UrbanKGent: A Unified Large Language Model Agent Framework for Urban
Knowledge Graph Construction
- URL: http://arxiv.org/abs/2402.06861v1
- Date: Sat, 10 Feb 2024 01:50:19 GMT
- Title: UrbanKGent: A Unified Large Language Model Agent Framework for Urban
Knowledge Graph Construction
- Authors: Yansong Ning, Hao Liu
- Abstract summary: This paper presents UrbanKGent, a unified large language model agent framework, for urban knowledge graph construction.
We first construct the knowledgeable instruction set for UrbanKGC tasks via relational-aware and geospatial-infused instruction generation.
We then propose a tool-augmented iterative trajectory refinement module to enhance and refine the trajectories distilled from GPT-4.
- Score: 5.705623864954382
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Urban knowledge graph has recently worked as an emerging building block to
distill critical knowledge from multi-sourced urban data for diverse urban
application scenarios. Despite its promising benefits, urban knowledge graph
construction (UrbanKGC) still heavily relies on manual effort, hindering its
potential advancement. This paper presents UrbanKGent, a unified large language
model agent framework, for urban knowledge graph construction. Specifically, we
first construct the knowledgeable instruction set for UrbanKGC tasks (such as
relational triplet extraction and knowledge graph completion) via
heterogeneity-aware and geospatial-infused instruction generation. Moreover, we
propose a tool-augmented iterative trajectory refinement module to enhance and
refine the trajectories distilled from GPT-4. Through hybrid instruction
fine-tuning with augmented trajectories on Llama-2-13B, we obtain the UrbanKGC
agent, UrbanKGent-13B. We perform a comprehensive evaluation on two real-world
datasets using both human and GPT-4 self-evaluation. The experimental results
demonstrate that UrbanKGent-13B not only can significantly outperform 21
baselines in UrbanKGC tasks, but also surpass the state-of-the-art LLM, GPT-4,
by more than 10\% with approximately 20 times lower cost. We deploy
UrbanKGent-13B to provide online services, which can construct an UrbanKG with
thousands of times richer relationships using only one-fifth of the data
compared with the existing benchmark. Our data, code, and opensource UrbanKGC
agent are available at https://github.com/usail-hkust/UrbanKGent.
Related papers
- COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation [1.5745692520785073]
We introduce a novel graph-based masked autoencoder (GMAE) for city-scale urban layout generation.
The method encodes attributed buildings, city blocks, communities and cities into a unified graph structure.
Our approach achieves good realism, semantic consistency, and correctness across the heterogeneous urban styles in 330 US cities.
arXiv Detail & Related papers (2024-07-16T00:49:53Z) - Unified Data Management and Comprehensive Performance Evaluation for
Urban Spatial-Temporal Prediction [Experiment, Analysis & Benchmark] [78.05103666987655]
This work addresses challenges in accessing and utilizing diverse urban spatial-temporal datasets.
We introduceatomic files, a unified storage format designed for urban spatial-temporal big data, and validate its effectiveness on 40 diverse datasets.
We conduct extensive experiments using diverse models and datasets, establishing a performance leaderboard and identifying promising research directions.
arXiv Detail & Related papers (2023-08-24T16:20:00Z) - UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal
Prediction [23.842678225828184]
This paper presents UUKG, the unified urban knowledge graph dataset for knowledge-enhanced urbantemporal predictions.
We first construct UrbanKGs consisting of millions of triplets for two metropolises by connecting heterogeneous urban entities.
We conduct qualitative and quantitative analysis on constructed UrbanKGs and uncover diverse high-order structural patterns.
arXiv Detail & Related papers (2023-06-20T10:40:53Z) - Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language
Models [53.09723678623779]
We propose TAGREAL to automatically generate quality query prompts and retrieve support information from large text corpora.
The results show that TAGREAL achieves state-of-the-art performance on two benchmark datasets.
We find that TAGREAL has superb performance even with limited training data, outperforming existing embedding-based, graph-based, and PLM-based methods.
arXiv Detail & Related papers (2023-05-24T22:09:35Z) - UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building
Instance Segmentation [50.52615875873055]
UrbanBIS comprises six real urban scenes, with 2.5 billion points, covering a vast area of 10.78 square kilometers.
UrbanBIS provides semantic-level annotations on a rich set of urban objects, including buildings, vehicles, vegetation, roads, and bridges.
UrbanBIS is the first 3D dataset that introduces fine-grained building sub-categories.
arXiv Detail & Related papers (2023-05-04T08:01:38Z) - A Contextual Master-Slave Framework on Urban Region Graph for Urban
Village Detection [68.84486900183853]
We build an urban region graph (URG) to model the urban area in a hierarchically structured way.
Then, we design a novel contextual master-slave framework to effectively detect the urban village from the URG.
The proposed framework can learn to balance the generality and specificity for UV detection in an urban area.
arXiv Detail & Related papers (2022-11-26T18:17:39Z) - Automated Urban Planning aware Spatial Hierarchies and Human
Instructions [33.06221365923015]
We propose a novel, deep, human-instructed urban planner based on generative adversarial networks (GANs)
GANs build urban functional zones based on information from human instructions and surrounding contexts.
We conduct extensive experiments to validate the efficacy of our work.
arXiv Detail & Related papers (2022-09-26T20:37:02Z) - Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge
Transfer [58.6106391721944]
Cross-city knowledge has shown its promise, where the model learned from data-sufficient cities is leveraged to benefit the learning process of data-scarce cities.
We propose a model-agnostic few-shot learning framework for S-temporal graph called ST-GFSL.
We conduct comprehensive experiments on four traffic speed prediction benchmarks and the results demonstrate the effectiveness of ST-GFSL compared with state-of-the-art methods.
arXiv Detail & Related papers (2022-05-27T12:46:52Z) - Effective Urban Region Representation Learning Using Heterogeneous Urban
Graph Attention Network (HUGAT) [0.0]
We propose heterogeneous urban graph attention network (HUGAT) for learning the representations of urban regions.
In our experiments on NYC data, HUGAT outperformed all the state-of-the-art models.
arXiv Detail & Related papers (2022-02-18T04:59:20Z) - Methodological Foundation of a Numerical Taxonomy of Urban Form [62.997667081978825]
We present a method for numerical taxonomy of urban form derived from biological systematics.
We derive homogeneous urban tissue types and, by determining overall morphological similarity between them, generate a hierarchical classification of urban form.
After framing and presenting the method, we test it on two cities - Prague and Amsterdam.
arXiv Detail & Related papers (2021-04-30T12:47:52Z)
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.