Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking
This addresses the challenge of expensive hand-labeled metadata for database organization, offering a tool for novice users to interactively assess and organize large datasets, though it appears incremental as it builds on interactive ranking methods.
The paper tackles the problem of organizing large databases by learning low-dimensional continuous criteria through interactive ranking, enabling novice users to describe relative ordering of examples, and demonstrates the tool's efficiency in organizing thousands of data points along 1D and 2D sliders.
Large databases are often organized by hand-labeled metadata, or criteria, which are expensive to collect. We can use unsupervised learning to model database variation, but these models are often high dimensional, complex to parameterize, or require expert knowledge. We learn low-dimensional continuous criteria via interactive ranking, so that the novice user need only describe the relative ordering of examples. This is formed as semi-supervised label propagation in which we maximize the information gained from a limited number of examples. Further, we actively suggest data points to the user to rank in a more informative way than existing work. Our efficient approach allows users to interactively organize thousands of data points along 1D and 2D continuous sliders. We experiment with datasets of imagery and geometry to demonstrate that our tool is useful for quickly assessing and organizing the content of large databases.