%0 Generic %1 rauch2023activeglae %A Rauch, Lukas %A Aßenmacher, Matthias %A Huseljic, Denis %A Wirth, Moritz %A Bischl, Bernd %A Sick, Bernhard %D 2023 %K active-learning benchmarks dataset pre-trained %T ActiveGLAE: A Benchmark for Deep Active Learning with Transformers %U https://arxiv.org/pdf/2306.10087 %X Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is currently no standardized evaluation protocol for transformer-based language models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for practitioners. To tackle this challenge, we propose the ActiveGLAE benchmark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.

@misc{rauch2023activeglae, abstract = {Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is currently no standardized evaluation protocol for transformer-based language models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for practitioners. To tackle this challenge, we propose the ActiveGLAE benchmark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.}, added-at = {2023-06-22T07:14:52.000+0200}, archiveprefix = {arXiv}, author = {Rauch, Lukas and Aßenmacher, Matthias and Huseljic, Denis and Wirth, Moritz and Bischl, Bernd and Sick, Bernhard}, biburl = {https://www.bibsonomy.org/bibtex/2c5e79cd7792c41dd54c8e6e9fabe3bf2/ghagerer}, eprint = {2306.10087}, interhash = {f53db50db8e5db94b91b8faae266cbc5}, intrahash = {c5e79cd7792c41dd54c8e6e9fabe3bf2}, keywords = {active-learning benchmarks dataset pre-trained}, month = jun, primaryclass = {cs.LG}, timestamp = {2023-06-22T07:14:52.000+0200}, title = {ActiveGLAE: A Benchmark for Deep Active Learning with Transformers}, url = {https://arxiv.org/pdf/2306.10087}, year = 2023 }