2 citations · 3 across the 4 of their papers we have counts for
7 papers
Nexus: Inferring Join Graphs from Metadata Alone via Iterative Low-Rank Matrix Completion
Tianji Cong, Yuanyuan Tian, Andreas Mueller +5
Automatically inferring join relationships is a critical task for effective data discovery, integration, querying and reuse. However, accurately and efficiently identifying these r…
SemBench: A Benchmark for Semantic Query Processing Engines
Jiale Lao, Andreas Zimmerer, Olga Ovcharenko +12
We present a benchmark targeting a novel class of systems: semantic query processing engines. Those systems rely inherently on generative and reasoning capabilities of state-of-the…
OpenForge: Probabilistic Metadata Integration
Tianji Cong, Fatemeh Nargesian, Junjie Xing +1
Modern data stores increasingly rely on metadata for enabling diverse activities such as data cataloging and search. However, metadata curation remains a labor-intensive task, and…
Observatory: Characterizing Embeddings of Relational Tables
Tianji Cong, Madelon Hulsebos, Zhenjie Sun +2
Language models and specialized table embedding models have recently demonstrated strong performance on many tasks over tabular data. Researchers and practitioners are keen to leve…
Pylon: Semantic Table Union Search in Data Lakes
Tianji Cong, Fatemeh Nargesian, H. V. Jagadish
The large size and fast growth of data repositories, such as data lakes, has spurred the need for data discovery to help analysts find related data. The problem has become challeng…
WarpGate: A Semantic Join Discovery System for Cloud Data Warehouses
Tianji Cong, James Gale, Jason Frantz +2
Data discovery is a major challenge in enterprise data analysis: users often struggle to find data relevant to their analysis goals or even to navigate through data across data sou…
Can Attention Masks Improve Adversarial Robustness?
Pratik Vaishnavi, Tianji Cong, Kevin Eykholt +2
Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear n…