Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins

06/02/2021
by   Sahaana Suri, et al.
13

Structured data, or data that adheres to a pre-defined schema, can suffer from fragmented context: information describing a single entity can be scattered across multiple datasets or tables tailored for specific business needs, with no explicit linking keys (e.g., primary key-foreign key relationships or heuristic functions). Context enrichment, or rebuilding fragmented context, using keyless joins is an implicit or explicit step in machine learning (ML) pipelines over structured data sources. This process is tedious, domain-specific, and lacks support in now-prevalent no-code ML systems that let users create ML pipelines using just input data and high-level configuration files. In response, we propose Ember, a system that abstracts and automates keyless joins to generalize context enrichment. Our key insight is that Ember can enable a general keyless join operator by constructing an index populated with task-specific embeddings. Ember learns these embeddings by leveraging Transformer-based representation learning techniques. We describe our core architectural principles and operators when developing Ember, and empirically demonstrate that Ember allows users to develop no-code pipelines for five domains, including search, recommendation and question answering, and can exceed alternatives by up to 39 configuration change.

READ FULL TEXT

page 1

page 2

page 5

page 11

research
06/11/2019

Toward Best Practices for Explainable B2B Machine Learning

To design tools and data pipelines for explainable B2B machine learning ...
research
05/04/2023

ExeKGLib: Knowledge Graphs-Empowered Machine Learning Analytics

Many machine learning (ML) libraries are accessible online for ML practi...
research
04/01/2020

Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution

The deployment of Machine Learning (ML) models is a difficult and time-c...
research
06/25/2021

Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search

Recent work has made significant progress in helping users to automate s...
research
04/19/2023

Towards Building Child-Centered Machine Learning Pipelines: Use Cases from K-12 and Higher-Education

Researchers and policy-makers have started creating frameworks and guide...
research
07/08/2019

Quantifying Transparency of Machine Learning Systems through Analysis of Contributions

Increased adoption and deployment of machine learning (ML) models into b...
research
02/02/2023

Predefined domain specific embeddings of food concepts and recipes: A case study on heterogeneous recipe datasets

Although recipe data are very easy to come by nowadays, it is really har...

Please sign up or login with your details

Forgot password? Click here to reset