Enhanced Urban Region Profiling with Adversarial Self-Supervised
Learning
- URL: http://arxiv.org/abs/2402.01163v1
- Date: Fri, 2 Feb 2024 06:06:45 GMT
- Title: Enhanced Urban Region Profiling with Adversarial Self-Supervised
Learning
- Authors: Weiliang Chan, Qianqian Ren, Jinbao Li
- Abstract summary: We propose a self-supervised graph collaborative filtering model for urban region embedding called EUPAS.
Specifically, region heterogeneous graphs containing human mobility data, point of interests (POIs) information, and geographic neighborhood details for each region are fed into the model.
The model generates region embeddings that preserve intra-region and inter-region dependencies through GCNs and multi-head attention.
- Score: 8.328861861105889
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Urban region profiling is pivotal for smart cities, but mining fine-grained
semantics from noisy and incomplete urban data remains challenging. In
response, we propose a novel self-supervised graph collaborative filtering
model for urban region embedding called EUPAS. Specifically, region
heterogeneous graphs containing human mobility data, point of interests (POIs)
information, and geographic neighborhood details for each region are fed into
the model, which generates region embeddings that preserve intra-region and
inter-region dependencies through GCNs and multi-head attention. Meanwhile, we
introduce spatial perturbation augmentation to generate positive samples that
are semantically similar and spatially close to the anchor, preparing for
subsequent contrastive learning. Furthermore, adversarial training is employed
to construct an effective pretext task by generating strong positive pairs and
mining hard negative pairs for the region embeddings. Finally, we jointly
optimize supervised and self-supervised learning to encourage the model to
capture the high-level semantics of region embeddings while ignoring the noisy
and unimportant details. Extensive experiments on real-world datasets
demonstrate the superiority of our model over state-of-the-art methods.
Related papers
- Learning Geospatial Region Embedding with Heterogeneous Graph [16.864563545518124]
We present GeoHG, an effective heterogeneous graph structure for learning comprehensive region embeddings for various downstream tasks.
Specifically, we tailor satellite image representation learning through geo-entity segmentation and point-of-interest (POI) integration for expressive intra-regional features.
GeoHG unifies informative spatial interdependencies and socio-environmental attributes into a powerful heterogeneous graph to encourage explicit modeling of higher-order inter-regional relationships.
arXiv Detail & Related papers (2024-05-23T03:19:02Z) - Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning [50.88504784466931]
Multi-task dense prediction involves semantic segmentation, depth estimation, and surface normal estimation.
Existing solutions typically rely on learning global image representations for global cross-task image matching.
Our proposal involves modeling region-wise representations using Gaussian Distributions.
arXiv Detail & Related papers (2024-03-15T12:41:30Z) - RegionGPT: Towards Region Understanding Vision Language Model [88.42271128373191]
RegionGPT (short as RGPT) is a novel framework designed for complex region-level captioning and understanding.
We develop an automated region caption data generation pipeline, enriching the training set with detailed region-level captions.
We demonstrate that a universal RGPT model can be effectively applied and significantly enhancing performance across a range of region-level tasks.
arXiv Detail & Related papers (2024-03-04T18:58:08Z) - Reconstructing Spatiotemporal Data with C-VAEs [49.1574468325115]
Conditional continuous representation of moving regions is commonly used.
In this work, we explore the capabilities of Conditional Varitemporal Autoencoder (C-VAE) models to generate realistic representations of regions' evolution.
arXiv Detail & Related papers (2023-07-12T15:34:10Z) - Attentive Graph Enhanced Region Representation Learning [7.4106801792345705]
Representing urban regions accurately and comprehensively is essential for various urban planning and analysis tasks.
We propose the Attentive Graph Enhanced Region Representation Learning (ATGRL) model, which aims to capture comprehensive dependencies from multiple graphs and learn rich semantic representations of urban regions.
arXiv Detail & Related papers (2023-07-06T16:38:43Z) - Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation [19.419836274690816]
We propose a new spatial-temporal graph learning model (GraphST) for enabling effective self-supervised learning.
Our proposed model is an adversarial contrastive learning paradigm that automates the distillation of crucial multi-view self-supervised information.
We demonstrate the superiority of our proposed GraphST method in various spatial-temporal prediction tasks on real-life datasets.
arXiv Detail & Related papers (2023-06-19T03:09:35Z) - Multi-Temporal Relationship Inference in Urban Areas [75.86026742632528]
Finding temporal relationships among locations can benefit a bunch of urban applications, such as dynamic offline advertising and smart public transport planning.
We propose a solution to Trial with a graph learning scheme, which includes a spatially evolving graph neural network (SEENet)
SEConv performs the intra-time aggregation and inter-time propagation to capture the multifaceted spatially evolving contexts from the view of location message passing.
SE-SSL designs time-aware self-supervised learning tasks in a global-local manner with additional evolving constraint to enhance the location representation learning and further handle the relationship sparsity.
arXiv Detail & Related papers (2023-06-15T07:48:32Z) - Point-Level Region Contrast for Object Detection Pre-Training [147.47349344401806]
We present point-level region contrast, a self-supervised pre-training approach for the task of object detection.
Our approach performs contrastive learning by directly sampling individual point pairs from different regions.
Compared to an aggregated representation per region, our approach is more robust to the change in input region quality.
arXiv Detail & Related papers (2022-02-09T18:56:41Z) - Urban Region Profiling via A Multi-Graph Representation Learning
Framework [0.0]
We propose a multi-graph representative learning framework, called Region2Vec, for urban region profiling.
Experiments on real-world datasets show that Region2Vec can be employed in three applications and outperforms all state-of-the-art baselines.
arXiv Detail & Related papers (2022-02-04T11:05:37Z) - An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot
Learning [77.72330187258498]
We propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet)
ERPCNet extracts and aggregates localities based on semantic relevance and visual correlations without human-annotated regions.
It not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization.
arXiv Detail & Related papers (2021-11-03T11:13:13Z) - Learning Neighborhood Representation from Multi-Modal Multi-Graph:
Image, Text, Mobility Graph and Beyond [20.014906526266795]
We propose a novel approach to integrate multi-modal geotagged inputs as either node or edge features of a multi-graph.
Specifically, we use street view images and POI features to characterize neighborhoods (nodes) and use human mobility to characterize the relationship between neighborhoods (directed edges)
The embedding we trained outperforms the ones using only unimodal data as regional inputs.
arXiv Detail & Related papers (2021-05-06T07:44:05Z)
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.