Integrating Prior Knowledge in Mixed-Initiative Social Network Clustering

Fig. 1: Three Geo-Storyline designs showing the geo-temporal evolution of the relationships between people. The two selected people in blue moved together from north to south. (A) Coordinated Views include a map on the left and a unique Storyline timeline on the right. While scrolling, links appear between the relationship nearest to the map and the associated locations. (B) In Map Glyphs each relationship is represented by a map with the associated locations drawn in orange. (C) Time Glyphs are composed by a map on the left and a scrollable list of Storyline glyphs on the right. Each Storyline glyph contains all the relationships associated with one location. Gray lines between a location on the map and a storyline glyph indicate the correspondence between the two.

Section: Study: Discussion and Limitationsmentioning

confidence: 99%

Geo-Storylines: Integrating Maps Into Storyline Visualizations

Hulstein

Peña-Araya

Bezerianos

2022

“…[17,72]), and design novel user interaction scheme for exploratory analysis (e.g. [30,56,63,67]). Depending on the nature of the graph data, they have developed a variety of systems and algorithms for directed/undirected graphs, multivariate graphs (with node/edge attributes) and dynamic network visualization to support a wide range of graph analytic tasks [40,57].…”

Section: Graph Visualizationmentioning

confidence: 99%

Interactive Visual Pattern Search on Graph Data via Graph Representation Learning

Song

Dai²,

et al. 2022

Fig. 1. The visualization interface of GraphQ contains: (1) A query editing panel to specify the subgraph patterns and initiate the search.(2.1) (2.2) Query result panels to display the retrieved results. The graph thumbnails can be displayed in overview and detail modes.(3) A statistics and filtering panel that helps users select a graph to construct example-based query, and visualizes the distribution of the query results in the database. (4) A query option control panel to specify whether fuzzy-pattern search is enabled and whether the node-match should be highlighted. (5) A popup window for pairwise comparison between the query pattern and the returned result.The figure shows a case study on program workflow graph pattern search and the details are described in Section 5.1.

“…There is a wide variety of knowledge to implement the above models. Specifically, the knowledge can be standard procedures [21] and linguistic rules [48] collected from domain literature, relationships between samples [16,51,74] specified by users, constraints distilled from expert experiences [46], numeric features calculated based on pre-collected samples [72,73], etc. Besides, many recent works attempt to utilize knowledge involved in off-the-shelf digital resources, such as ontology [41,59], corpus [82], knowledge graphs [8,37], pre-trained models (e.g., knowledge distillation) [75], etc.…”

Section: Knowledge-assisted Visual Analyticsmentioning

confidence: 99%

“…A recent trend is introducing knowledge into the analysis models to break their performance bottleneck, yielding more desirable results. Relevant research involves many classic analysis tasks, such as labeling [61], clustering [16,51,82], topic extraction [14,33], ranking [74], etc. Our approach utilizes a similar strategy, i.e., incorporating human knowledge into the embedding network by adding a classification loss.…”

Section: Knowledge-assisted Visual Analyticsmentioning

confidence: 99%

Incorporation of Human Knowledge Into Data Embeddings to Improve Pattern Significance and Interpretability

Zhou

2022

2 a1 b1 c1 b2 a2 c1 c2 Fig. 1. The visualization system interface that consists of three components: (a) Knowledge Editor (KE), (b) Data Projector (DP), and (c) Pattern Explainer (PE). The analyst is analyzing the Covid-19 dataset [2] that consists of 173 sequences, each recording the number of monthly-confirmed cases (per million people) from May 2020 to April 2021 of a country. The analyst creates six country groups (see colored tree nodes) according to their knowledge using (a) and incorporates the class information into the embeddings of countries to generate the projection with clear and class-consistent visual structures that foreshadow underlying data patterns. (b2)The embedding projection without knowledge where does not exist visual structure.