Finding the Sweet Spot: Batch Selection for One-Class Active Learning

Englhardt, Adrian; Trittenbach, Holger; Vetter, Dennis; Böhm, Klemens

doi:10.1137/1.9781611976236.14

Cited by 6 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…22 The next batch of experiments was selected by taking the top 100 molecules as ranked by the acquisition function. This is a naive method to select batches: all molecules are selected independently of each other, which can be suboptimal, 23 but it greatly decreases the computational complexity of the process compared to other batch selection policies. 24 After a batch is selected the activity readings for the new molecules are added to the data set.…”

Section: ■ Introductionmentioning

confidence: 99%

Batched Bayesian Optimization for Drug Design in Noisy Environments

Bellamy

Rehim

Orhobor

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The early stages of the drug design process involve identifying compounds with suitable bioactivities via noisy assays. As databases of possible drugs are often very large, assays can only be performed on a subset of the candidates. Selecting which assays to perform is best done within an active learning process, such as batched Bayesian optimization, and aims to reduce the number of assays that must be performed. We compare how noise affects different batched Bayesian optimization techniques and introduce a retest policy to mitigate the effect of noise. Our experiments show that batched Bayesian optimization remains effective, even when large amounts of noise are present, and that the retest policy enables more active compounds to be identified in the same number of experiments.

show abstract

Section: ■ Introductionmentioning

confidence: 99%

Batched Bayesian Optimization for Drug Design in Noisy Environments

Bellamy

Rehim

Orhobor

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…The effectiveness of ER depends on three crucial properties of the replay batch (Englhardt et al 2020): informativeness, representativeness, and diversity. In the CL setting, informativeness serves as a property that helps prevent catastrophic forgetting.…”

Section: Introductionmentioning

confidence: 99%

The Inter-batch Diversity of Samples in Experience Replay for Continual Learning

Krutsylo

2024

AAAI

View full text Add to dashboard Cite

In a Continual Learning setting, models are trained on data with occasional distribution shifts, resulting in forgetting the information learned before each shift. Experience Replay (ER) addresses this challenge by retaining part of the old training samples and replaying them alongside current data, improving the model's understanding of the overall distribution in training batches. The crucial factor in ER performance is the diversity of samples within batches. The impact of sample diversity across a sequence of batches is investigated, introducing a new metric and an associated approach to assess and leverage this diversity. This exploration opens up significant potential for future work, as various strategies can be devised to ensure inter-batch diversity. Achieving optimal results may involve striking a balance between this novel metric and other inherent properties of a batch or sequence.

show abstract

Bayesian Optimization in Drug Discovery

Colliandre,

Muller

2023

Methods in Molecular Biology

View full text Add to dashboard Cite

Finding the Sweet Spot: Batch Selection for One-Class Active Learning

Cited by 6 publications

References 23 publications

Batched Bayesian Optimization for Drug Design in Noisy Environments

Batched Bayesian Optimization for Drug Design in Noisy Environments

The Inter-batch Diversity of Samples in Experience Replay for Continual Learning

Bayesian Optimization in Drug Discovery

Contact Info

Product

Resources

About