Gengchen Mai

Gengchen Mai
University of Georgia | UGA · Department of Geography

Doctor of Philosophy

About

60
Publications
12,399
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
771
Citations
Additional affiliations
August 2021 - August 2022
Stanford University
Position
  • PostDoc Position
September 2015 - June 2021
University of California, Santa Barbara
Position
  • PhD Student

Publications

Publications (60)
Article
Full-text available
Qualitative spatial/temporal reasoning (QSR/QTR) plays a key role in research on human cognition, e.g., as it relates to navigation, as well as in work on robotics and artificial intelligence. Although previous work has mainly focused on various spatial and temporal calculi, more recently representation learning techniques such as embedding have be...
Article
The longer the COVID-19 pandemic lasts, the more apparent it becomes that understanding its social drivers may be as important as understanding the virus itself. One such social driver is misinformation and distrust in institutions. This is particularly interesting as the scientific process is more transparent than ever before. Numerous scientific...
Article
Geoparsing, the task of extracting toponyms from texts and associating them with geographic locations, has witnessed remarkable progress over the past years. However, despite its intrinsically geospatial nature, existing evaluations tend to focus on overall performance while paying little attention to its variation across geographic space. In this...
Article
Full-text available
Narrative cartography is a discipline which studies the interwoven nature of stories and maps. However, conventional geovisualization techniques of narratives often encounter several prominent challenges, including the data acquisition & integration challenge and the semantic challenge. To tackle these challenges, in this paper, we propose the idea...
Article
Knowledge graphs (KGs) are a novel paradigm for the representation, retrieval, and integration of data from highly heterogeneous sources. Within just a few years, KGs and their supporting technologies have become a core component of modern search engines, intelligent personal assistants, business intelligence, and so on. Interestingly, despite larg...
Article
Knowledge graphs (KGs) are a novel paradigm for the representation, retrieval, and integration of data from highly heterogeneous sources. Within just a few years, KGs and their supporting technologies have become a core component of modern search engines, intelligent personal assistants, business intelligence, and so on. Interestingly, despite larg...
Preprint
Full-text available
Generating learning-friendly representations for points in a 2D space is a fundamental and long-standing problem in machine learning. Recently, multi-scale encoding schemes (such as Space2Vec) were proposed to directly encode any point in 2D space as a high-dimensional vector, and has been successfully applied to various (geo)spatial prediction tas...
Preprint
Full-text available
Narrative cartography is a discipline which studies the interwoven nature of stories and maps. However, conventional geovisualization techniques of narratives often encounter several prominent challenges, including the data acquisition & integration challenge and the semantic challenge. To tackle these challenges, in this paper, we propose the idea...
Article
Full-text available
One of the key value propositions for knowledge graphs and semantic web technologies is fostering semantic interoperability, i.e., integrating data across different themes and domains. But why do we aim at interoperability in the first place? A common answer to this question is that each individual data source only contains partial information abou...
Preprint
Full-text available
Almost all statements in knowledge bases have a temporal scope during which they are valid. Hence, knowledge base completion (KBC) on temporal knowledge bases (TKB), where each statement \textit{may} be associated with a temporal scope, has attracted growing attention. Prior works assume that each statement in a TKB \textit{must} be associated with...
Preprint
Full-text available
A common need for artificial intelligence models in the broader geoscience is to represent and encode various types of spatial data, such as points (e.g., points of interest), polylines (e.g., trajectories), polygons (e.g., administrative regions), graphs (e.g., transportation networks), or rasters (e.g., remote sensing images), in a hidden embeddi...
Article
Full-text available
As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial ope...
Article
Full-text available
Identifying determinants of tourist destination choice is an important task in the study of nature-based tourism. Traditionally, the study of tourist behavior relies on survey data and travel logs, which are labor-intensive and time-consuming. Thanks to location-based social networks, more detailed data is available at a finer grained spatio-tempor...
Preprint
Full-text available
As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial ope...
Article
Full-text available
Many geoportals such as ArcGIS Online are established with the goal of improving geospatial data reusability and achieving intelligent knowledge discovery. However, according to previous research, most of the existing geoportals adopt Lucene-based techniques to achieve their core search functionality, which has a limited ability to capture the user...
Article
