Graph Neural Networks (GNNs) have become increasingly important in recent years due to their state-of-the-art performance on many important downstream applications. Existing GNNs have mostly focused on learning a single node representation, despite that a node often exhibits polysemous behavior in different contexts. In this work, we develop a persona-based graph neural network framework called PersonaSAGE that learns multiple persona-based embeddings for each node in the graph. Such disentangled representations are more interpretable and useful than a single embedding. Furthermore, PersonaSAGE learns the appropriate set of persona embeddings for each node in the graph, and every node can have a different number of assigned persona embeddings. The framework is flexible enough and the general design helps in the wide applicability of the learned embeddings to suit the domain. We utilize publicly available benchmark datasets to evaluate our approach and against a variety of baselines. The experiments demonstrate the effectiveness of PersonaSAGE for a variety of important tasks including link prediction where we achieve an average gain of 15% while remaining competitive for node classification. Finally, we also demonstrate the utility of PersonaSAGE with a case study for personalized recommendation of different entity types in a data management platform.

Visualization recommendation systems make understanding data more accessible to users of all skill levels by automatically generating visualizations for users to explore. However, most existing visualization recommendation systems focus on ranking all possible visualizations based on the attributes or encodings, which makes it difficult to find the most interesting or relevant insights. We therefore introduce a novel class of visualization recommendation systems that automatically rank and recommend both groups of related insights and the most important insights within each group. Our approach combines results across different learning-based methods to discover insights automatically and generalizes to a variety of attribute types (e.g., categorical, numerical, and temporal), including non-trivial combinations of these attribute types. We then implemented a new insight-centric visualization recommendation system, SpotLight, which ranks annotated visualizations in visual insight groups. Finally, we conducted a user study which showed that users are able to quickly understand and find relevant insights in unfamiliar data.

Modern organizations amass their datasets into centralized repositories called data lakes, affording analytics as needed. The resultant scale and complexity of these data lakes, however, can make data navigation and monitoring challenging for users. We present DataCockpit, a Python toolkit that leverages datasets, usage logs, and associated meta-data to provision data usage and quality characteristics. DataCockpit computes these characteristics for each attribute (e.g., number of times it was queried for subsequent use in downstream applications) and record (e.g., number of non-missing, valid values) and aggregates them at the level of datasets. We develop a visual monitoring tool, powered by DataCockpit, and demonstrate how it can assist data / system administrators as well as end-users to effectively navigate and monitor a data lake. DataCockpit and the monitoring tool are available as open source software for developers to build custom monitoring applications on top of data lakes.

Analyzing data and creating effective visualizations often requires extensive domain expertise. For users with less experience, it can be difficult to know how to get started with exploratory data analysis (EDA) and how to approach the code. Chatbots can reduce the gap between analysis outcomes and user expectations by leveraging multi-turn conversations to provide a more natural interface between the user and computer-agent. To inform the design of future visual EDA chatbots, we conduct a survey and interview study with ten potential users. Our results suggest that users want a visual EDA chatbot that can make exploratory data analysis easier, while also augmenting their knowledge of visualization and analysis techniques. Between the initial survey and post-interview questionnaire, we saw increased optimism overall for the usefulness and anticipated analytic ease of visual EDA chatbots. Based on these results, we identify four key design guidelines: future visual EDA chatbots should (1) understand the user’s data and intent, (2) respond with useful visualizations, (3) leverage the history of the visualizations and data, and (4) produce verifiable and shareable analysis processes.

