Publications [Home]

2026

• TATA: An Efficient Framework for Task Transfer in Query Plan Representation

• GoodTP: An Effective Data Selection Framework for Enhancing Trajectory Similarity Learning via Monte Carlo Tree Search

• Are Learned DBMS Components Robust to Workload Drift?

• SOLAR: Efficient Spatial Queries on Real-time LSM-based Storage

• ARCADE: A Real-Time Data System for Hybrid and Continuous Query Processing across Diverse Data Modalities

• CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG

• Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining

• Cross-city Time Series Forecasting with Retrieval-Augmented Large Language Models

2025

• NEXT: A New Secondary Index Framework for LSM-based Data Storage

• DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph

• MAST: Towards Efficient Analytical Query Processing on Point Cloud Data

• BT-Tree: A Reinforcement Learning Based Index for Big Trajectory Data

• CAMAL: Optimizing LSM-trees via Active Learning

• LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency

• RankPQO: Learning-to-Rank for Parametric Query Optimization

• GeoBloom: Revisiting Lightweight Models for Geographic Information Retrieval

• Demonstrating MAST: An Efficient System for Point Cloud Data Analytics

• FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting

• Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization

• Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey

• HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling

• Reconciling Geospatial Prediction and Retrieval via Sparse Representations

• TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability

• PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models

• SMARTraj: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning

• Self-supervised representation learning for geospatial objects: A survey

• Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis

• ST-LLM+: Graph Enhanced Spatio-Temporal Large Language Models for Traffic Prediction

• Semantic-Enhanced Representation Learning for Road Networks With Temporal Dynamics

• ARTS: A General and Efficient Multi-Task Self-Prompt Framework for Explainable Sequential Recommendation

• LIST: learning to index spatio-textual data for embedding based spatial keyword queries

2024

• PLATON: Top-down R-tree Packing with Learned Partition Policy

• Selectivity Estimation for Queries Containing Predicates over Set-Valued Attributes

• Lemo: A Cache-Enhanced Learned Optimizer for Concurrent Queries

• Nuhuo: An Effective Estimation Model for Traffic Speed Histogram Imputation on A Road Network

• A Comparative Study and Component Analysis of Query Plan Representation Techniques in ML4DB Studies

• TERI: An Effective Framework for Trajectory Recovery with Irregular Time Intervals

• Trajectory Similarity Measurement: An Efficiency Perspective

• Collectively Simplifying Trajectories in a Database: A Query Accuracy Driven Approach

• AdapTraj: A Multi-Source Domain Generalization Framework for Multi-Agent Trajectory Prediction

• SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting

• Quantum Algorithm for Maximum K-Plex Problem

• UnifiedSSR: A Unified Framework of Sequential Search and Recommendation

• MMPOI: A Multi-Modal Content-Aware Framework for POI Recommendations

• AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction

• Zero-shot urban function inference with street view images through prompting a pretrained vision-language model

• On the opportunities and challenges of foundation models for geoai (vision paper)

• City Foundation Models for Learning General Purpose Representations from OpenStreetMap

• On Evaluation Metrics for Diversity-enhanced Recommendations

• Road Network Representation Learning with the Third Law of Geography

2023

• Effectiveness Perspectives and a Deep Relevance Model for Spatial Keyword Queries

• The RLR-Tree: A Reinforcement Learning Based R-Tree for Spatial Data

• Mining Geospatial Relationships from Text

• WISK: A Workload-aware Learned Index for Spatial Keyword Queries

• Towards Designing and Learning Piecewise Space-Filling Curves

• Learned Index Benefits: Machine Learning Based Index Performance Estimation

• Urban Region Representation Learning with OpenStreetMap Building Footprints

• Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning

• Multivariate Time-series Imputation with Disentangled Temporal Representations

• Region Embedding with Intra and Inter-View Contrastive Learning.

