Forgetting and consolidation for incremental and cumulative knowledge acquisition systems

TL;DR

This paper introduces a novel incremental knowledge acquisition system that employs forgetting and consolidation mechanisms, inspired by cognitive processes, to improve long-term learning and avoid redundancy in knowledge bases.

Contribution

It presents a new framework that applies metrics based on the MML principle to manage rule retention, forgetting, and consolidation in an incremental learning system.

Findings

Effective rule management in chess domain

Improved knowledge stability and plasticity

Demonstrated long-term learning benefits

Abstract

The application of cognitive mechanisms to support knowledge acquisition is, from our point of view, crucial for making the resulting models coherent, efficient, credible, easy to use and understandable. In particular, there are two characteristic features of intelligence that are essential for knowledge development: forgetting and consolidation. Both plays an important role in knowledge bases and learning systems to avoid possible information overflow and redundancy, and in order to preserve and strengthen important or frequently used rules and remove (or forget) useless ones. We present an incremental, long-life view of knowledge acquisition which tries to improve task after task by determining what to keep, what to consolidate and what to forget, overcoming The Stability-Plasticity dilemma. In order to do that, we rate rules by introducing several metrics through the first adaptation, to our knowledge, of the Minimum Message Length (MML) principle to a coverage graph, a hierarchical assessment structure which treats evidence and rules in a unified way. The metrics are not only used to forget some of the worst rules, but also to set a consolidation process to promote those selected rules to the knowledge base, which is also mirrored by a demotion system. We evaluate the framework with a series of tasks in a chess rule learning domain.