In data platforms with thousands of data tables available for exploration, users often need to retrieve some data based on limited knowledge of the data sources and schema. The task that automates retrieving attributes from an online data lake given a set of entities from users is called “entity augmentation”. The key for successful entity augmentation is an accurate construction of semantic relationships between data tables. Current techniques either focus on retrieving categorical values or numerical values with pre-defined rules. Further, they assume there are meta-data available for each table, such as texts and tags. In this paper, we introduce a semantic graph for numerical data augmentation that (i) matches columns with similar semantic relationships without any meta-data from the tables; (ii) infer the conversion rules among different numerical columns based on the values. The approach is designed to be highly scalable and parallel for large-scale data lakes with millions of large datasets. We also propose efficient algorithms to construct the semantic graph on a distributed computing environment (i.e. Spark) and conduct numerical data augmentation using the graph. Through comprehensive experiments on real-world datasets, the approach is shown to (1) achieve better accuracy on semantic matches and value conversions and (2) scales to the tractable computation time on large-scale data. Finally, we also present an interface to apply the semantic graph for real-world scenarios.

In this work, we study the problem of generating a set of images from an arbitrary tabular dataset. The set of generated images provides an intuitive visual summary of the tabular data that can be quickly and easily communicated and understood by the user. More specifically, we formally introduce this new dataset to image generation task and discuss a few motivating applications including exploratory data analysis and understanding customer segments for creating better marketing campaigns. We then curate a benchmark dataset for training such models, which we release publicly for others to use and develop new models for other important applications of interest. Further, we describe a general and flexible framework that serves as a fundamental basis for studying and developing models for this new task of generating images from tabular data. From the framework, we propose a few different approaches with varying levels of complexity and tradeoffs. One such approach leverages both numerical and textual data as the input to our image generation pipeline. The pipeline consists of an image decoder and a conditional auto-regressive sequence generation model which also includes a pre-trained tabular representation in the input layer. We evaluate the performance of these approaches through several quantitative metrics (FID for image quality and LPIPS scores for image diversity).

In this work, we develop a Graph Neural Network (GNN) framework for the problem of personalized visualization recommendation. The GNN-based framework first represents the large corpus of datasets and visualizations from users as a large heterogeneous graph. Then, it decomposes a visualization into its data and visual components, and then jointly models each of them as a large graph to obtain embeddings of the users, attributes (across all datasets in the corpus), and visual-configurations. From these user-specific embeddings of the attributes and visual-configurations, we can predict the probability of any visualization arising from a specific user. Finally, the experiments demonstrated the effectiveness of using graph neural networks for automatic and personalized recommendation of visualizations to specific users based on their data and visual (design choice) preferences. To the best of our knowledge, this is the first such work to develop and leverage GNNs for this problem.

Given entities and their interactions in the web data, which may have occurred at different time, how can we find communities of entities and track their evolution? In this paper, we approach this important task from graph clustering perspective. Recently, state-of-the-art clustering performance in various domains has been achieved by deep clustering methods. Especially, deep graph clustering (DGC) methods have successfully extended deep clustering to graph-structured data by learning node representations and cluster assignments in a joint optimization framework. Despite some differences in modeling choices (e.g., encoder architectures), existing DGC methods are mainly based on autoencoders and use the same clustering objective with relatively minor adaptations. Also, while many real-world graphs are dynamic, previous DGC methods considered only static graphs. In this work, we develop CGC, a novel end-to-end framework for graph clustering, which fundamentally differs from existing methods. CGC learns node embeddings and cluster assignments in a contrastive graph learning framework, where positive and negative samples are carefully selected in a multi-level scheme such that they reflect hierarchical community structures and network homophily. Also, we extend CGC for time-evolving data, where temporal graph clustering is performed in an incremental learning fashion, with the ability to detect change points. Extensive evaluation on real-world graphs demonstrates that the proposed CGC consistently outperforms existing methods.

Visualization recommendation work has focused solely on scoring visualizations based on the underlying dataset, and not the actualuserand their past visualization feedback. These systems recommend the same visualizations for every user, despite that the underlying user interests, intent, and visualization preferences are likely to be fundamentally different, yet vitally important. In this work, we formally introduce the problem ofpersonalized visualization recommendationand present a generic learning framework for solving it. In particular, we focus on recommending visualizations personalized for each individual user based on their past visualization interactions (e.g., viewed, clicked, manually created) along with the data from those visualizations. More importantly, the framework can learn from visualizations relevant to other users, even if the visualizations are generated from completely different datasets. Experiments demonstrate the effectiveness of the approach as it leads to higher quality visualization recommendations tailored to the specific user intent and preferences. To support research on this new problem, we release our user-centric visualization corpus consisting of 17.4k users exploring 94k datasets with 2.3 million attributes and 32k user-generated visualizations.

