Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916684507381760 |
|---|---|
| author | Gebreegziabher, Simret Araya Yang, Yukun Glassman, Elena L. Li, Toby Jia-Jun |
| author_facet | Gebreegziabher, Simret Araya Yang, Yukun Glassman, Elena L. Li, Toby Jia-Jun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16561 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories Gebreegziabher, Simret Araya Yang, Yukun Glassman, Elena L. Li, Toby Jia-Jun Human-Computer Interaction 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. |
| title | Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2409.16561 |