<i>embComp</i>: Visual Interactive Comparison of Vector Embeddings

Heimerl, Florian; Kralj, Christoph; Möller, Torsten B.; Gleicher, Michael

doi:10.1109/tvcg.2020.3045918

Cited by 18 publications

(20 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xia et al [11] introduce a technique for finding clusters and outliers in embeddings based on successive projections that maximize a marked pattern's saliency. Other tools focus on the interactive comparison of embeddings, based on dissimilarity matrices [12], linking clusters between embeddings [13], or visualizations of neighborhood overlap [14].…”

Section: Exploration Of Embedding Spacesmentioning

confidence: 99%

“…In EmbeddingVis [31], users are offered multiple embeddings for comparison and to examine which properties the embeddings value. Comparison of embeddings is also the focus of the work by Heimerl et al [14] and Boggust et al [32], in which they compare two embeddings and their local neighborhoods. GNNVIS by Jin et al [33] lets users analyze graph neural networks and their prediction results with multiple views that summarize node-level metrics, structure, and data.…”

Section: Network Embeddingsmentioning

confidence: 99%

See 1 more Smart Citation

Visual Exploration of Relationships and Structure in Low-Dimensional Embeddings

Eckelt

Hinterreiter

Adelberger

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

In this work, we propose an interactive visual approach for the exploration and formation of structural relationships in embeddings of high-dimensional data. These structural relationships, such as item sequences, associations of items with groups, and hierarchies between groups of items, are defining properties of many real-world datasets. Nevertheless, most existing methods for the visual exploration of embeddings treat these structures as second-class citizens or do not take them into account at all. In our proposed analysis workflow, users explore enriched scatterplots of the embedding, in which relationships between items and/or groups are visually highlighted. The original high-dimensional data for single items, groups of items, or differences between connected items and groups is accessible through additional summary visualizations. We carefully tailored these summary and difference visualizations to the various data types and semantic contexts. During their exploratory analysis, users can externalize their insights by setting up additional groups and relationships between items and/or groups. We demonstrate the utility and potential impact of our approach by means of two use cases and multiple examples from various domains.

show abstract

Section: Exploration Of Embedding Spacesmentioning

confidence: 99%

Section: Network Embeddingsmentioning

confidence: 99%

Visual Exploration of Relationships and Structure in Low-Dimensional Embeddings

Eckelt

Hinterreiter

Adelberger

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…Ghosh et al [28] developed VisExPres, an interactive toolkit for user-driven evaluation of embeddings. Heimerl et al [29] compare embeddings based on different quantitative metrics, while Cutura et al does so with dimensional reduction techniques and matrix visualizations [30]. Liu et al [31] analogize the process of mapping and comparing semantic dimensions within latent spaces to latent space cartography.…”

Section: Latent Space Interpretermentioning

confidence: 99%

Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding

Liu

Wang

Bernard

et al. 2022

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Graph neural networks (GNNs) are a class of powerful machine learning tools that model node relations for making predictions of nodes or links. GNN developers rely on quantitative metrics of the predictions to evaluate a GNN, but similar to many other neural networks, it is difficult for them to understand if the GNN truly learns characteristics of a graph as expected. We propose an approach to corresponding an input graph to its node embedding (aka latent space), a common component of GNNs that is later used for prediction. We abstract the data and tasks, and develop an interactive multi-view interface called CorGIE to instantiate the abstraction. As the key function in CorGIE, we propose the K-hop graph layout to show topological neighbors in hops and their clustering structure. To evaluate the functionality and usability of CorGIE, we present how to use CorGIE in two usage scenarios, and conduct a case study with two GNN experts. Availability: Open-source code, supplemental materials & video at https://osf.io/tr3sb/.

show abstract

“…The key to visual analysis is a matrix visualization for representing the discrepancy between distance matrices, which are linked with 2D scatter plot projections of the data. Heimerl et al [34] introduced an interactive visualisation approach of embComp for comparing two embeddings that capture the similarity between objects, such as word and document embeddings. The proposed approach features overview visualizations that are based on metrics for measuring differences in the local structure around objects and detailed views allowing comparisons of the local structure around the selected objects and relating this local information to global views.…”

Section: Comparison Visualisationmentioning

confidence: 99%

Facilitating Machine Learning Model Comparison and Explanation through a Radial Visualisation

2021

View full text Add to dashboard Cite

Building an effective Machine Learning (ML) model for a data set is a difficult task involving various steps. One of the most important steps is to compare a substantial amount of generated ML models to find the optimal one for deployment. It is challenging to compare such models with a dynamic number of features. Comparison is more than only finding differences of ML model performance, as users are also interested in the relations between features and model performance such as feature importance for ML explanations. This paper proposes RadialNet Chart, a novel visualisation approach, to compare ML models trained with a different number of features of a given data set while revealing implicit dependent relations. In RadialNet Chart, ML models and features are represented by lines and arcs, respectively. These lines are generated effectively using a recursive function. The dependence of ML models with a dynamic number of features is encoded into the structure of visualisation, where ML models and their dependent features are directly revealed from related line connections. ML model performance information is encoded with colour and line width in RadialNet Chart. Taken together with the structure of visualisation, feature importance can be directly discerned in RadialNet Chart for ML explanations. Compared with other commonly used visualisation approaches, RadialNet Chart can help to simplify the ML model comparison process with different benefits such as the following: more efficient in terms of helping users to focus their attention to find visual elements of interest and easier to compare ML performance to find optimal ML model and discern important features visually and directly instead of through complex algorithmic calculations for ML explanations.

show abstract

embComp: Visual Interactive Comparison of Vector Embeddings

Cited by 18 publications

References 48 publications

Visual Exploration of Relationships and Structure in Low-Dimensional Embeddings

Visual Exploration of Relationships and Structure in Low-Dimensional Embeddings

Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding

Facilitating Machine Learning Model Comparison and Explanation through a Radial Visualisation

Contact Info

Product

Resources

About