Towards Human-Guided Machine Learning
Authors
Automated Machine Learning (AutoML) systems are emerging that automatically search for possible solutions from a large space of possible kinds of models. Although fully automated machine learning is appropriate for many applications, users often have knowledge that supplements and constraints the available data and solutions. This paper proposes human-guided machine learning (HGML) as a hybrid approach where a user interacts with an AutoML system and tasks it to explore different problem settings that reflect the user’s knowledge about the data available. We present: 1) a task analysis of HGML that shows the tasks that a user would want to carry out, 2) a characterization of two scientific publications, one in neuroscience and one in political science, in terms of how the authors would search for solutions using an AutoML system, 3) requirements for HGML based on those characterizations, and 4) an assessment of existing AutoML systems in terms of those requirements.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 83%
Genie in the Model: Automatic Generation of Human-in-the-Loop Deep Neural Networks for Mobile Applications
UbiComp '23· Human-LLM Collaboration +2
- 71%
Never-ending Learning of User Interfaces
UIST '23· Human-LLM Collaboration +2
- 67%
Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communication
CHI '23· Human-LLM Collaboration +1
- 67%
Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
CHI '24· Human-LLM Collaboration +1
- 67%
VAL: Interactive Task Learning with GPT Dialog Parsing
CHI '24· Human-LLM Collaboration +1
- 67%
Need Help? Designing Proactive AI Assistants for Programming
CHI '25· Human-LLM Collaboration +1
- 67%
InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs
CHI '25· Human-LLM Collaboration +1
- 67%
Interactive Hyperparameter Optimization with Paintable Timelines
DIS '21· Human-LLM Collaboration +1
- 67%
Decision rule elicitation for domain adaptation
IUI '21· Human-LLM Collaboration +1
- 67%
Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation
IUI '25· Human-LLM Collaboration +1
Based on Jaccard similarity of research subtopics & professions (≥60%)