2022

• QueryFormer: A Tree Transformer Model for Query Plan Representation

• Example-based Spatial Pattern Matching

• ABC : Attributed Bipartite Co-clustering

• SAM: Database Generation from Query Workload with Supervised Autoregressive Model

• DMCS : Density Modularity based Community Search

• Unsupervised Selectivity Estimation by Integrating Gaussian Mixture Models and Autoregressive Model

• Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation

• Points-of-Interest Relationship Inference with Spatial-enriched Graph Neural Networks

• Entity Resolution with Hierarchical Graph Attention Networks

• Geospatial Entity Resolution

• The Datasets Dilemma: How Much Do We Really Know About Recommendation Datasets?

• Similar Trajectory Search with Spatio-temporal Deep Representation Learning

2021

• A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation

• Robust Road Network Representation Learning: When Traffic Patterns Meet Traveling Semantics

• STAR: A Cache-based Distributed Warehouse System for Spatial Data Streams

• Sinkhorn Collaborative Filtering

• Trajectory Simplification with Reinforcement Learning

• Error-Bounded Online Trajectory Simplification with Multi-Agent Reinforcement Learning

• Location- and keyword-based querying of geo-textual data: a survey

• A Survey on Trajectory Data Management, Analytics, and Learning

• Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting

• A Linear Time Approach to Computing Time Series Similarity based on Deep Metric Learning

2020

• Densely Connected User Community and Location Cluster Search in Location-Based Social Networks

• STAR: A Distributed Stream Warehouse System for Spatial Data (Demo)

• SSTD: A Distributed System on Streaming Spatio-Textual Data

• Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning

• Online Anomalous Trajectory Detection with Deep Generative Sequence Modeling

• Spatial Transition Learning on Road Networks with Deep Probabilistic Models

• Context-aware Deep Model for Joint Mobility and Time Prediction

• HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems

• Structural Relationship Representation Learning with Graph Embedding for Personalized Product Search

• HME: A Hyperbolic Metric Embedding Approach for Next-POI Recommendation

• Global Context Enhanced Graph Nerual Networks for Session-based Recommendation

• PGeoTopic: A Distributed Solution for Mining Geographical Topic Models

• Deterministic Inference of Topic Models via Maximal Latent State Replication

2019

• Computing Trajectory Similarity in Linear Time: A Generic Seed-Guided Neural Metric Learning Approach

• Finding attribute-aware similar regions for data analysis

• Learning Travel Time Distributions with Deep Generative Model

• Effective and Efficient Sports Play Retrieval with Deep Representation Learning

• Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation

• SURGE: Continuous Detection of Bursty Regions Over a Stream of Spatial Objects

• Exploring Market Competition over Topics in Spatio-Temporal Document Collections

2018

• Efficient Selection of Geospatial Data on maps for Interactive Visualized Exploration

• Finding Seeds and Relevant Tags Jointly: For Targeted Influence Maximization in Social Networks

• ANR: Aspect-based Neural Recommender (code )

• Deep Representation Learning for Trajectory Similarity Computation [pdf] (code)

• Inf2vec: Latent Representation Model for Social Influence Embedding

• On Spatial Pattern Matching

• SURGE: Continuous Detection of Bursty Regions over a Stream of Spatial Objects

• Efficient Similar Region Search with Deep Metric Learning

• Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns

• High-dimensional Similarity Learning via Dual-sparse Random Projection

• PANDA: A System for Partial Topology-based Search on Large Networks (Demo)

• Linking Fine-Grained Locations in User Comments

• Reverse k Nearest Neighbor Search over Trajectories

2017

• Distributed Algorithms on Exact Personalized PageRank

• An Experimental Evaluation of Point-of-interest Recommendation in Location-based Social Networks (code and dataset)

• Discovering Fine Grained Pollution Sources and Propagation Patterns in Urban Area

• Biclustering: An application of Dual Topic Models

• Distributed Publish/Subscribe Query Processing on the Spatio-Textual Data Stream

• A General Model for Out-of-town Region Recommendation

• POI2Vec: Geographical Latent Representation for Predicting Future Visitors

• PRED: Periodic Region Detection for Mobility Modeling of Social Media Users

• Analyzing Sentiments in One Go: A Supervised Joint Topic Modeling Approach

• Influence maximization in trajectory databases

• PANDA: Towards Partial Topology-based Search on Large Networks in a Single Machine

2016

• Towards Personalized Maps: Mining User Preferences from Geo-textual Data (Demo website)

