EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection

Abstract

Figure 1: EmbeddingVis consists of (1) control panel, (2) graph view, (3) cluster transition view, (4) pairwise ranking view and (5) structural view. Using EmbeddingVis to verify preserved metrics at the instance level: (a) users lasso a cluster of nodes and the corresponding nodes are highlighted and linked across different embedding spaces (b1-e1). Clicking one "hub" node in this cluster (label 20) in the graph view generates four neighbor ranking lists of this "hub" node: (b2) the graph space, (c2) DeepWalk, (d2) struc2vec, and (e2) node2vec. The highlighted rectangles (c2, d2, e2) indicate the preserved metrics by each embedding. (f) Users can click "Filter" to highlight the nodes of each ranking list in the cluster transition view (b3-e3). (g) The Euclidean distance between adjacent nodes in struc2vec is more volatile compared with that in the other two spaces. ABSTRACTConstructing latent vector representation for nodes in a network through embedding models has shown its practicality in many graph analysis applications, such as node classification, clustering, and link prediction. However, despite the high efficiency and accuracy of learning an embedding model, people have little clue of what information about the original network is preserved in the embedding vectors. The abstractness of low-dimensional vector representation, stochastic nature of the construction process, and non-transparent hyper-parameters all obscure understanding of network embedding results. Visualization techniques have been introduced to facilitate embedding vector inspection, usually by projecting the embedding *

Inspecting the Running Process of Horizontal Federated Learning via Visual Analytics

“…In the data engineering stage, data visualization can help humans explore the data and obtain a qualitative sense of the nature of the data [38], [39]. In the model development stage, visual analytics systems serve as development tools, which increase the transparency and understandability of the development [40], [41], [42], [43], [44], [45]. At the last stage, that is, model operation, visualization can help explain the inner workings of the system to end-users during model deployment.…”

A User-Centered Design of Explainable AI for Clinical Decision Support

“…Visual analytic tools have been used to open the black box and explain the logic of the ML models [18][19][20][21]. However, the application of visual analytics tools for XAI in CDSS has been much more limited.…”

MaraVis: Representation and Coordinated Intervention of Medical Encounters in Urban Marathon

“…signature vectors of two runners. We choose Canberra Distance because it is sensitive to small changes and normalizes the absolute difference of individual comparisons, benefiting to the detection of clusters and outliers [23]. Therefore, an entire distance matrix can be obtained for the following dimensionality reduction analysis.…”

“…We select t-SNE as the dimensionality reduction technique because it shows superiority in generating 2D projection that "can reveal meaningful insights about data, e.g., clusters and outliers". It is more visually interpretable than naïve eigen-analysis, and depending on the distribution, more intuitive than MDS results, which preserve global structure more at the expense of local structure retained by t-SNE [23].…”