This paper introduces higher-order link prediction methods based on the notion of closing higher-order network motifs. The methods are fast and efficient for real-time ranking and link prediction-based applications such as online visitor stitching, web search, and online recommendation. In such applications, real-time performance is critical. The proposed methods do not require any explicit training data, nor do they derive an embedding from the graph data, or perform any explicit learning. Most existing unsupervised methods with the above desired properties are all based on closing triangles (common neighbors, Jaccard similarity, and the ilk). In this work, we develop unsupervised techniques based on the notion of closing higher-order motifs that generalize beyond closing simple triangles. Through extensive experiments, we find that these higher-order motif closures often outperform triangle-based methods, which are commonly used in practice. This result implies that one should consider other motif closures beyond simple triangles. We also find that the best motif closure depends highly on the underlying network and its structural properties. Furthermore, all methods described in this work are fast for link prediction-based applications requiring real-time performance. The experimental results indicate the importance of closing higher-order motifs for unsupervised link prediction. Finally, these new higher-order motif closures can serve as a basis for studying and developing better unsupervised real-time link prediction and ranking methods.

Visualization recommendation is important for exploratory analysis and making sense of the data quickly by automatically recommending relevant visualizations to the user. In this work, we propose the first end-to-end ML-based visualization recommendation system that leverages a large corpus of datasets and their relevant visualizations to learn a visualization recommendation model automatically. Then, given a new unseen dataset from an arbitrary user, the model automatically generates visualizations for that new dataset, derives scores for the visualizations, and outputs a list of recommended visualizations to the user ordered by effectiveness. We also describe an evaluation framework to quantitatively evaluate visualization recommendation models learned from a large corpus of visualizations and datasets. Through quantitative experiments, a user study, and qualitative analysis, we show that our end-to-end ML-based system recommends more effective and useful visualizations compared to existing state-of-the-art rule-based systems.

Scientific-style figures are commonly used on the web to present numerical information. Captions that tell accurate figure information and sound natural would significantly improve figure accessibility. In this paper, we present promising results on machine figure captioning. A recent corpus analysis of real-world captions reveals that machine figure captioning systems should start by generating accurate caption units. We formulate the caption unit generation problem as a controlled captioning problem. Given a caption unit type as a control signal, a model generates an accurate caption unit of that type. As a proof-of-concept on single bar charts, we propose a model, FigJAM, that achieves this goal through utilizing metadata information and a joint static and dynamic dictionary. Quantitative evaluations with two datasets from the figure question answering task show that our model can generate more accurate caption units than competitive baseline models. A user study with ten human experts confirms the value of machine-generated caption units in their standalone accuracy and naturalness. Finally, a post-editing simulation study demonstrates the potential for models to paraphrase and stitch together single-type caption units into multi-type captions by learning from data.

In this article, we introduce a generalization of graphlets to heterogeneous networks called typed graphlets . Informally, typed graphlets are small typed induced subgraphs. Typed graphlets generalize graphlets to rich heterogeneous networks as they explicitly capture the higher-order typed connectivity patterns in such networks. To address this problem, we describe a general framework for counting the occurrences of such typed graphlets. The proposed algorithms leverage a number of combinatorial relationships for different typed graphlets. For each edge, we count a few typed graphlets, and with these counts along with the combinatorial relationships, we obtain the exact counts of the other typed graphlets in o (1) constant time. Notably, the worst-case time complexity of the proposed approach matches the time complexity of the best known untyped algorithm. In addition, the approach lends itself to an efficient lock-free and asynchronous parallel implementation. While there are no existing methods for typed graphlets, there has been some work that focused on computing a different and much simpler notion called colored graphlet. The experiments confirm that our proposed approach is orders of magnitude faster and more space-efficient than methods for computing the simpler notion of colored graphlet. Unlike these methods that take hours on small networks, the proposed approach takes only seconds on large networks with millions of edges. Notably, since typed graphlet is more general than colored graphlet (and untyped graphlets), the counts of various typed graphlets can be combined to obtain the counts of the much simpler notion of colored graphlets. The proposed methods give rise to new opportunities and applications for typed graphlets.

