We propose a computational framework for identifying approximate functional dependencies (AFDs) in a relation, leveraging the frequency distribution information of individual attributes.This framework operates without requiring access to the full database, processing records one at a time as necessary.Our approach generalizes existing measures for quantifying errors in perfect dependencies and formalizes two primary problems: finding top-𝑘 AFDs and identifying all AFDs within a specified error threshold, 𝜖.Our proposed framework provides anytime solutions, meaning it returns results after processing each record.A key innovation of our work lies in effectively estimating error bounds of the candidate AFDs, which allows to produce anytime solutions.We present an exact algorithm that delivers precise solutions when possible.We also develop an algorithm that always returns a solution albeit with some imprecision in the output.We demonstrate the applicability of these algorithms under various data organization strategies, such as indexing by key or key-like attributes.Our experimental results, based on both real-world and synthetic datasets, validate the effectiveness of our approach and show that it outperforms state-of-the-art solutions.

Data-sharing ecosystems connect providers, consumers, and intermediaries to facilitate the exchange and use of data for a wide range of downstream tasks. In sensitive domains such as healthcare, privacy is enforced as a hard constraint--any shared data must satisfy a minimum privacy threshold. However, among all masking configurations that meet this requirement, the utility of the masked data can vary significantly, posing a key challenge: how to efficiently select the optimal configuration that preserves maximum utility. This paper presents A egis , a middleware framework that selects optimal masking configurations for machine learning datasets with features and class labels. A egis incorporates a utility optimizer that minimizes predictive utility deviation --quantifying shifts in feature-label correlations due to masking. Our framework leverages limited data summaries (such as 1D histograms) or none to estimate the feature-label joint distribution, making it suitable for scenarios where raw data is inaccessible due to privacy restrictions. To achieve this, we propose a joint distribution estimator based on iterative proportional fitting, which allows supporting various feature-label correlation quantification methods such as mutual information, chi-square, or g3. Our experimental evaluation of real-world datasets shows that Aegis identifies optimal masking configurations over an order of magnitude faster, while the resulting masked datasets achieve predictive performance on downstream ML tasks on par with baseline approaches and complements privacy anonymization data masking techniques.

Abstract The ability to reuse trained models in Reinforcement Learning (RL) holds substantial practical value in particular for complex tasks. While model reusability is widely studied for supervised models in data management, to the best of our knowledge, this is the first ever principled study that is proposed for RL. To capture trained policies, we develop a framework based on an expressive and lossless graph data model that accommodates Temporal Difference Learning and Deep-RL based RL algorithms. Our framework is able to capture arbitrary reward functions that can be composed at inference time. The framework comes with theoretical guarantees and shows that it yields the same result as policies trained from scratch. We design a parameterized algorithm that strikes a balance between efficiency and quality w.r.t cumulative reward. Our experiments with two common RL tasks (query refinement and robot movement) corroborate our theory and show the effectiveness and efficiency of our algorithms.

We investigate the problem of finding winner(s) given a large number of users' (voters') preferences casted as ballots, one from each of the m users, where each ballot is a ranked order of preference of up to ℓ out of n items (candidates). Given a group protected attribute with k different values and a priority that imposes a selection order among these groups, the goal is to satisfy the priority order and select a winner per group that is most representative. It is imperative that at times the original users' preferences may require further manipulation to meet these fairness and priority requirement. We consider manipulation by modifications and formalize the margin finding problem under modification problem. We study the suitability of Instant Run-off Voting (IRV) as a preference aggregation method and demonstrate its advantages over positional methods. We present a suite of technical results on the hardness of the problem, design algorithms with theoretical guarantees and further investigate efficiency opportunities. We present exhaustive experimental evaluations using multiple applications and large-scale datasets to demonstrate the effectiveness of IRV, and efficacy of our designed solutions qualitatively and scalability-wise.

Given a large number (notationally m ) of users' (members or voters) preferences as inputs over a large number of items or candidates (notationally n ), preference queries leverage different preference aggregation methods to aggregate individual preferences in a systematic manner and come up with a single output (either a complete order or top- k , ordered or unordered) that is most representative of the users' preferences. The goal of this 1.5 hour lecture style tutorial is to adapt different preference aggregation methods from social choice theories, summarize how existing research has handled fairness over these methods, identify their limitations, and outline new research directions.

