Goal-Driven Sequential Data Abstraction

TL;DR

This paper introduces a reinforcement learning framework for goal-driven sequential data abstraction that can adapt to different domains and preservation goals without relying on human examples.

Contribution

It presents a novel, domain-agnostic reinforcement learning approach for sequential data abstraction that is flexible and does not depend on human-labeled training data.

Findings

Effective across sketch, video, and text data domains.

Achieves promising results in preserving data aspects according to goals.

Processes input holistically without order constraints.

Abstract

Automatic data abstraction is an important capability for both benchmarking machine intelligence and supporting summarization applications. In the former one asks whether a machine can `understand' enough about the meaning of input data to produce a meaningful but more compact abstraction. In the latter this capability is exploited for saving space or human time by summarizing the essence of input data. In this paper we study a general reinforcement learning based framework for learning to abstract sequential data in a goal-driven way. The ability to define different abstraction goals uniquely allows different aspects of the input data to be preserved according to the ultimate purpose of the abstraction. Our reinforcement learning objective does not require human-defined examples of ideal abstraction. Importantly our model processes the input sequence holistically without being constrained by the original input order. Our framework is also domain agnostic -- we demonstrate applications to sketch, video and text data and achieve promising results in all domains.