Heterogeneous networks are seemingly ubiquitous in the real world. Yet, most graph mining methods such as clustering have mostly focused on homogeneous graphs by ignoring semantic information in real-world systems. Moreover, most methods are based on first-order connectivity patterns (edges) despite that higher-order connectivity patterns are known to be important in understanding the structure and organization of such networks. In this work, we propose a framework for higher-order spectral clustering in heterogeneous networks through the notions of typed graphlets and typed-graphlet conductance. The proposed method builds clusters that preserve the connectivity of higher-order structures built up from typed graphlets. The approach generalizes previous work on higher-order spectral clustering. We theoretically prove a number of important results including a Cheeger-like inequality for typed-graphlet conductance that shows near-optimal bounds for the method. The theoretical results greatly simplify previous work while providing a unifying theoretical framework for analyzing higher-order spectral methods. Empirically, we demonstrate the effectiveness of the framework quantitatively for three important applications including clustering, compression, and link prediction.

The success of many graph-based machine learning tasks highly depends on an appropriate representation learned from the graph data. Most work has focused on learning node embeddings that preserve proximity as opposed to structural role-based embeddings that preserve the structural similarity among nodes. These methods fail to capture higher-order structural dependencies and connectivity patterns that are crucial for structural role-based applications such as visitor stitching from web logs. In this work, we formulate higher-order network representation learning and describe a general framework called HONE for learning such structural node embeddings from networks via the subgraph patterns (network motifs, graphlet orbits/positions) in a nodes neighborhood. A general diffusion mechanism is introduced in HONE along with a space-efficient approach that avoids explicit construction of the k-step motif-based matrices using a k-step linear operator. Furthermore, HONE is shown to be fast and efficient with a worst-case time complexity that is nearly-linear in the number of edges. The experiments demonstrate the effectiveness of HONE for a number of important tasks including link prediction and visitor stitching from large web log data.

Online visitor behaviors are often modeled as a large sparse matrix, where rows represent visitors and columns represent behavior. To discover customer segments with different hierarchies, marketers often need to cluster the data in different splits. Such analyses require the clustering algorithm to provide real-time responses on user parameter changes, which the current techniques cannot support. In this paper, we propose a real-time clustering algorithm, sparse density peaks, for large-scale sparse data. It pre-processes the input points to compute annotations and a hierarchy for cluster assignment. While the assignment is only a single scan of the points, a naive pre-processing requires measuring all pairwise distances, which incur a quadratic computation overhead and is infeasible for any moderately sized data. Thus, we propose a new approach based on MinHash and LSH that provides fast and accurate estimations. We also describe an efficient implementation on Spark that addresses data skew and memory usage. Our experiments show that our approach (1) provides a better approximation compared to a straightforward MinHash and LSH implementation in terms of accuracy on real datasets, (2) achieves a 20 × speedup in the end-to-end clustering pipeline, and (3) can maintain computations with a small memory. Finally, we present an interface to explore customer segments from millions of online visitor records in real-time.

