Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories

TL;DR

This paper introduces MOCHA, an interactive machine learning tool that leverages human concept learning theories and cognitive insights to improve model training and user understanding through counterfactual data and batch annotation.

Contribution

It combines neuro-symbolic data generation and structural alignment theory to enhance co-adaptive machine teaching, supported by a user study.

Findings

MOCHA improves model learning efficiency.

Users better understand model behavior and data concepts.

The tool is effective and usable in practice.

Abstract

An important challenge in interactive machine learning, particularly in subjective or ambiguous domains, is fostering bi-directional alignment between humans and models. Users teach models their concept definition through data labeling, while refining their own understandings throughout the process. To facilitate this, we introduce MOCHA, an interactive machine learning tool informed by two theories of human concept learning and cognition. First, it utilizes a neuro-symbolic pipeline to support Variation Theory-based counterfactual data generation. By asking users to annotate counterexamples that are syntactically and semantically similar to already-annotated data but predicted to have different labels, the system can learn more effectively while helping users understand the model and reflect on their own label definitions. Second, MOCHA uses Structural Alignment Theory to present groups of counterexamples, helping users comprehend alignable differences between data items and annotate them in batch. We validated MOCHA's effectiveness and usability through a lab study with 18 participants.