Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples

December 10, 2019 Β· Declared Dead Β· πŸ› International Conference on Intelligent User Interfaces

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Angie Boggust, Brandon Carter, Arvind Satyanarayan arXiv ID 1912.04853 Category cs.HC: Human-Computer Interaction Cross-listed cs.CL, cs.LG Citations 76 Venue International Conference on Intelligent User Interfaces Last Checked 3 months ago
Abstract
Embeddings mapping high-dimensional discrete input to lower-dimensional continuous vector spaces have been widely adopted in machine learning applications as a way to capture domain semantics. Interviewing 13 embedding users across disciplines, we find comparing embeddings is a key task for deployment or downstream analysis but unfolds in a tedious fashion that poorly supports systematic exploration. In response, we present the Embedding Comparator, an interactive system that presents a global comparison of embedding spaces alongside fine-grained inspection of local neighborhoods. It systematically surfaces points of comparison by computing the similarity of the $k$-nearest neighbors of every embedded object between a pair of spaces. Through case studies across multiple modalities, we demonstrate our system rapidly reveals insights, such as semantic changes following fine-tuning, language changes over time, and differences between seemingly similar models. In evaluations with 15 participants, we find our system accelerates comparisons by shifting from laborious manual specification to browsing and manipulating visualizations.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Human-Computer Interaction

Died the same way β€” πŸ‘» Ghosted