mlsanityData to 7 Oct 2026

Knowledge-driven Active Learning

arXiv 2110.08265 ↗First posted 15 Oct 2021cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The deployment of Deep Learning (DL) models is still precluded in those contexts where the amount of supervised data is limited. To answer this issue, active learning strategies aim at minimizing the amount of labelled data required to train a DL model. Most active strategies are based on uncertain sample selection, and even often restricted to samples lying close to the decision boundary. These techniques are theoretically sound, but an understanding of the selected samples based on their content is not straightforward, further driving non-experts to consider DL as a black-box. For the first time, here we propose to take into consideration common domain-knowledge and enable non-expert users to train a model with fewer samples. In our Knowledge-driven Active Learning (KAL) framework, rule-based knowledge is converted into logic constraints and their violation is checked as a natural guide for sample selection. We show that even simple relationships among data and output classes offer a way to spot predictions for which the model need supervision. We empirically show that KAL (i) outperforms many active learning strategies, particularly in those contexts where domain knowledge is rich, (ii) it discovers data distribution lying far from the initial training data, (iii) it ensures domain experts that the provided knowledge is acquired by the model, (iv) it is suitable for regression and object recognition tasks unlike uncertainty-based strategies, and (v) its computational demand is low.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 92 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

35 of 92 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  6. 2020Concept Bottleneck Modelscited by 1,022
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  9. 2020A Survey of Deep Active Learningcited by 547
  10. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  11. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  12. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
23 more
  1. 2017A simple neural network module for relational reasoningcited by 345
  2. 2019Learning Loss for Active Learningcited by 335
  3. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  4. 2019Variational Adversarial Active Learningcited by 284
  5. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  6. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  7. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  8. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  9. 2018Deep Learning: A Critical Appraisalcited by 214
  10. 2020Logic Tensor Networkscited by 197
  11. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  12. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  13. 2019Diverse mini-batch Active Learningcited by 88
  14. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  15. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  16. 2020Scalable Active Learning for Object Detectioncited by 58
  17. 2021Entropy-based Logic Explanations of Neural Networkscited by 51
  18. 2021Logic Explained Networkscited by 45
  19. 2020Confidence Estimation via Auxiliary Modelscited by 33
  20. 2020Adaptive Object Detection with Dual Multi-Label Predictioncited by 26
  21. 2018Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensemblescited by 20
  22. 2020Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifierscited by 10
  23. 2021Bayesian Active Learning by Disagreements: A Geometric Perspectivecited by 9

Built on by

Not cited yet.