Multi-Fidelity Active Learning with GFlowNets

• URL: http://arxiv.org/abs/2306.11715v2
• Date: Sun, 1 Sep 2024 11:15:16 GMT
• Title: Multi-Fidelity Active Learning with GFlowNets
• Authors: Alex Hernandez-Garcia, Nikita Saxena, Moksh Jain, Cheng-Hao Liu, Yoshua Bengio,
• Abstract summary: We propose a multi-fidelity active learning algorithm with GFlowNets as a sampler, to efficiently discover diverse, high-scoring candidates. Our evaluation on molecular discovery tasks shows that multi-fidelity active learning with GFlowNets can discover high-scoring candidates at a fraction of the budget of its single-fidelity counterpart.
• Score: 65.91555804996203
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In the last decades, the capacity to generate large amounts of data in science and engineering applications has been growing steadily. Meanwhile, machine learning has progressed to become a suitable tool to process and utilise the available data. Nonetheless, many relevant scientific and engineering problems present challenges where current machine learning methods cannot yet efficiently leverage the available data and resources. For example, in scientific discovery, we are often faced with the problem of exploring very large, structured and high-dimensional spaces. Moreover, the high fidelity, black-box objective function is often very expensive to evaluate. Progress in machine learning methods that can efficiently tackle such challenges would help accelerate currently crucial areas such as drug and materials discovery. In this paper, we propose a multi-fidelity active learning algorithm with GFlowNets as a sampler, to efficiently discover diverse, high-scoring candidates where multiple approximations of the black-box function are available at lower fidelity and cost. Our evaluation on molecular discovery tasks shows that multi-fidelity active learning with GFlowNets can discover high-scoring candidates at a fraction of the budget of its single-fidelity counterpart while maintaining diversity, unlike RL-based alternatives. These results open new avenues for multi-fidelity active learning to accelerate scientific discovery and engineering design.

Related papers

• regAL: Python Package for Active Learning of Regression Problems [0.0]
  Python package regAL allows users to evaluate different active learning strategies for regression problems. We present our Python package regAL, which allows users to evaluate different active learning strategies for regression problems.
  arXiv  Detail & Related papers  (2024-10-23T14:34:36Z)
• GFlowNets for AI-Driven Scientific Discovery [74.27219800878304]
  We present a new probabilistic machine learning framework called GFlowNets. GFlowNets can be applied in the modeling, hypotheses generation and experimental design stages of the experimental science loop. We argue that GFlowNets can become a valuable tool for AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2023-02-01T17:29:43Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)
• What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks? [59.51457877578138]
  We study contrastive learning on the wearable-based activity recognition task. This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
  arXiv  Detail & Related papers  (2022-02-12T06:10:15Z)
• Maximum Entropy Model-based Reinforcement Learning [0.0]
  This work connects exploration techniques and model-based reinforcement learning. We have designed a novel exploration method that takes into account features of the model-based approach. We also demonstrate through experiments that our method significantly improves the performance of the model-based algorithm Dreamer.
  arXiv  Detail & Related papers  (2021-12-02T13:07:29Z)
• Understanding the World Through Action [91.3755431537592]
  I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning. I will discuss how such a procedure is more closely aligned with potential downstream tasks.
  arXiv  Detail & Related papers  (2021-10-24T22:33:52Z)
• Learning Multimodal Rewards from Rankings [7.266985088439535]
  We go beyond learning a unimodal reward and focus on learning a multimodal reward function. We formulate the multimodal reward learning as a mixture learning problem. We conduct experiments and user studies using a multi-task variant of OpenAI's LunarLander and a real Fetch robot.
  arXiv  Detail & Related papers  (2021-09-27T01:22:01Z)
• Bayesian active learning for production, a systematic study and a reusable library [85.32971950095742]
  In this paper, we analyse the main drawbacks of current active learning techniques. We do a systematic study on the effects of the most common issues of real-world datasets on the deep active learning process. We derive two techniques that can speed up the active learning loop such as partial uncertainty sampling and larger query size.
  arXiv  Detail & Related papers  (2020-06-17T14:51:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.