• A System for Region Search and Exploration (Demo website)

• Tutorial: Querying Geo-Textual Data: Spatial Keyword Queries and Beyond (Tutorial slides )

• Topic Exploration in Spatio-Temporal Document Collections

• Towards Best Region Search for Data Exploration

• Invited paper: Querying and Mining Geo-textual Data for Exploration: Challenges and Opportunities

• Recognition and Linking of Fine-Grained Locations from Tweets [pdf]

• Annotating Points of Interest with Geo-tagged Tweets

• Efficient Processing of Location-Aware Group Preference Queries

• ConTrack: A Scalable Method For Tracking Multiple Concepts In Large Scale Multidimensional Data

• Learning to Find Topic Experts in Twitter via Different Relations

• A General Recommendation Model for Heterogeneous Networks

2015

• Where you Instagram? Associating Your Instagram Photos with Points of Interest [pdf]

• Rank-GeoFM: A Ranking based Geographical Factorization Method for Point of Interest Recommendation [pdf]

• Diversity-Aware Top-k Publish/Subscribe for Text Stream [pdf]

• Efficient Algorithms for Answering the m-Closest Keywords Query [pdf]

• Temporal Spatial-Keyword Top-k Publish/Subscribe [pdf] (Datasets)

• A General Graph-based Model for Recommendation in Event-based Social Networks [pdf] (Datasets )

• SAR: A Sentiment-Aspect-Region Model for User Preference Analysis in Geo-tagged Reviews [pdf]

• Mining User Intents in Twitter: A Semi-Supervised Approach to Inferring Intent Categories for Tweets [pdf]

• On Information Coverage for Location Category Based Point-of-Interest Recommendation

• DynaDiffuse: A Dynamic Diffusion Model for Continuous Time Constrained Influence Maximization

• A Tri-Role Topic Model for Domain-Specific Question Answering

• Personalized Ranking Metric Embedding for Next New POI Recommendation [pdf]

• Efficient Processing of Spatial Group Keyword Queries

• Who, where, when and what: a nonparametric bayesian approach to context-aware recommendation and search for twitter users. [pdf] (Dataset)

2014

• COM: A Generative Model for Group Recommendation

• Graph-based Point-of-interest Recommendation with Geographical and Temporal Influences (datasets)

• Tagging Your Tweets: A Probabilistic Modeling of Hashtag Annotation in Twitter

• In Search of Influential Event Organizers in Online Social Networks

• Retrieving Regions of Interest for User Exploration

• SOPS: A System for Efficient Processing of Spatial-Keyword Publish/Subscribe

• Coarse-to-Fine Review Selection via Supervised Joint Aspect and Sentiment Model

• Influence Maximization with Novelty Decay in Social Networks

• Distributed Spatial Keyword Querying on Road Networks

• Efficient algorithms and cost models for reverse spatial-keyword k-nearest neighbor search

• Where your photo is taken: Geolocation prediction for social images

2013

• Who, where, when and what: discover spatio-temporal topics for twitter users (datasets)

• Efficient proximity detection among mobile objects in road networks with self-adjustment methods

• An efficient query indexing mechanism for filtering geo-textual data

• Time-aware point-of-interest recommendation (datasets)

• Spatial Keyword Query Processing: An Experimental Evaluation [PDF] (code)

• KORS: Keyword-aware Optimal Route Search System

• Influence Spreading Path and its Application to the Time Constrained Social Influence Maximization Problem and Beyond (Source code )

2012

• Time Constrained Influence Maximization in Social Networks [PDF] ( The algorithm in the ICDM paper is extended to find influential nodes for the traditional influence maximization problem without time constraints, which appears in our TKDE paper. Source code )

• Topic-Driven Reader Comments Summarization

• One seed to find them all: Mining Opinion Features via Association [PDF]

• Keyword-aware Optimal Route Search [PDF]

• Shortest Path and Distance Queries on Road Networks: An Experimental Evaluation.

• SWORS: A System for Efficient Retrieval of Relevant Spatial Web Objects [PDF]

• DISKs: A System for Distributed Spatial Group Keyword Search on Road Networks

• Category Hierarchy Maintenance: A Data-Driven Approach [PDF] Annotated dataset here

• Will This #Hashtag Be Popular Tomorrow?

