%0 Journal Article %1 herde2023multi %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %D 2023 %J Transactions on Machine Learning Research %K imported itegpub isac-www NoisyLabels DeepLearning Crowdsourcing %T Multi-annotator Deep Learning: A Probabilistic Framework for Classification %U https://openreview.net/forum?id=MgdoxzImlK %X Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings. We address this issue by presenting a probabilistic training framework named multi-annotator deep learning (MaDL). A downstream ground truth and an annotator performance model are jointly trained in an end-to-end learning approach. The ground truth model learns to predict instances' true class labels, while the annotator performance model infers probabilistic estimates of annotators' performances. A modular network architecture enables us to make varying assumptions regarding annotators' performances, e.g., an optional class or instance dependency. Further, we learn annotator embeddings to estimate annotators' densities within a latent space as proxies of their potentially correlated annotations. Together with a weighted loss function, we improve the learning from correlated annotation patterns. In a comprehensive evaluation, we examine three research questions about multi-annotator supervised learning. Our findings show MaDL's state-of-the-art performance and robustness against many correlated, spamming annotators.

@article{herde2023multi, abstract = {Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings. We address this issue by presenting a probabilistic training framework named multi-annotator deep learning (MaDL). A downstream ground truth and an annotator performance model are jointly trained in an end-to-end learning approach. The ground truth model learns to predict instances' true class labels, while the annotator performance model infers probabilistic estimates of annotators' performances. A modular network architecture enables us to make varying assumptions regarding annotators' performances, e.g., an optional class or instance dependency. Further, we learn annotator embeddings to estimate annotators' densities within a latent space as proxies of their potentially correlated annotations. Together with a weighted loss function, we improve the learning from correlated annotation patterns. In a comprehensive evaluation, we examine three research questions about multi-annotator supervised learning. Our findings show MaDL's state-of-the-art performance and robustness against many correlated, spamming annotators.}, added-at = {2023-10-18T11:37:39.000+0200}, author = {Herde, Marek and Huseljic, Denis and Sick, Bernhard}, biburl = {https://www.bibsonomy.org/bibtex/2585c0c2c8eb52d717ffe6c603d01084a/ies}, codeurl = {https://github.com/ies-research/multi-annotator-deep-learning}, interhash = {f3f942451e0beb8358412bfe5ea5618a}, intrahash = {585c0c2c8eb52d717ffe6c603d01084a}, journal = {Transactions on Machine Learning Research}, keywords = {imported itegpub isac-www NoisyLabels DeepLearning Crowdsourcing}, timestamp = {2023-10-18T11:37:39.000+0200}, title = {Multi-annotator Deep Learning: A Probabilistic Framework for Classification}, url = {https://openreview.net/forum?id=MgdoxzImlK}, year = 2023 }