active learning 主动学习

Deep Active Learning: Pool-based AL selects most informative data iteratively from a large pool of unlabeled i.i.d. data samples until either the basic learner(s) reaches a certain level of performance or a fixed budget is exhausted.

Querying Strategies

uncertainty-based

Uncertainty-based DAL selects data samples with high aleatoric uncertainty or epistemic uncertainty.

  • Aleatoric uncertainty refers to the natural uncertainty in data due to influences on data generation processes that are inherently random.
  • Epistemic uncertainty comes from the modeling/learning process and is caused by a lack of knowledge.

Typical methods:

  1. Maximum Entropy (Entropy) selects data x that maximize the predictive entropy.
  2. Margin selects data x whose two most likely labels have smallest difference in posterior probabilities.
  3. Least Confidence (LeastConf) selects data x whose most likely label ŷ has lowest posterior probability
  4. **Bayesian Active Learning by Disagreements (BALD) ** chooses data points that are
    expected to maximize the information gained from the model parameters ω, i.e. the mu-
    tual information between predictions and model posterior: αBALD (x, M) = HM [y|x] −
    Ep(ω|Dl) [HM[y|x, ω]].
  5. Mean Standard Deviation (MeanSTD) maximizes the mean standard deviation of the predicted probabilities over all k classes: αMeanSTD (x, M) = 1 k Pk pVarq(ω)[p(y = k|x, ω)].
  6. DeepFool Active Learning method (AdvDeepFool)
  7. Generative Adversarial Active Learning (GAAL)
  8. Bayesian Generative Active Deep Learning (BGADL)
  9. Batch Active learning by Diverse Gradient Embeddings (BADGE)
  10. Loss Prediction Loss (LPL)

representativeness/diversity-based

Representative/diversity-based strategies select batches of samples representative of the unlabeled set and are based on the intuition that the selected representative examples, once labeled, can act as a surrogate for the entire dataset.

Typical methods:

  1. KMeans
  2. CoreSet
  3. Cluster-Margin
  4. Active-DPP

combined strategies

Due to the demand for larger batch size (representative/diversity) and more precise decision boundaries for higher model performance (uncertainty) in DAL, combined strategies have become the dominant approaches to DAL. It aims to achieve a trade-off between uncertainty and representativeness/diversity in query selection.

参考文献

Zhan, Xueying, et al. “A comparative survey of deep active learning.” arXiv preprint arXiv:2203.13450 (2022).