As 98 percent of shoppers do not make a purchase on the first visit, we study the problem of predicting whether they would come back for a purchase later (i.e., conversion prediction). This problem is important for strategizing “retargeting”, for example, by sending coupons for customers who are likely to convert. For this goal, we study the following two problems, prediction of market and predictability of customer. First, prediction of market aims at identifying a conversion rate for a given product and its customer behavior modeling, which is an important analytics metric for retargeting process. Compared to existing approaches using either of customer or product-level conversion pattern, we propose a joint modeling of both patterns based on the well-studied buying decision process. Second, we can observe customer-specific behaviors after showing retargeting ads, to predict whether this specific customer follows the market model (high predictability) or not (low predictability). For the former, we apply the market model, and for the latter, we propose a new customer-specific prediction based on dynamic ad behavior features. To evaluate the effectiveness of our methods, we perform extensive experiments on the simulated dataset generated based on a set of real-world web logs and retargeting campaign logs. The evaluation results show that conversion predictions and predictability by our approach are consistently more accurate and robust than those by existing baselines in dynamic market environment.

The success of deep convolutional neural networks in the domains of computer vision and speech recognition has led researchers to investigate generalizations of the said architecture to graph-structured data. A recently-proposed method called Graph Convolutional Networks has been able to achieve state-of-the-art results in the task of node classification. However, since the proposed method relies on localized first-order approximations of spectral graph convolutions, it is unable to capture higher-order interactions between nodes in the graph. In this work, we propose a motif-based graph attention model, called Motif Convolutional Networks, which generalizes past approaches by using weighted multi-hop motif adjacency matrices to capture higher-order neighborhoods. A novel attention mechanism is used to allow each individual node to select the most relevant neighborhood to apply its filter. We evaluate our approach on graphs from different domains (social networks and bioinformatics) with results showing that it is able to outperform a set of competitive baselines on the semi-supervised node classification task. Additional results demonstrate the usefulness of attention, showing that different higher-order neighborhoods are prioritized by different kinds of nodes.

Motivated by the computational and storage challenges that dense embeddings pose, we introduce the problem of latent network summarization that aims to learn a compact, latent representation of the graph structure with dimensionality that is independent of the input graph size (\i.e., #nodes and #edges), while retaining the ability to derive node representations on the fly. We propose Multi-LENS, an inductive multi-level latent network summarization approach that leverages a set of relational operators and relational functions (compositions of operators) to capture the structure of egonets and higher-order subgraphs, respectively. The structure is stored in low-rank, size-independent structural feature matrices, which along with the relational functions comprise our latent network summary. Multi-LENS is general and naturally supports both homogeneous and heterogeneous graphs with or without directionality, weights, attributes or labels. Extensive experiments on real graphs show 3.5-34.3% improvement in AUC for link prediction, while requiring 80-2152x less output storage space than baseline embedding methods on large datasets. As application areas, we show the effectiveness of Multi-LENS in detecting anomalies and events in the Enron email communication graph and Twitter co-mention graph.

Understanding user behavior and predicting future behavior on the web is critical for providing seamless user experiences as well as increasing revenue of service providers. Recently, thanks to the remarkable success of recurrent neural networks (RNNs), it has been widely used for modeling sequences of user behaviors. However, although sequential behaviors appear across multiple domains in practice, existing RNN-based approaches still focus on the single-domain scenario assuming that sequential behaviors come from only a single domain. Hence, in order to analyze sequential behaviors across multiple domains, they require to separately train multiple RNN models, which fails to jointly model the interplay among sequential behaviors across multiple domains. Consequently, they often suffer from lack of information within each domain. In this paper, we first introduce a practical but overlooked phenomenon in sequential behaviors across multiple domains, i.e.,domain switch where two successive behaviors belong to different domains. Then, we propose aDomain Switch-Aware Holistic Recurrent Neural Network (DS-HRNN) that effectively shares the knowledge extracted from multiple domains by systematically handlingdomain switch for the multi-domain scenario. DS-HRNN jointly models the multi-domain sequential behaviors and accurately predicts the future behaviors in each domain with only a single RNN model. Our extensive evaluations on two real-world datasets demonstrate that \DCHRNN\ outperforms existing RNN-based approaches and non-sequential baselines with significant improvements by up to 14.93% in terms of recall of the future behavior prediction.

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). 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.

