mlsanityData to 14 Oct 2026

ALF: An Active Learning Framework for Scientific Discovery

arXiv 2609.31197 ↗First posted 25 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine learning for scientific discovery is almost systematically data bound. Producing relevant high quality data, under budget constraints, is amongst the most promising ways to advance the field. Active learning (AL) offers promise wherever labelling requires expensive experiment, measurement, or simulation. Most existing tools cover only part of the data acquisition loop, and typically focus on either offline benchmarking or online deployment, but not both. We present ALF, a modular AL Framework that runs the full data acquisition loop via five modular components. One clear API for both settings: offline, against an existing dataset for controlled and reproducible experimentation; and online, against an oracle for acquiring new candidates in real-world deployments. ALF is open-source and available at https://github.com/instadeepai/alf.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 31 references that are in the map. First posted on arXiv 25 Sep 2026.

Builds on

13 of 31 references.

References · 13

  1. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  2. 2017A Tutorial on Thompson Samplingcited by 433
  3. 2019Analyzing Learned Molecular Representations for Property Predictioncited by 375
  4. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 297
  5. 2024Vanilla Bayesian Optimization Performs Great in High Dimensionscited by 92
  6. 2020AdaLead: A simple and robust adaptive greedy search algorithm for sequence designcited by 65
  7. 2020Accelerating high-throughput virtual screening through molecular pool-based active learningcited by 59
  8. 2022TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discoverycited by 45
  9. 2022GAUCHE: A Library for Gaussian Processes in Chemistrycited by 41
  10. 2018modAL: A modular active learning framework for Pythoncited by 35
  11. 2026MADE: Benchmark Environments for Closed-Loop Materials Discoverycited by 7
  12. 2026Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPscited by 3
1 more
  1. 2026Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPscited by 2

Built on by

Not cited yet.