · Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distance metric, Mahalanobis distance, and gene…

Dimensionality ReductionMetric LearningSurveyTriplet