Publication Details

Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement

BOBÁK Petr, ČMOLÍK Ladislav and ČADÍK Martin. Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement. IEEE Transactions on Visualization and Computer Graphics, vol. 30, no. 9, 2024, pp. 5908-5922. ISSN 1077-2626. Available from: http://cphoto.fit.vutbr.cz/reinforced-labels/
Type
journal article
Language
english
Authors
Bobák Petr, Ing. (DCGM FIT BUT)
Čmolík Ladislav, Ing., Ph.D. (FEE CTU)
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

Point-Feature Label Placement, Machine Learning, Multi-Agent Reinforcement Learning

Abstract

Over the recent years, Reinforcement Learning combined with Deep Learning techniques has successfully proven to solve
complex problems in various domains, including robotics, self-driving cars, and finance. In this paper, we are introducing Reinforcement Learning (RL) to label placement, a complex task in data visualization that seeks optimal positioning for labels to avoid overlap and ensure legibility. Our novel point-feature label placement method utilizes Multi-Agent Deep Reinforcement Learning to learn the label placement strategy, the first machine-learning-driven labeling method, in contrast to the existing hand-crafted algorithms designed by human experts. To facilitate RL learning, we developed an environment where an agent acts as a proxy for a label, a short textual annotation that augments visualization. Our results show that the strategy trained by our method significantly outperforms the random strategy of an
untrained agent and the compared methods designed by human experts in terms of completeness (i.e., the number of placed labels). The trade-off is increased computation time, making the proposed method slower than the compared methods. Nevertheless, our method is ideal for scenarios where the labeling can be computed in advance, and completeness is essential, such as cartographic maps, technical drawings, and medical atlases. Additionally, we conducted a user study to assess the perceived performance. The outcomes revealed that the participants considered the proposed method to be significantly better than the other examined methods. This indicates that the improved completeness is not just reflected in the quantitative metrics but also in the subjective evaluation by the participants.

Published
2024
Pages
5908-5922
Journal
IEEE Transactions on Visualization and Computer Graphics, vol. 30, no. 9, ISSN 1077-2626
Publisher
IEEE Computer Society
DOI
EID Scopus
BibTeX
@ARTICLE{FITPUB13067,
   author = "Petr Bob\'{a}k and Ladislav \v{C}mol\'{i}k and Martin \v{C}ad\'{i}k",
   title = "Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement",
   pages = "5908--5922",
   journal = "IEEE Transactions on Visualization and Computer Graphics",
   volume = 30,
   number = 9,
   year = 2024,
   ISSN = "1077-2626",
   doi = "10.1109/TVCG.2023.3313729",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/13067"
}
Back to top