Traffic forecasting is a challenging problem due to the complexity of jointly modeling spatio‐temporal dependencies at different scales. Recently, several hybrid deep learning models have been developed to capture such dependencies. These approaches typically utilize convolutional neural networks or graph neural networks (GNNs) to model spatial dep...
Article
Full-text available
Learning knowledge graph (KG) embeddings is an emerging technique for a variety of downstream tasks such as summarization, link prediction, information retrieval, and question answering. However, most existing KG embedding models neglect space and, therefore, do not perform well when applied to (geo)spatial data and tasks. For those models that con...
Preprint
Learning knowledge graph (KG) embeddings is an emerging technique for a variety of downstream tasks such as summarization, link prediction, information retrieval, and question answering. However, most existing KG embedding models neglect space and, therefore, do not perform well when applied to (geo)spatial data and tasks. For those models that con...
Conference Paper
Full-text available
Many geoportals such as ArcGIS Online are established with the goal of improving geospatial data reusability and achieving intelligent knowledge discovery. However, according to previous research, most of the existing geoportals adopt Lucene-based techniques to achieve their core search functionality, which has a limited ability to capture the user...
Preprint
Many geoportals such as ArcGIS Online are established with the goal of improving geospatial data reusability and achieving intelligent knowledge discovery. However, according to previous research, most of the existing geoportals adopt Lucene-based techniques to achieve their core search functionality, which has a limited ability to capture the user...
Conference Paper
Full-text available
nsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations (embeddings) based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks. We see a strikingly similar situati...
Preprint
Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks. We see a strikingly similar situation in spatia...
Conference Paper
Full-text available
Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in modeling graph data, we propose a unified GCN framework, named TransGCN, to address this task, in which relat...
Conference Paper
Full-text available
Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of contributions from different query paths. We proposed to leverage a graph attention mechanism [20] to handle t...
Preprint
Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in modeling graph data, we propose a unified GCN framework, named TransGCN, to address this task, in which relat...
Preprint
Recently, several studies have explored methods for using KG embedding to answer logical queries. These approaches either treat embedding learning and query answering as two separated learning tasks, or fail to deal with the variability of contributions from different query paths. We proposed to leverage a graph attention mechanism to handle the un...
Conference Paper
Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in modeling graph data, we propose a unified GCN framework, named TransGCN, to address this task, in which relat...
Conference Paper
Full-text available
Recent years have witnessed a rapid increase in Question Answering (QA) research and products in both academic and industry. However, geographic question answering remained nearly untouched although geographic questions account for a substantial part of daily communication. Compared to general QA systems , geographic QA has its own uniqueness, one...
Article
Full-text available
Web-scale knowledge graphs such as the global Linked Data cloud consist of billions of individual statements about millions of entities. In recent years, this has fueled the interest in knowledge graph summarization techniques that compute representative subgraphs for a given collection of nodes. In addition, many of the most densely connected enti...
Article
Full-text available
Waldo Tobler frequently reminded us that the law named after him was nothing more than calling for exceptions. This paper discusses one of these exceptions. Spatial relation between points are frequently modeled as vectors in which both distance and direction are of equal prominence. However, in Toblers First Law of Geography (TFL), such a relation...
Article
Full-text available
The realization that knowledge often forms a densely interconnected graph has fueled the development of graph databases, Web-scale knowledge graphs and query languages for them, novel visualization and query paradigms, as well as new machine learning methods tailored to graphs as data structures. One such example is the densely connected and global...
Conference Paper
Full-text available
Bias, may it be in sampling or judgment, is not a new topic. However, with the increasing usage of data and models trained from them in almost all areas of everyday life, the topic rapidly gains relevance to the broad public. Even more, the opportunistic reuse of data (traces) that characterizes today's data science calls for new ways to understand...
Conference Paper
Full-text available
The past decades have witnessed a rapid increase in the global scientific output as measured by publish papers. Exploring a scientific field and searching for relevant papers and authors seems like a needle-in-a-haystack problem. Although many academic search engines have been developed to accelerate this retrieval process, most of them rely on con...
Preprint
Full-text available
