VisExPreS: A Visual Interactive Toolkit for User-Driven Evaluations of Embeddings

Ghosh, Aindrila; Nashaat, Mona; Miller, James; Quader, Shaikh

doi:10.1109/tvcg.2020.3039106

Cited by 4 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DR model's behavior is explained by looking at the proxy model's behavior and feature importance. VisExPreS [14,15] produces a local approximation of the neighborhood structure to generate interpretable explanations on the preserved locality for a single instance. Chatzimparmpas et al [5] present t-viSNE, an interactive tool for the visual exploration of t-SNE projections.…”

Section: Local and Switching Explainermentioning

confidence: 99%

“…The metrics of the test set are introduced to evaluate the generalization performance of the model. The output of the 'transform' function in the official code 15 is used to test the generalization performance of the baseline.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…(2) Proxy explanation. These methods explain a DR approach by analyzing the parameters of the proxy model [5,13,15]. Although they are more scalable as they can work with DR, such methods are only a simple explanation of DR.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DMT-EV: An Explainable Deep Network for Dimension Reduction

Zang

Cheng

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Dimension reduction (DR) is commonly utilized to capture intrinsic structure and transform high-dimensional data into low-dimensional space while retaining meaningful properties of original data. It is used in a wide variety of applications such as image recognition, single-cell sequencing analysis, and biomarker discovery. However, contemporary parametric-free and parametric DR techniques suffer from several major shortcomings, such as the inability to preserve both global and local features and the pool generalization performance. On the other hand, regarding explainability, it is crucial to comprehend the embedding process, especially the contribution of each feature to the embedding process while understanding how each feature affects the embedding results that identify critical components and helps diagnose the embedding process. To address these problems, we have developed a deep neural network method called EVNet which provides not only excellent performance in structural maintainability but also explainability to the DR therein. EVNet starts from data augmentation and with a manifold-based loss function to improve embedding performance. The explanation is based on saliency maps and is aimed to examine the trained EVNet parameters and contributions of components during the embedding process. The proposed techniques are integrated with a visual interface to help the user to adjust EVNet to achieve better DR performance and explainability. The interactive visual interface makes it easier to illustrate the data features, compare different DR techniques, and investigate the explainability of DR. An in-depth experimental comparison is provided which shows that EVNet consistently outperforms the state-of-the-art methods in both performance measures and explainability.

show abstract

Section: Local and Switching Explainermentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

DMT-EV: An Explainable Deep Network for Dimension Reduction

Zang

Cheng

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…One theme is to reveal local and global structures of one or multiple latent spaces. 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].…”

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

“…Heimerl et al [22] proposed a set of metrics to measure the relationships (embedding correspondences) between two embeddings in a coordinated multi-view system called embComp. Ghosh et al [18] introduced a toolkit -VisExPreS -to disclose and compare the preserved global and local structures from the embeddings for novice data analysts.…”

Section: Related Workmentioning

confidence: 99%

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Rathore¹,

Dev²,

Phillips³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1. With VERB, users can explore the high-dimensional word representations interactively before, during, and after applying bias mitigation techniques. (A) Embedding View highlights a subset of word embeddings using dimensionality reduction and visualizes the step-by-step transformations of their embeddings across various debiasing techniques. (B) Control Panel enables users to configure each debiasing technique and provides controls to iterate through each step of the transformation. (C) Explanation Panel gives a step-by-step description of the transformation. In this example, in the Embedding View, word representations are reoriented with the concept direction (Gender) along the x-axis. They are then transformed by a debiasing technique called the Linear Projection that removes this concept. These transformed representations are visualized again in (D) after a new dimensionality reduction, where there is no longer a well-defined gender concept, and hence the stereotypical associations are mitigated.

show abstract

VisExPreS: A Visual Interactive Toolkit for User-Driven Evaluations of Embeddings

Cited by 4 publications

References 36 publications

DMT-EV: An Explainable Deep Network for Dimension Reduction

DMT-EV: An Explainable Deep Network for Dimension Reduction

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

VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations

Contact Info

Product

Resources

About