Due to their great performance in many challenges, Deep Learning (DL) techniques keep gaining popularity in many fields. They have been adapted to process graph data structures to solve various complicated tasks such as graph classification and edge prediction. Eventually, they reached the Graph Drawing (GD) task. This article is an extended version of the previously published (DNN)2 and presents a framework to leverage DL techniques for graph drawing (DL4GD). We demonstrate how it is possible to train a Deep Learning model to extract features from a graph and project them into a graph layout. The method proposes to leverage efficient Convolutional Neural Networks, adapting them to graphs using Graph Convolutions. The graph layout projection is learned by optimizing a cost function that does not require any ground truth layout, as opposed to prior work. This paper also proposes an implementation and benchmark of the framework to study its sensitivity to certain deep learning-related conditions. As the field is novel, and many questions remain to be answered, we do not focus on finding the most optimal implementation of the method, but rather contribute toward a better understanding of the approach potential. More precisely, we study different learning strategies relative to the models training datasets. Finally, we discuss the main advantages and limitations of DL4GD.

Information Visualization has been one of the cornerstones of Data Science, turning the abundance of Big Data being produced through modern systems into actionable knowledge. Indeed, the Big Data era has realized the availability of voluminous datasets that are dynamic, multidimensional, noisy and heterogeneous in nature. Transforming a data-curious user into someone who can access and analyze that data is even more burdensome now for a great number of users with little or no support and expertise on the data processing part.

Current deep learning approaches are cutting-edge methods for solving classification tasks. Arising transfer learning techniques allows applying large generic model to simple tasks whereas simpler models could be used. Large models raise the major problem of their memory consumption and processor usage and lead to a prohibitive ecological footprint. In that paper, we present a novel visual analytics approach to interactively prune those networks and thus limit that issue. Our technique leverages a novel sparkline matrix visualization technique as well as a novel local metric which evaluates the discriminatory power of a filter to guide the pruning process and make it interpretable. We assess the well- founded of our approach through two realistic case studies and a user study. For both of them, the interactive refinement of the model led to a significantly smaller model having similar prediction accuracy than the original one.

Edge‐Path bundling is a recent edge bundling approach that does not incur ambiguities caused by bundling disconnected edges together. Although the approach produces less ambiguous bundlings, it suffers from high computational cost. In this paper, we present a new Edge‐Path bundling approach that increases the computational speed of the algorithm without reducing the quality of the bundling. First, we demonstrate that biconnected components can be processed separately in an Edge‐Path bundling of a graph without changing the result. Then, we present a new edge bundling algorithm that is based on observing and exploiting a strong relationship between Edge‐Path bundling and graph spanners. Although the worst case complexity of the approach is the same as of the original Edge‐Path bundling algorithm, we conduct experiments to demonstrate that the new approach is 5 – 256 times faster than Edge‐Path bundling depending on the dataset, which brings its practical running time more in line with traditional edge bundling algorithms.

The use and creation of machine‐learning‐based solutions to solve problems or reduce their computational costs are becoming increasingly widespread in many domains. Deep Learning plays a large part in this growth. However, it has drawbacks such as a lack of explainability and behaving as a black‐box model. During the last few years, Visual Analytics has provided several proposals to cope with these drawbacks, supporting the emerging eXplainable Deep Learning field. This survey aims to (i) systematically report the contributions of Visual Analytics for eXplainable Deep Learning; (ii) spot gaps and challenges; (iii) serve as an anthology of visual analytical solutions ready to be exploited and put into operation by the Deep Learning community (architects, trainers and end users) and (iv) prove the degree of maturity, ease of integration and results for specific domains. The survey concludes by identifying future research challenges and bridging activities that are helpful to strengthen the role of Visual Analytics as effective support for eXplainable Deep Learning and to foster the adoption of Visual Analytics solutions in the eXplainable Deep Learning community. An interactive explorable version of this survey is available online at https://aware‐diag‐sapienza.github.io/VA4XDL .

come from teaching and research institutions in France or abroad, or from public or private research centers.L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

This paper presents a novel approach called Pharmacophore Activity Delta for extracting outstanding pharmacophores from a chemogenomic dataset, with a specific focus on a kinase target known as BCR-ABL. The method involves constructing a Hasse diagram, referred to as the pharmacophore network, by utilizing the subgraph partial order as an initial step, leading to the identification of pharmacophores for further evaluation. A pharmacophore is classified as a ‘Pharmacophore Activity Delta’ if its capability to effectively discriminate between active vs inactive molecules significantly deviates (by at least δ standard deviations) from the mean capability of its related pharmacophores. Among the 1479 molecules associated to BCR-ABL binding data, 130 Pharmacophore Activity Delta were identified. The pharmacophore network reveals distinct regions associated with active and inactive molecules. The study includes a discussion on representative key areas linked to different pharmacophores, emphasizing structure–activity relationships.

