mlsanityData to 7 Oct 2026

kFolden: k-Fold Ensemble for Out-Of-Distribution Detection

arXiv 2108.12731 ↗First posted 29 Aug 2021cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP). In this work, we propose a simple yet effective framework kFolden, which mimics the behaviors of OOD detection during training without the use of any external data. For a task with k training labels, kFolden induces k sub-models, each of which is trained on a subset with k-1 categories with the left category masked unknown to the sub-model. Exposing an unknown label to the sub-model during training, the model is encouraged to learn to equally attribute the probability to the seen k-1 labels for the unknown label, enabling this framework to simultaneously resolve in- and out-distribution examples in a natural way via OOD simulations. Taking text classification as an archetype, we develop benchmarks for OOD detection using existing text classification datasets. By conducting comprehensive comparisons and analyses on the developed benchmarks, we demonstrate the superiority of kFolden against current methods in terms of improving OOD detection performances while maintaining improved in-domain classification accuracy. The code and datasets can be found at: urlhttps://github.com/ShannonAI/kfolden-ood-detection.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 29 Aug 2021.

Builds on

36 of 64 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  11. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
24 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  2. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  3. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  5. 2016Learning to learn by gradient descent by gradient descentcited by 616
  6. 2019How to Fine-Tune BERT for Text Classification?cited by 409
  7. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  8. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  9. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  10. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  11. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  12. 2020Selective Question Answering under Domain Shiftcited by 228
  13. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  14. 2021BertGCN: Transductive Text Classification by Combining GCN and BERTcited by 74
  15. 2019Calibration of Encoder Decoder Models for Neural Machine Translationcited by 67
  16. 2020Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Taskscited by 51
  17. 2019Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classificationcited by 35
  18. 2018Natural Language to Structured Query Generation via Meta-Learningcited by 33
  19. 2020Description Based Text Classification with Reinforcement Learningcited by 27
  20. 2017Confident Multiple Choice Learningcited by 24
  21. 2020Uncertainty-aware Self-training for Text Classification with Few Labelscited by 19
  22. 2019Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsingcited by 18
  23. 2019Learning to Customize Model Structures for Few-shot Dialogue Generation Taskscited by 15
  24. 2019Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learningcited by 10

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 4; 2024: 1.

10 papers.

  1. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  2. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  3. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  4. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  5. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29
  6. 2023Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Featurescited by 12
  7. 2022Self-Supervised Losses for One-Class Textual Anomaly Detectioncited by 5
  8. 2024Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detectioncited by 4
  9. 2022Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Taskscited by 1
  10. 2022Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Modelscited by 1