Open Problem: Active Representation Learning

2024/06/06 by Nikola Milošević, Milosevic, Nikola, G.A. Müller +5 · 1 citation
Computer Science · Social Sciences · #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning and Algorithms #Multi-Agent Systems and Negotiation #Robotics (cs.RO) #Systems and Control (eess.SY) #Wikis in Education and Collaboration #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2406.03845

openalex publication_date 2024/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous Localization and Mapping (active SLAM), and translate them to scientific discovery problems, exemplified by adaptive microscopy. We explore the need for a framework that derives exploration skills from representations that are in some sense actionable, aiming to enhance the efficiency and effectiveness of data collection and model building in the natural sciences.

Cited by

• Visualizing the multidimensional landscape of biological variation in modern microscopy

Related

• Guided Data Discovery in Interactive Visualizations via Active Search
• PAL -- Parallel active learning for machine-learned potentials
• Active Learning: Problem Settings and Recent Developments
• Can I see an Example? Active Learning the Long Tail of Attributes and Relations
• Learning to Explore using Active Neural SLAM