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

12/10/2019
by   Angie Boggust, et al.
0

Embeddings – mappings from high-dimensional discrete input to lower-dimensional continuous vector spaces – have been widely adopted in machine learning, linguistics, and computational biology as they often surface interesting and unexpected domain semantics. Through semi-structured interviews with embedding model researchers and practitioners, we find that current tools poorly support a central concern: comparing different embeddings when developing fairer, more robust models. In response, we present the Embedding Comparator, an interactive system that balances gaining an overview of the embedding spaces with making fine-grained comparisons of local neighborhoods. For a pair of models, we compute the similarity of the k-nearest neighbors of every embedded object, and visualize the results as Local Neighborhood Dominoes: small multiples that facilitate rapid comparisons. Using case studies, we illustrate the types of insights the Embedding Comparator reveals including how fine-tuning embeddings changes semantics, how language changes over time, and how training data differences affect two seemingly similar models.

READ FULL TEXT

page 1

page 5

page 7

page 8

page 9

page 10

research
11/05/2019

embComp: Visual Interactive Comparison of Vector Embeddings

This work introduces embComp, a novel approach for comparing two embeddi...
research
05/28/2019

Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae

Embeddings are a fundamental component of many modern machine learning a...
research
02/05/2022

Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces

Modern machine learning techniques commonly rely on complex, high-dimens...
research
11/16/2016

Embedding Projector: Interactive Visualization and Interpretation of Embeddings

Embeddings are ubiquitous in machine learning, appearing in recommender ...
research
06/26/2022

Locked and unlocked smooth embeddings of surfaces

We study the continuous motion of smooth isometric embeddings of a plana...
research
03/31/2020

Information Leakage in Embedding Models

Embeddings are functions that map raw input data to low-dimensional vect...
research
08/17/2022

Visual Comparison of Language Model Adaptation

Neural language models are widely used; however, their model parameters ...

Please sign up or login with your details

Forgot password? Click here to reset