[
https://issues.apache.org/jira/browse/COMDEV-472?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Bertty Contreras updated COMDEV-472:
------------------------------------
Priority: Critical (was: Major)
> Apache Wayang(Incubating): AI Data Generator for Cost model Calibration
> -----------------------------------------------------------------------
>
> Key: COMDEV-472
> URL: https://issues.apache.org/jira/browse/COMDEV-472
> Project: Community Development
> Issue Type: New Feature
> Components: GSoC/Mentoring ideas
> Reporter: Bertty Contreras
> Priority: Critical
> Labels: gsoc, gsoc2022, machine_learning
> Original Estimate: 5h 50m
> Remaining Estimate: 5h 50m
>
> *Synopsis*
> The current Apache Wayang (Incubating) uses a cost model to select the right
> set of platforms while optimizing the query plans. Nevertheless, the accuracy
> of picking the correct configuration depends on the cost model's quality; The
> idea is to build an AI pipeline capable of generating data for the current
> profiler of Apache Wayang (Incubating), where another AI component is the
> main component for the calibration process.
>
> *Benefits to Community*
> The benefits for the community will be the option of having a well-calibrated
> cost model for their environments with low human effort. Being cost modelling
> one of the most difficult tasks, having such an AI pipeline will enrich
> users’ experience when using Apache Wayang (Incubating).
>
> *Deliverables*
> The delivery expected is an adaptation of the paper "Expand your Training
> Limits! Generating Training Data for ML-based Data Management" [1], where the
> authors assume an ML-Cost-Model, but in this case, the idea needs
> modifications to run in the current setup of Apache Wayang(Incubating).
>
> The expected steps are the following:
> * Understand the paper [1]
> * Get Into the current process of the profiler of Apache Wayang (Incubating)
> * Design the AI profile pipeline, based on [1] and the current profiler
> * Discuss ideas on how to integrate the designed AI pipeline into Apache
> Wayang(Incubating)
> * Implement the AI-DataGenerator Component
>
> *Related Work*
> [1] [Expand your Training Limits! Generating Training Data for ML-based Data
> Management|https://www.agora-ecosystem.com/publications_pdf/expand_training_limits.pdf]
> [2] [RHEEMix in the data jungle: a cost-based optimizer for cross-platform
> systems]([https://wayang.apache.org/assets/pdf/paper/journal_vldb.pdf])
>
> *Biographical Information*
>
> Bertty Contreras-Rojas is a Senior Software Engineer at Databloom Inc. He is
> one of the PPMC of Apache Wayang(Incubating). He has many years of experience
> developing intensive processing data systems for several industries, such as
> banking systems. He was a research engineer at the Qatar Computing Research
> Institute, where he was responsible for developing the declarative query
> engine for Rheem and adding new underlying platforms to Rheem.
>
> Rodrigo Pardo-Meza is a Senior Software Engineer at Databloom Inc. He is one
> of the PPMC of Apache Wayang(Incubating). He has many years of experience
> developing applications that support Big Data processing, with experience
> implementing ETL processes over distributed systems to optimize inventories
> in supply chains. He was a research engineer at the Qatar Computing Research
> Institute, where he specialized in human interface interaction with big data
> analytics. During this time, he co-develop an ML-based cross-platform query
> optimizer.
>
> Jorge Quiané is the head of the Big Data Systems research group at the Berlin
> Institute for the Foundations of Learning and Data (BIFOLD) and a Principal
> Researcher at DIMA (TU Berlin). He also acts as the Scientific Coordinator of
> the IAM group at the German Research Center for ArtificialIntelligence
> (DFKI). His current research is in the broad area of big data: mainly in
> federated data analytics, scalable data infrastructures, and distributed
> query processing. He has published numerous research papers on data
> management and novel system architectures. He has recently been honoured with
> the 2022 ACM SIGMOD Research Highlight Award and the Best Paper Award at ICDE
> 2021 for his work on “EfficientControl Flow in Dataflow Systems”. He holds
> five patents in core database areas and on machine learning. Earlier in his
> career, he was a Senior Scientist at the Qatar Computing Research Institute
> (QCRI) and a Postdoctoral Researcher at Saarland University. He obtained his
> PhD in computer science from INRIA (Nantes University).
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