• Overlapping Decomposition for Causal Graphical Modeling

• Enhancing naive bayes with various smoothing methods for short text classification [PDF]

• Author Name Disambiguation Using a New Categorical Distribution Similarity [PDF]

• Functional Feature Extraction and Chemical Retrieval

• A framework for efficient spatial web object retrieval

• An Evaluation of Classification Models for Question Topic Categorization [PDF]

• Approaches to Exploring Category Information for Question Retrieval inCommunity Question-Answer Archives [PDF]

• 3D Subspace Clustering in Value Investing

2011

• Collective Spatial Keyword Querying. [PDF] (Source code here )

• Reverse Spatial and Textual k Nearest Neighbor Search [PDF]

• Simulated Annealing based Influence Maximization in Social Networks

• Integrating Community Question and Answer Archives

• Efficient Continuously Moving Top-K Spatial Keyword Query Processing

• On the Complexity of View Update Analysis and its Application to Annotation Propagation

• Partial Evaluation for Distributed XPath Query Processing and Beyond

• Joint Top-K Spatial Keyword Query Processing,

• A Survey on Enhanced Subspace Clustering

• Centroid-based Actionable 3D Subspace Clustering

2010

• Retrieving Top-k Prestige-Based Relevant Spatial Web Objects

• Mining Significant Semantic Locations From GPS Data,

• Exploring Domain-specific Term Weight in Archived Question Search.

• Community-based Greedy Algorithm for Mining Top-K Influential Nodes in Mobile Social Networks [PDF]

• A Generalized Framework of Exploring Category Information for Question Retrieval in Community Question Answer Archives. (supplementary materials on dataset)

• Evolutionary Taxonomy Construction from Dynamic Tag Space

• Using Transactional Data from ERP Systems for Expert Finding [PDF]

• Content-enriched Classifier for Web Video Classification

• ISIS: A New Approach for Efficient Similarity Search in Sparse Databases

2009

• Efficient Algorithms for Computing Link-based Similarity in Real World Networks.

• The Use of Categorization Information in Language Models for Question Retrieval. (supplementary materials on dataset)

• Efficient Retrieval of the Top-k Most Relevant Spatial Web Objects

• Routing Questions to Right Users in Online Communities

• A Revisit of Query Expansion with Different Semantic Levels

2008

• Finding Question-Answer Pairs from Online Forums

• Using Conditional Random Fields to Extract Contexts and Answers of Questions from Online Forums. (supplementary materials on data)

• Semantic Similarity Based on Compact Concept Ontology.

• Updating Recursive XML Views of Relations.

2007

• Improving Data Quality: Consistency and Accuracy.

• Query and Update Through XML Views.

• Query XML with Update Syntax.

• Distributed Query Evaluation with Performance Guarantees.

• Detecting Erroneous Sentences using labeled sequential Patterns and Tree Patterns.

• Detecting Erroneous Sentences using Automatically Mined Sequential Patterns.

• Updating recursive XML views of relations.

2006

• Annotation Propagation Revisited for Key Preserving Views.

• Using Partial Evaluation in Distributed Query Evaluation.

• Composite Acoustic Features for Efficient Music Similarity Query.

• An Estimation System for XPath Expressions.

• Summarizing frequent patterns using profiles.

2005

• Mining Top-k Covering Rule Groups for Gene Expression Data.

• On effective E-mail Classification via Neural Networks.

2004

• Mining Frequent Closed Patterns in Microarray Data.

• Large Incremental Maintenance of Quotient Cube for Sum and Median.

• Semantic Mining and Analysis of Gene Expression Data (Demo).

• FARMER: Fining Interesting Association Rule Groups by Row Enumeration in Biological Datasets.

• COBBLER: Combining Column and Row Enumeration for Closed Pattern Discovery.

• Go Green: Recycle and Reuse Frequent Patterns.

• Semi-Supervised Text Classification Using Partitioned EM.

2003

• CARPENTER: Finding Closed Patterns in Long Biological Datasets.

2002

• Speed-up Iterative Frequent Itemset Mining with Constraint Changes

• Discovering frequent substructures from hierarchical semi-structured data.