A Five-Level Design Framework for Bicluster Visualizations

Abstract

Abstract-Analysts often need to explore and identify coordinated relationships (e.g., four people who visited the same five cities on the same set of days) within some large datasets for sensemaking. Biclusters provide a potential solution to ease this process, because each computed bicluster bundles individual relationships into coordinated sets. By understanding such computed, structural, relations within biclusters, analysts can leverage their domain knowledge and intuition to determine the importance and relevance of the extracted relationships for making hypotheses. However, due to the lack of systematic design guidelines, it is still a challenge to design effective and usable visualizations of biclusters to enhance their perceptablity and interactivity for exploring coordinated relationships. In this paper, we present a five-level design framework for bicluster visualizations, with a survey of the state-of-the-art design considerations and applications that are related or that can be applied to bicluster visualizations. We summarize pros and cons of these design options to support user tasks at each of the five-level relationships. Finally, we discuss future research challenges for bicluster visualizations and their incorporation into visual analytics tools.

Understanding Hidden Memories of Recurrent Neural Networks

“…Co-clustering is a widely used method for analyzing bipartite graphs, which simultaneously clusters two kinds of entities in a graph [28]. Some recent work combined co-clustering with visualization to assist intelligence analysis, where different types of entities are considered [13,43]. A most recent work proposed by Xu et al [51] presented an interactive co-clustering visualization where cluster nodes are visualized as adjacency matrices or treemaps.…”

The State of the Art in Integrating Machine Learning into Visual Analytics

“…The authors utilize an interactive layout where fuzzy bi‐clusters are investigated for multi‐tissue type analysis. Biclustering is an algorithmic technique to solve for coordinated relationships computed from high‐dimensional data representations [MO04], and has been used in other domains, including text analysis [SNR14, SMNR16, FSB*13].…”

Survey of Surveys (SoS) ‐ Mapping The Landscape of Survey Papers in Information Visualization

“…Sun et al provide a survey focused on bi‐cluster visualization, design considerations, and applications. Bi‐clusters “provide a rich high‐level abstraction that represents coordinated relationships between groups of entities of different types” [SNR14]. The advantages and disadvantages are compared, and a five‐level relationship is presented to assist in design options that support user‐tasks.…”