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Although many networks contain this type of temporal information, the majority of research in network representation learning has focused on static snapshots of the graph and has largely ignored the temporal dynamics of the network. In this work, we describe a general framework for incorporating temporal information into network embedding methods. The framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks. Overall, the experiments demonstrate the effectiveness of the proposed framework and dynamic network embedding approach as it achieves an average gain of 11.9% across all methods and graphs. The results indicate that modeling temporal dependencies in graphs is important for learning appropriate and meaningful network representations.

The rapid growth of mobile devices has resulted in the generation of a large number of user behavior logs that contain latent intentions and user interests. However, exploiting such data in real-world applications is still difficult for service providers due to the complexities of user behavior over a sheer number of possible actions that can vary according to time. In this work, a time-aware RNN model, TRNN, is proposed for predictive analysis from user behavior data. First, our approach predicts next user action more accurately than the baselines including the n-gram models as well as two recently introduced time-aware RNN approaches. Second, we use TRNN to learn user embeddings from sequences of user actions and show that overall the TRNN embeddings outperform conventional RNN embeddings. Similar to how word embeddings benefit a wide range of task in natural language processing, the learned user embeddings are general and could be used in a variety of tasks in the digital marketing area. This claim is supported empirically by evaluating their utility in user conversion prediction, and preferred application prediction. According to the evaluation results, TRNN embeddings perform better than the baselines including Bag of Words (BoW), TFIDF and Doc2Vec. We believe that TRNN embeddings provide an effective representation for solving practical tasks such as recommendation, user segmentation and predictive analysis of business metrics.

Generally 2% of shoppers make a purchase on the first visit to an online store while the other 98% enjoys only window-shopping. To bring people back to the store and close the deal, "retargeting" has been a vital online advertising strategy that leads to "conversion" of window-shoppers into buyers. As such retargeting is more effective as a focused tool, in this paper, we study the problem of identifying a conversion rate for a given product and its current customers, which is an important analytics metric for retargeting process. Compared to existing approaches using either of customer- or product-level conversion pattern, we propose a joint modeling of both level patterns based on the well-studied buying decision process. To evaluate the effectiveness of our method, we perform extensive experiments on the simulated dataset generated based on a set of real-world web logs. The evaluation results show that conversion predictions by our approach are consistently more accurate and robust than those by existing baselines in dynamic market environment.

Personalization -- the customization of experiences, interfaces, and content to individual users -- has catalyzed user growth and engagement for many web services. A critical prerequisite to personalization is establishing user identity. However the variety of devices, including mobile phones, appliances, and smart watches, from which users access web services from both anonymous and logged-in sessions poses a significant obstacle to user identification. The resulting entity resolution task of establishing user identity across devices and sessions is commonly referred to as ``visitor stitching.'' We introduce a general, probabilistic approach to visitor stitching using features and attributes commonly contained in web logs. Using web logs from two real-world corporate websites, we motivate the need for probabilistic models by quantifying the difficulties posed by noise, ambiguity, and missing information in deployment. Next, we introduce our approach using probabilistic soft logic (PSL), a statistical relational learning framework capable of capturing similarities across many sessions and enforcing transitivity. We present a detailed description of model features and design choices relevant to the visitor stitching problem. Finally, we evaluate our PSL model on binary classification performance for two real-world visitor stitching datasets. Our model demonstrates significantly better performance than several state-of-the-art classifiers, and we show how this advantage results from collective reasoning across sessions.

The representation of information collections needs to be optimized for human cognition. While documents often include rich visual components, collections, including personal collections and those generated by search engines, are typically represented by lists of text-only surrogates. By concurrently invoking complementary components of human cognition, combined image-text surrogates will help people to more effectively see, understand, think about, and remember an information collection. This research develops algorithmic methods that use the structural context of images in HTML documents to associate meaningful text and thus derive combined image-text surrogates. Our algorithm first recognizes which documents consist essentially of informative and multimedia content. Then, the algorithm recognizes the informative sub-trees within each such document, discards advertisements and navigation, and extracts images with contextual descriptions. Experimental results demonstrate the algorithm's efficacy. An implementation of the algorithm is provided in combinFormation, a creativity support tool for collection authoring. The enhanced image-text surrogates enhance the experiences of users finding and collecting information as part of developing new ideas.