Many services that perform information retrieval for Points of Interest (POI) utilize a Lucene-based setup with spatial filtering. While this type of system is easy to implement it does not make use of semantics but relies on direct word matches between a query and reviews leading to a loss in both precision and recall. To study the challenging tas...
Conference Paper
Full-text available
16 With recent advancements in deep convolutional neural networks, researchers in geographic in-17 formation science gained access to powerful models to address challenging problems such as 18 extracting objects from satellite imagery. However, as the underlying techniques are essentially 19 borrowed from other research fields, e.g., computer visio...
Article
Distributed ledger technologies such as blockchains and smart contracts have the potential to transform many sectors ranging from the handling of health records to real estate. Here we discuss the value proposition of these technologies and crypto-currencies for science in general and academic publishing in specific. We outline concrete use cases,...
Conference Paper
The Web-accessible of large, global-coverage databases of Points of Interest (POI) as well as social sensing techniques to study how humans behave towards these POI, i.e., when they visit them, how they write about them, the sequences in which they visit these POI, and so forth, have lead to researchers and companies utilizing POI to represent regi...
Conference Paper
Full-text available
In this dataset description paper we introduce the GNIS-LD, an authoritative and public domain Linked Dataset derived from the Geographic Names Information System (GNIS) which was developed by the U.S. Geological Survey (USGS) and the U.S. Board on Geographic Names. GNIS provides data about current, as well as historical, physical, and cultural geo...
Chapter
In this dataset description paper we introduce the GNIS-LD, an authoritative and public domain Linked Dataset derived from the Geographic Names Information System (GNIS) which was developed by the U.S. Geological Survey (USGS) and the U.S. Board on Geographic Names. GNIS provides data about current, as well as historical, physical, and cultural geo...
Chapter
With the fast development of mobile Web and computing technologies, as well as increasingly availability of mobile devices, mobile information technologies have revolutionary influence on the human society. In this article, we present a comprehensive review of mobile geographic information systems (GIS) and location-based services (LBS) concepts, c...
Conference Paper
Full-text available
With a rapidly increasing amount of machine-readable resources being generated and published to the Linked Data cloud, human-readable representations of those resources continue to serve an important demand. While dereferencing interfaces offer an easy, general-purpose solution to providing human-readable representations, they are not always well-e...
Conference Paper
Full-text available
Understanding, representing, and reasoning about Points Of Interest (POI) types such as Auto Repair, Body Shop, Gas Stations, or Planetarium, is a key aspect of geographic information retrieval, recommender systems, geographic knowledge graphs, as well as studying urban spaces in general, e.g., for extracting functional or vague cognitive regions f...
Article
Full-text available
Density-based clustering algorithms such as DBSCAN have been widely used for spatial knowledge discovery as they offer several key advantages compared to other clustering algorithms. They can discover clusters with arbitrary shapes, are robust to noise and do not require prior knowledge (or estimation) of the number of clusters. The idea of using a...
Conference Paper
In this work we introduce an anisotropic density-based clustering algorithm. It outperforms DBSCAN and OPTICS for the detection of anisotropic spatial point patterns and performs equally well in cases that do not explicitly benefit from an anisotropic perspective. ADCN has the same time complexity as DBSCAN and OPTICS, namely O(n log n) when using...
Conference Paper
Full-text available
As more data from heterogeneous sources become available, interfaces that support the federated exploration of these data are gaining importance to uncover relations between entities across multiple sources. Instead of explicit queries, visual interfaces enable a follow-your-nose style of exploration by which a user can seamlessly navigate between...
Conference Paper
Full-text available
While the adoption of Linked Data technologies has grown dramatically over the past few years, it has not come without its own set of growing challenges. The triplification of domain data into Linked Data has not only given rise to a leading role of places and positioning information for the dense interlinkage of data about actors, objects, and eve...
Article
Cash crop expansion has been a major land use change in tropical and subtropical regions worldwide. Quantifying the determinants of cash crop expansion should provide deeper spatial insights into the dynamics and ecological consequences of cash crop expansion. This paper investigated the process of cash crop expansion in Hangzhou region (China) fro...
Article
Peri-urban vegetation, which delivers a diversity of fundamental services, sustains increasing pressures from human activities. Characterizing the socioeconomic drivers of vegetated landscape pattern changes can inform ecological management. Vegetated landscape pattern changes, (including paddy, dryland, woodland, forest, and perennial plantations)...

Network

Cited By