3 Search Results for "Gao, Song"

Document
Short Paper
DOI: 10.4230/LIPIcs.GIScience.2023.43
Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper)

Authors: Yuhan Ji and Song Gao

Published in: LIPIcs, Volume 277, 12th International Conference on Geographic Information Science (GIScience 2023)

Abstract
This research focuses on assessing the ability of large language models (LLMs) in representing geometries and their spatial relations. We utilize LLMs including GPT-2 and BERT to encode the well-known text (WKT) format of geometries and then feed their embeddings into classifiers and regressors to evaluate the effectiveness of the LLMs-generated embeddings for geometric attributes. The experiments demonstrate that while the LLMs-generated embeddings can preserve geometry types and capture some spatial relations (up to 73% accuracy), challenges remain in estimating numeric values and retrieving spatially related objects. This research highlights the need for improvement in terms of capturing the nuances and complexities of the underlying geospatial data and integrating domain knowledge to support various GeoAI applications using foundation models.
Cite as

Yuhan Ji and Song Gao. Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 43:1-43:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{ji_et_al:LIPIcs.GIScience.2023.43,
  author =	{Ji, Yuhan and Gao, Song},
  title =	{{Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations}},
  booktitle =	{12th International Conference on Geographic Information Science (GIScience 2023)},
  pages =	{43:1--43:6},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-288-4},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{277},
  editor =	{Beecham, Roger and Long, Jed A. and Smith, Dianna and Zhao, Qunshan and Wise, Sarah},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2023.43},
  URN =		{urn:nbn:de:0030-drops-189381},
  doi =		{10.4230/LIPIcs.GIScience.2023.43},
  annote =	{Keywords: LLMs, foundation models, GeoAI}
}
Document
Short Paper
DOI: 10.4230/LIPIcs.GIScience.2023.93
The Ethics of AI-Generated Maps: DALL·E 2 and AI’s Implications for Cartography (Short Paper)

Authors: Qianheng Zhang, Yuhao Kang, and Robert Roth

Published in: LIPIcs, Volume 277, 12th International Conference on Geographic Information Science (GIScience 2023)

Abstract
The rapid advancement of artificial intelligence (AI) such as the emergence of large language models ChatGPT and DALL·E 2 has brought both opportunities for improving productivity and raised ethical concerns. This paper investigates the ethics of using artificial intelligence (AI) in cartography, with a particular focus on the generation of maps using DALL·E 2. To accomplish this, we first created an open-sourced dataset that includes synthetic (AI-generated) and real-world (human-designed) maps at multiple scales with a variety of settings. We subsequently examined four potential ethical concerns that may arise from the characteristics of DALL·E 2 generated maps, namely inaccuracies, misleading information, unanticipated features, and irreproducibility. We then developed a deep learning-based model to identify those AI-generated maps. Our research emphasizes the importance of ethical considerations in the development and use of AI techniques in cartography, contributing to the growing body of work on trustworthy maps. We aim to raise public awareness of the potential risks associated with AI-generated maps and support the development of ethical guidelines for their future use.
Cite as

Qianheng Zhang, Yuhao Kang, and Robert Roth. The Ethics of AI-Generated Maps: DALL·E 2 and AI’s Implications for Cartography (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 93:1-93:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{zhang_et_al:LIPIcs.GIScience.2023.93,
  author =	{Zhang, Qianheng and Kang, Yuhao and Roth, Robert},
  title =	{{The Ethics of AI-Generated Maps: DALL·E 2 and AI’s Implications for Cartography}},
  booktitle =	{12th International Conference on Geographic Information Science (GIScience 2023)},
  pages =	{93:1--93:6},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-288-4},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{277},
  editor =	{Beecham, Roger and Long, Jed A. and Smith, Dianna and Zhao, Qunshan and Wise, Sarah},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2023.93},
  URN =		{urn:nbn:de:0030-drops-189886},
  doi =		{10.4230/LIPIcs.GIScience.2023.93},
  annote =	{Keywords: Ethics, GeoAI, DALL-E, Cartography}
}
Document
DOI: 10.4230/LIPIcs.GIScience.2021.I.12
LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection

Authors: Jinmeng Rao, Song Gao, Yuhao Kang, and Qunying Huang

Published in: LIPIcs, Volume 177, 11th International Conference on Geographic Information Science (GIScience 2021) - Part I (2020)

Abstract
The prevalence of location-based services contributes to the explosive growth of individual-level trajectory data and raises public concerns about privacy issues. In this research, we propose a novel LSTM-TrajGAN approach, which is an end-to-end deep learning model to generate privacy-preserving synthetic trajectory data for data sharing and publication. We design a loss metric function TrajLoss to measure the trajectory similarity losses for model training and optimization. The model is evaluated on the trajectory-user-linking task on a real-world semantic trajectory dataset. Compared with other common geomasking methods, our model can better prevent users from being re-identified, and it also preserves essential spatial, temporal, and thematic characteristics of the real trajectory data. The model better balances the effectiveness of trajectory privacy protection and the utility for spatial and temporal analyses, which offers new insights into the GeoAI-powered privacy protection.
Cite as

Jinmeng Rao, Song Gao, Yuhao Kang, and Qunying Huang. LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection. In 11th International Conference on Geographic Information Science (GIScience 2021) - Part I. Leibniz International Proceedings in Informatics (LIPIcs), Volume 177, pp. 12:1-12:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@InProceedings{rao_et_al:LIPIcs.GIScience.2021.I.12,
  author =	{Rao, Jinmeng and Gao, Song and Kang, Yuhao and Huang, Qunying},
  title =	{{LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection}},
  booktitle =	{11th International Conference on Geographic Information Science (GIScience 2021) - Part I},
  pages =	{12:1--12:17},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-166-5},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{177},
  editor =	{Janowicz, Krzysztof and Verstegen, Judith A.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.GIScience.2021.I.12},
  URN =		{urn:nbn:de:0030-drops-130471},
  doi =		{10.4230/LIPIcs.GIScience.2021.I.12},
  annote =	{Keywords: GeoAI, Deep Learning, Trajectory Privacy, Generative Adversarial Networks}
}
  • Refine by Author
  • 2 Gao, Song
  • 2 Kang, Yuhao
  • 1 Huang, Qunying
  • 1 Ji, Yuhan
  • 1 Rao, Jinmeng
  • Show More...

  • Refine by Classification
  • 2 Computing methodologies → Artificial intelligence
  • 1 Human-centered computing → Human computer interaction (HCI)
  • 1 Security and privacy → Privacy protections

  • Refine by Keyword
  • 3 GeoAI
  • 1 Cartography
  • 1 DALL-E
  • 1 Deep Learning
  • 1 Ethics
  • Show More...

  • Refine by Type
  • 3 document

  • Refine by Publication Year
  • 2 2023
  • 1 2020

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact