Representation Independent Analytics Over Structured Data

TL;DR

This paper introduces the concept of representation independence in database analytics, aiming to develop algorithms effective across various data structures, and empirically evaluates existing algorithms' independence levels.

Contribution

The paper formalizes the notion of representation independence and analyzes its properties for a range of data analytics algorithms, highlighting their limitations and potential for generalization.

Findings

Most algorithms are not inherently representation independent.

Certain heuristics exhibit greater representation independence under specific conditions.

Empirical analysis reveals the varying degrees of independence among popular algorithms.

Abstract

Database analytics algorithms leverage quantifiable structural properties of the data to predict interesting concepts and relationships. The same information, however, can be represented using many different structures and the structural properties observed over particular representations do not necessarily hold for alternative structures. Thus, there is no guarantee that current database analytics algorithms will still provide the correct insights, no matter what structures are chosen to organize the database. Because these algorithms tend to be highly effective over some choices of structure, such as that of the databases used to validate them, but not so effective with others, database analytics has largely remained the province of experts who can find the desired forms for these algorithms. We argue that in order to make database analytics usable, we should use or develop algorithms that are effective over a wide range of choices of structural organizations. We introduce the notion of representation independence, study its fundamental properties for a wide range of data analytics algorithms, and empirically analyze the amount of representation independence of some popular database analytics algorithms. Our results indicate that most algorithms are not generally representation independent and find the characteristics of more representation independent heuristics under certain representational shifts.