Projecting a set of $n$ points on a grid of size $\sqrt{n}\times\sqrt{n}$ provides the best possible information density in two dimensions without overlap. We leverage the Voronoi Relaxation method to devise a novel and versatile post-processing algorithm called VRGrid: it enables the arrangement of any 2D data on a grid while preserving its initial positions. We apply VRGrid to generate compact and overlap-free visualization of popular and overlap-prone projection methods (e.g., t-SNE). We prove that our method complexity is $O(\sqrt{n}.i.n.log(n))$ , with i a determined maximum number of iterations and $n$ the input dataset size. It is thus usable for visualization of several thousands of points. We evaluate VRGrid's efficiency with several metrics: distance preservation (DP), neighborhood preservation (NP), pairwise relative positioning preservation (RPP) and global positioning preservation (GPP). We benchmark VRGrid against two state-of-the-art methods: Self-Sorting Maps (SSM) and Distance-preserving Grid (DGrid). VRGrid outperforms these two methods, given enough iterations, on DP, RPP and GPP which we identify to be the key metrics to preserve the positions of the original set of points.

Current machine learning and deep learning approaches are cutting-edge methods for solving classification tasks. Comparing the performances of classification models has become a prominent task since the outbreak of these techniques. The performance of such classification models is measured by the ratio between the correctly predicted samples and the others. The most widely used visualization to represent this information is the Confusion matrix. Yet, if this technique is suited to apprehend one model performances, very few works use this representation to compare models. In that paper, we present the Relative Confusion Matrix (RCM), a new matrix visualization that leverages Confusion matrices and a color encoding to expose the class-wise differences of performances between two models. We conduct a user evaluation to compare RCM with two confusion matrix variants. Our results show that RCM encoding leads to a more efficient comparison of two models than existing approaches.

The design of efficient representations is well established as a fruitful way to explore and analyze complex or large data. In these representations, data are encoded with various visual attributes depending on the needs of the representation itself. To make coherent design choices about visual attributes, the visual search field proposes guidelines based on the human brain’s perception of features. However, information visualization representations frequently need to depict more data than the amount these guidelines have been validated on. Since, the information visualization community has extended these guidelines to a wider parameter space.This paper contributes to this theme by extending visual search theories to an information visualization context. We consider a visual search task where subjects are asked to find an unknown outlier in a grid of randomly laid out distractors. Stimuli are defined by color and shape features for the purpose of visually encoding categorical data. The experimental protocol is made of a parameters space reduction step (i.e., sub-sampling) based on a machine learning model, and a user evaluation to validate hypotheses and measure capacity limits. The results show that the major difficulty factor is the number of visual attributes that are used to encode the outlier. When redundantly encoded, the display heterogeneity has no effect on the task. When encoded with one attribute, the difficulty depends on that attribute heterogeneity until its capacity limit (7 for color, 5 for shape) is reached. Finally, when encoded with two attributes simultaneously, performances drop drastically even with minor heterogeneity.

The design of efficient representations is well established as a fruitful way to explore and analyze complex or large data. In these representations, data are encoded with various visual attributes depending on the needs of the representation itself. To make coherent design choices about visual attributes, the visual search field proposes guidelines based on the human brain perception of features. However, information visualization representations frequently need to depict more data than the amount these guidelines have been validated on. Since, the information visualization community has extended these guidelines to a wider parameter space. This paper contributes to this theme by extending visual search theories to an information visualization context. We consider a visual search task where subjects are asked to find an unknown outlier in a grid of randomly laid out distractor. Stimuli are defined by color and shape features for the purpose of visually encoding categorical data. The experimental protocol is made of a parameters space reduction step (i.e., sub-sampling) based on a machine learning model, and a user evaluation to measure capacity limits and validate hypotheses. The results show that the major difficulty factor is the number of visual attributes that are used to encode the outlier. When redundantly encoded, the display heterogeneity has no effect on the task. When encoded with one attribute, the difficulty depends on that attribute heterogeneity until its capacity limit (7 for color, 5 for shape) is reached. Finally, when encoded with two attributes simultaneously, performances drop drastically even with minor heterogeneity.

