A Pattern Language for Machine Learning Tasks

TL;DR

This paper introduces a unified, graph-based framework for defining and optimizing machine learning tasks as equality constraints, enabling model-agnostic behavior control and practical data manipulation without complex training procedures.

Contribution

It formalizes tasks as constraints, develops a graphical mathematics for them, and demonstrates a novel data editing method that is model-agnostic and efficient.

Findings

Framework unifies diverse ML approaches

Enables model-agnostic behavior design

Successful implementation of a data manipulation task

Abstract

We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our theoretical framework, we exhibit and implement a novel "manipulator" task that minimally edits input data to have a desired attribute. Our model-agnostic approach achieves this end-to-end, and without the need for custom architectures, adversarial training, random sampling, or interventions on the data, hence enabling capable, small-scale, and training-stable models.