In order to evaluate the performance of information retrieval and extraction algorithms, we need test collections. A test collection consists of a set of documents, a clearly formed problem that an algorithm is supposed to provide solutions to, and the answers that the algorithm should produce when executed on the documents. Defining the association between elements in the test collection and answers is known as labeling. For mainstream information retrieval problems, there are publicly available test collections which have been maintained for years. However, the scope of these problems, and thus the associated test collections, is limited. In other cases, researchers need to build, label, and manage their own test collections, which can be a tedious and error-prone task. We were building test collections of HTML documents, for problems in which the answers that the algorithm supplies is a sub-tree of the DOM (Document Object Model). To lighten the burden of this task, we developed a test collection management and labeling system (TCMLS), to facilitate usability in the process of building test collections, applying them to validate algorithms, and potentially sharing them across the research community.

combinFormation is a mixed-initiative creativity support tool for searching, browsing, organizing, and integrating information. Images and text are connected to represent surrogates (enhanced bookmarks), optimizing the use of human cognitive facilities. Composition, an alternative to lists and spatial hypertext, is used to represent a collection of surrogates as a connected whole, using principles from art and design. This facilitates the creative process ofinformation discovery, in which humans develop new ideas while finding and collecting information. To provoke the user to think about the large space of potentially relevant information resources, a generative agent proactively engages in collecting information resources, forming image and text surrogates, and composing them visually. The agent develops the collection and its visual representation over time, enabling the user to see ideas and relationships. To keep the human in control, we develop interactive mechanisms for authoring the composition and directing the agent. In a field study in an interdisciplinary course on The Design Process, over a hundred students alternated using combinFormation and Google+Word to collect prior work on information discovery invention assignments. The students that used combinFormation's mixed-initiative composition of image and text surrogates performed better.

A surrogate is an object that stands for a document and enables navigation to that document. Hypermedia is often represented with textual surrogates, even though studies have shown that image and text surrogates facilitate the formation of mental models and overall understanding. Surrogates may be formed by breaking a document down into a set of smaller elements, each of which is a surrogate candidate. While processing these surrogate candidates from an HTML document, relevant information may appear together with less useful junk material, such as navigation bars and advertisements.

We are developing support for creativity in learning through information discovery and exploratory search. Users engage in creative tasks, such as inventing new products and services. The system supports evolving information needs. It gathers and presents relevant information visually using images and text. Users are able to search, browse, and explore results from multiple queries and interact with information elements by manipulating design and expressing interest. A field study was conducted to evaluate the system in an undergraduate class. The results demonstrated the efficacy of our system for developing creative ideas. Exposure to diverse information in visual and interactive forms is shown to support students engaged in invention tasks.

This paper presents an iterative method for generative semantic clustering of related information elements in spatial hypertext documents. The goal is to automatically organize them in ways that are meaningful to the user. We consider a process in which elements are gradually added to a spatial hypertext. The method for generating meaningful layout is based on a quantitative model that measures and represents the mutual relatedness between each new element and those already in the document. The measurement is based on attributes such as metadata, term vectors, user interest expressions, and document locations. We call this model relatedness potential, because it represents how much the new element is related and thus attracted to existing elements as a vector field across the space. Using this field as a gradient potential, the new element will be placed near the most attracted elements, forming clusters of related elements. The relative magnitude of contribution of attributes to relatedness potential can be controlled through an interactive interface.Unlike prior clustering methods such as k-means and self-organizing-maps, relatedness potential works well in iterative systems, in which the collection of elements is not defined a priori. Further, users can invoke relatedness potential to re-cluster elements, as they engage in on-the-fly provisional acts of direct manipulation reorganization and latching of a few most significant elements. A preliminary study indicates that users find this method generates spatial hypertext documents that are easier to read.