Exploiting Machine Learning Models for Approximate Query Processing

Lee, Taewhi; Nam, Ki-Hyuk; Park, Choon Seo; Kim, Sung‐Soo

doi:10.1109/bigdata55660.2022.10020252

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond traditional domains, GDMs have been utilized in graph generation [45][46][47], molecular and material generation [48][49][50], and in synthesizing tabular data to electrocardiogram signal synthesis [51][52][53]. The widespread adoption of GDMs can be attributed to several key advantages over other GenAI methods.…”

Section: Ai-generated Content Servicesmentioning

confidence: 99%

See 1 more Smart Citation

Semantic communications and generative artificial intelligence for user-centric metaverse services

View full text Add to dashboard Cite

First and foremost, I extend my deepest thanks to my supervisor, Professor Dusit Niyato. From my perspective, he exemplifies the ideal doctoral advisor, combining the roles of a mentor, guide, and friend with his unwavering commitment, genuine passion for research, steadfast support, and selfless mentorship. His consistent dedication to his students' best interests has greatly motivated my pursuit of research excellence and desire to contribute to the scientific community.I am indebted to my Thesis Advisory Committee, Prof. Soong Boon Hee and Prof.Rui Tan, for their invaluable guidance, insightful critiques, and encouragement throughout my doctoral journey. My heartfelt thanks go to all my collaborators who have contributed immensely to my research and growth: Prof. Abbas

show abstract

Section: Ai-generated Content Servicesmentioning

confidence: 99%

“…• Handles discrete data types effectively, as seen in MolDiff for molecular generation [48] and TabDDPM for tabular data synthesis [52]. The models presented in CoDi [51], TabDDPM [52], and DiffECG [53] have demonstrated the versatility of GDMs in tasks ranging from synthesizing tabular data to ECG signal synthesis.…”

Section: Othersmentioning

confidence: 99%

Semantic communications and generative artificial intelligence for user-centric metaverse services

View full text Add to dashboard Cite

show abstract

A Framework for Learned Approximate Query Processing for Tabular Data with Trajectory

Nam,

Kim,

Park

et al. 2023

2023 14th International Conference on Information and Communication Technology Convergence (ICTC)

View full text Add to dashboard Cite

PairwiseHist: Fast, Accurate and Space-Efficient Approximate Query Processing with Data Compression

Hurst,

Lucani,

Zhang

2024

Proc. VLDB Endow.

View full text Add to dashboard Cite

Exponential growth in data collection is creating significant challenges for data storage and analytics latency. Approximate Query Processing (AQP) has long been touted as a solution for accelerating analytics on large datasets, however, there is still room for improvement across all key performance criteria. In this paper, we propose a novel histogram-based data synopsis called PairwiseHist that uses recursive hypothesis testing to ensure accurate histograms and can be built on top of data compressed using Generalized Deduplication (GD). We thus show that GD data compression can contribute to AQP. Compared to state-of-the-art AQP approaches, Pairwise-Hist achieves better performance across all key metrics, including 2.6× higher accuracy, 3.5× lower latency, 24× smaller synopses and 1.5--4× faster construction time.

show abstract

Exploiting Machine Learning Models for Approximate Query Processing

Cited by 3 publications

References 9 publications

Semantic communications and generative artificial intelligence for user-centric metaverse services

Semantic communications and generative artificial intelligence for user-centric metaverse services

A Framework for Learned Approximate Query Processing for Tabular Data with Trajectory

PairwiseHist: Fast, Accurate and Space-Efficient Approximate Query Processing with Data Compression

Contact Info

Product

Resources

About