Search Results - "Huang, Zezhou"

Spatial and hedonic analysis of housing prices in Shanghai by Huang, Zezhou, Chen, Ruishan, Xu, Di, Zhou, Wei

“…•12, 732 valid house property information was collected with web crawler in Shanghai.•Strong spatial auto-correlation exists in housing price with Moran’s I of…”
Get full text

Disambiguate Entity Matching using Large Language Models through Relation Discovery by Huang, Zezhou

“…Entity matching is a critical challenge in data integration and cleaning, central to tasks like fuzzy joins and deduplication. Traditional approaches have…”
Get full text

Relationalizing Tables with Large Language Models: The Promise and Challenges by Huang, Zezhou, Wu, Eugene

“…Tables in the wild are usually not relationalized, making querying them difficult. To relationalize tables, recent works designed seven transformation…”
Get full text

Cocoon: Semantic Table Profiling Using Large Language Models by Huang, Zezhou, Wu, Eugene

“…Data profilers play a crucial role in the preprocessing phase of data analysis by identifying quality issues such as missing, extreme, or erroneous values…”
Get full text

Lightweight Materialization for Fast Dashboards Over Joins by Huang, Zezhou, Wu, Eugene

“…SIGMOD 2024 Dashboards are vital in modern business intelligence tools, providing non-technical users with an interface to access comprehensive business data…”
Get full text

Calibration: A Simple Trick for Wide-table Delta Analytics by Huang, Zezhou, Wu, Eugene

“…Data analytics over normalized databases typically requires computing and materializing expensive joins (wide-tables). Factorized query execution models…”
Get full text

Data Cleaning Using Large Language Models by Zhang, Shuo, Huang, Zezhou, Wu, Eugene

“…Data cleaning is a crucial yet challenging task in data analysis, often requiring significant manual effort. To automate data cleaning, previous systems have…”
Get full text

Reptile: Aggregation-level Explanations for Hierarchical Data by Huang, Zezhou, Wu, Eugene

“…Recent query explanation systems help users understand anomalies in aggregation results by proposing predicates that describe input records that, if deleted,…”
Get full text

Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL by Huang, Zezhou, Damalapati, Pavan Kalyan, Wu, Eugene

“…Text-to-SQL allows experts to use databases without in-depth knowledge of them. However, real-world tasks have both query and data ambiguities. Most works on…”
Get full text

The Fast and the Private: Task-based Dataset Search by Huang, Zezhou, Liu, Jiaxiang, Wang, Haonan, Wu, Eugene

“…Modern dataset search platforms employ ML task-based utility metrics instead of relying on metadata-based keywords to comb through extensive dataset…”
Get full text

JoinBoost: Grow Trees Over Normalized Data Using Only SQL by Huang, Zezhou, Sen, Rathijit, Liu, Jiaxiang, Wu, Eugene

“…VLDB 2023 Although dominant for tabular data, ML libraries that train tree models over normalized databases (e.g., LightGBM, XGBoost) require the data to be…”
Get full text

Aggregation Consistency Errors in Semantic Layers and How to Avoid Them by Huang, Zezhou, Damalapati, Pavan Kalyan, Wu, Eugene

“…Proceedings of the Workshop on Human-In-the-Loop Data Analytics 2023 Analysts often struggle with analyzing data from multiple tables in a database due to…”
Get full text

Kitana: Efficient Data Augmentation Search for AutoML by Huang, Zezhou, Subramaniam, Pranav, Fernandez, Raul Castro, Wu, Eugene

“…AutoML services provide a way for non-expert users to benefit from high-quality ML models without worrying about model design and deployment, in exchange for a…”
Get full text

Saibot: A Differentially Private Data Search Platform by Huang, Zezhou, Liu, Jiaxiang, Alabi, Daniel, Fernandez, Raul Castro, Wu, Eugene

“…VLDB 2023 Recent data search platforms use ML task-based utility measures rather than metadata-based keywords, to search large dataset corpora. Requesters…”
Get full text