No abstract

Graph-structured data arise naturally in many different application domains. By representing data as graphs, we can capture entities (i.e., nodes) as well as their relationships (i.e., edges) with each other. Many useful insights can be derived from graph-structured data as demonstrated by an ever-growing body of work focused on graph mining. However, in the real-world, graphs can be both large -with many complex patterns -and noisy which can pose a problem for effective graph mining. An effective way to deal with this issue is to incorporate "attention" into graph mining solutions. An attention mechanism allows a method to focus on task-relevant parts of the graph, helping it to make better decisions. In this work, we conduct a comprehensive and focused survey of the literature on the emerging field of graph attention models. We introduce three intuitive taxonomies to group existing work. These are based on problem setting (type of input and output), the type of attention mechanism used, and the task (e.g., graph classification, link prediction, etc.). We motivate our taxonomies through detailed examples and use each to survey competing approaches from a unique standpoint. Finally, we highlight several challenges in the area and discuss promising directions for future work.

No abstract

This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs. The HONE framework is highly expressive and flexible with many interchangeable components. The experimental results demonstrate the effectiveness of learning higher-order network representations. In all cases, HONE outperforms recent embedding methods that are unable to capture higher-order structures with a mean relative gain in AUC of 19% (and up to 75% gain) across a wide variety of networks and embedding methods. HIGHER-ORDER NETWORK EMBEDDINGSThis section describes the Higher-Order Network Embedding (HONE) framework. Given a network G = (V , E) with N = |V | nodes and a set H = {H 1 , . . . , H T } of T network motifs, form the motif This paper is published under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.

No abstract

While sometimes the task that motivates searching, browsing, and collecting information resources is finding a particular fact, humans often use information resources in intellectual and creative tasks that can include comparison, understanding, and discovery. Information discovery tasks involve not only finding relevant information, but also seeing relationships among collected information resources, and developing new ideas. Our hypothesis is that how information is represented impacts the magnitude of human creativity in information discovery tasks. How can we measure this creative cognition? Studies of search have focused on time and accuracy, metrics of limited value for measuring creative discovery.We develop a new experimental method, which measures the emergence of new ideas in information discovery, to evaluate the efficacy of representations. We compare the efficacy of the typical textual list representation for information collections with an alternative representation, combinFormation's composition of image and text surrogates. Representing collections with such compositions increases emergence in information discovery.Measuring Emergence in Information Discovery 3

No abstract

No abstract