A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
embComp: Visual Interactive Comparison of Vector Embeddings
[article]
2019
arXiv
pre-print
Preserved Fulltext
Other Versions
This work introduces embComp, a novel approach for comparing two embeddings that capture the similarity between objects, such as word and document embeddings. ...
Detail views allow comparison of the local structure around selected objects and relating this local information to the global views. ...
VISUAL INTERACTIVE EMBEDDING COMPARISON The previously described overviews build the core of our approach for embedding comparison. ...
arXiv:1911.01542v1
fatcat:5bkrti4bfbhwdm7pavpokypgcu
VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
on the word vectors using dimensionality reduction and interactive visual exploration. ...
In this paper, we utilize interactive visualization to increase the interpretability and accessibility of a collection of state-of-the-art debiasing techniques. ...
CONCLUSIONS AND DISCUSSIONS This paper presents VERB, a new tool for visualizing, interacting with, and teaching embedded representations of data. ...
arXiv:2104.02797v1
fatcat:htizaqvn2vdyzhxaef6umscz7a
Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
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. ...
[23] developed the embedding comparison system empComp. embComp facilitates top-down comparison of embeddings by displaying summary visualizations of embedding space differences and employing interaction ...
arXiv:1912.04853v3
fatcat:zfool6r745hlpef4nu7tl3gxi4
Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2202.02641v1 fatcat:t23n7cmnyzb4zccrwjdydopoce
Emblaze uses an animated, interactive scatter plot with a novel Star Trail augmentation to enable visual comparison. ...
Through a series of case studies with ML experts, we demonstrate how interactive comparison with Emblaze can help gain new insights into embedding space structure. ...
We thank Carolyn Rosé, Jill Lehman, Denis Newman-Griffis, and Dominik Moritz for their valuable feedback throughout the development of Emblaze. ...
arXiv:2202.02641v2
fatcat:sndccrscgzcmlh2hag7fqt6yfu
Comparing and Exploring High-Dimensional Data with Dimensionality Reduction Algorithms and Matrix Visualizations
2020
Proceedings of the International Conference on Advanced Visual Interfaces
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Figure 1 : The scatterplots in (a) and (c) visualize the dimensionality reduced representations of two distinct subspaces of a high-dimensional dataset. ...
ABSTRACT We propose Compadre, a tool for visual analysis for comparing distances of high-dimensional (HD) data and their low-dimensional projections. ...
EmbComp [20] is a recent approach that seeks to bridge the usage of metrics and interactive visual analysis for analyzing different word embeddings. ...
doi:10.1145/3399715.3399875
dblp:conf/avi/CuturaAFS20
fatcat:oehwih6ugncv7pkujwbw2vk5we