Edge bundling techniques cluster edges with similar attributes (i.e. similarity in direction and proximity) together to reduce the visual clutter. All edge bundling techniques to date implicitly or explicitly cluster groups of individual edges, or parts of them, together based on these attributes. These clusters can result in ambiguous connections that do not exist in the data. Confluent drawings of networks do not have these ambiguities, but require the layout to be computed as part of the bundling process. We devise a new bundling method, Edge-Path bundling, to simplify edge clutter while greatly reducing ambiguities compared to previous bundling techniques. Edge-Path bundling takes a layout as input and clusters each edge along a weighted, shortest path to limit its deviation from a straight line. Edge-Path bundling does not incur independent edge ambiguities typically seen in all edge bundling methods, and the level of bundling can be tuned through shortest path distances, Euclidean distances, and combinations of the two. Also, directed edge bundling naturally emerges from the model. Through metric evaluations, we demonstrate the advantages of Edge-Path bundling over other techniques.

Proceedings of GD2020: This volume contains the papers presented at GD~2020, the 28th International Symposium on Graph Drawing and Network Visualization, held on September 18-20, 2020 online. Graph drawing is concerned with the geometric representation of graphs and constitutes the algorithmic core of network visualization. Graph drawing and network visualization are motivated by applications where it is crucial to visually analyse and interact with relational datasets. Information about the conference series and past symposia is maintained at http://www.graphdrawing.org. The 2020 edition of the conference was hosted by University Of British Columbia, with Will Evans as chair of the Organizing Committee. A total of 251 participants attended the conference.

In information visualization, it has become mandatory to assess visualization techniques efficiency either to write a survey, optimize a technique or even design a new one. To do so, the common way is to conduct user evaluations through which human subjects are asked to solve a task on different visualization techniques while their performances are measured to assess which technique is the most efficient. These evaluations can be complex to design and setup in order not to be biased and, in the end, their results can become contestable when the evaluation methods standards evolve. To overcome these flaws, new evaluation methods are emerging, mostly making use of modern and efficient computer vision techniques such as deep learning. These new methods rely on a strong assumption that has not been studied deeply enough yet: humans and deep learning models performances can be correlated. This paper explores the performances of both a state-of-the-art deep neural network and human subjects on an outlier detection task taken from a previous experiment of the literature. The objective is to study whether the machine and humans behaviors were different or if some correlations can be observed. Our study shows that their results are significantly correlated and a machine learning model efficiently learned to predict human performances using deep neural network metrics as input. Hence, this work presents a use case where using a deep neural network to assess human subjects performances is efficient.

Deep Neural Networks are becoming the prominent solution when using machine learning models. However, they suffer from a black-box effect that renders complicated their inner workings interpretation and thus the understanding of their successes and failures. Information visualization is one way among others to help in their interpretability and hypothesis deduction. This paper presents a novel way to visualize a trained DNN to depict at the same time its architecture and its way of treating the classes of a test dataset at the layer level. In this way, it is possible to visually detect where the DNN starts to be able to discriminate the classes or where it could decrease its separation ability (and thus detect an oversized network). We have implemented the approach and validated it using several well-known datasets and networks. Results show the approach is promising and deserves further studies.

By leveraging recent progress of stochastic gradient descent methods, several works have shown that graphs could be efficiently laid out through the optimization of a tailored objective function. In the meantime, Deep Learning (DL) techniques achieved great performances in many applications. We demonstrate that it is possible to use DL techniques to learn a graph-to-layout sequence of operations thanks to a graph-related objective function. In this paper, we present a novel graph drawing framework called (DNN)^2: Deep Neural Network for DrawiNg Networks. Our method uses Graph Convolution Networks to learn a model. Learning is achieved by optimizing a graph topology related loss function that evaluates (DNN)^2 generated layouts during training. Once trained, the (DNN)^ model is able to quickly lay any input graph out. We experiment (DNN)^2 and statistically compare it to optimization-based and regular graph layout algorithms. The results show that (DNN)^2 performs well and are encouraging as the Deep Learning approach to Graph Drawing is novel and many leads for future works are identified.