For datasets exhibiting long tail phenomenon, we identify a fairness concern in existing top-k algorithms, that return a "fixed" set of k results for a given query. This causes a handful of popular records (products, items, etc) getting overexposed and always be returned to the user query, whereas, there exists a long tail of niche records that may be equally desirable (have similar utility). To alleviate this, we propose θ-Equiv-top-k-MMSP inside existing top-k algorithms - instead of returning a fixed top-k set, it generates all (or many) top-k sets that are equivalent in utility and creates a probability distribution over those sets. The end user will be returned one of these sets during the query time proportional to its associated probability, such that, after many draws from many end users, each record will have as equal exposure as possible (governed by uniform selection probability). θ-Equiv-top-k-MMSP is formalized with two sub-problems. (a) θ-Equiv-top-k-Sets to produce a set S of sets, each set has k records, where the sets are equivalent in utility with the top-k set; (b) MaxMinFair to produce a probability distribution over S, that is, PDF(S), such that the records in S have uniform selection probability. We formally study the hardness of θ-Equiv-top-k-MMSP. We present multiple algorithmic results - (a) An exact solution for θ-Equiv-top-k-Sets, and MaxMinFair. (b) We design highly scalable algorithms that solve θ-Equiv-top-k-Sets through a random walk and is backed by probability theory, as well as a greedy solution designed for MaxMinFair. (c) We finally present an adaptive random walk based algorithm that solves θ-Equiv-top-k-Sets and MaxMinFair at the same time. We empirically study how θ-Equiv-top-k-MMSP can alleviate a equitable exposure concerns that group fairness suffers from. We run extensive experiments using 6 datasets and design intuitive baseline algorithms that corroborate our theoretical analysis.

Creating a plan, i.e., composing a sequence of items to achieve a task is inherently complex if done manually. This requires not only finding a sequence of relevant items but also understanding user requirements and incorporating them as constraints. For instance, in course planning, items are core and elective courses, and degree requirements capture their complex dependencies as constraints. In trip planning, items are points of interest (POIs) and constraints represent time and monetary budget, two user-specified requirements. Most importantly, a plan must comply with the ideal interleaving of items to achieve a goal such as enhancing students' skills towards the broader learning goal of an education program, or in the travel scenario, improving the overall user experience. We study the Task Planning Problem (TPP) with the goal of generating a sequence of items that optimizes multiple objectives while satisfying complex constraints. TPP is modeled as a Constrained Markov Decision Process, and we adapt weighted Reinforcement Learning to learn a policy that satisfies complex dependencies between items, user requirements, and satisfaction. We present a computational framework RL-Planner for TPP. RL-Planner requires minimal input from domain experts (academic advisors for courses, or travel agents for trips), yet produces personalized plans satisfying all constraints. We run extensive experiments on datasets from university programs and from travel agencies. We compare our solutions with plans drafted by human experts and with fully automated approaches. Our experiments corroborate that existing automated solutions are not suitable to solve TPP and that our plans are highly comparable to expensive handcrafted ones.

Given multiple individual rank orders over a set of candidates or items, where the candidates belong to multiple (non-binary) protected groups, we study the classical rank aggregation problem subject to proportionate fairness or p-fairness (RAPF in short), considering Kemeny distance. We first study the problem of producing the closest p-fair ranking to an individual ranked order IPF in short) considering Kendall-Tau distance, and present multiple solutions for IPF. We then present two computational frameworks(a randomized randpickperm and a deterministic algpickperm) to solve RAPF that leverages the solutions of IPF as a subroutine.

This work formalizes the Route Planning Problem (RPP), wherein a set of distributed assets (e.g., ships, submarines, unmanned systems) simultaneously plan routes to optimize a team goal (e.g., find the location of an unknown threat or object in minimum time and/or fuel consumption) while ensuring that the planned routes satisfy certain constraints (e.g., avoiding collisions and obstacles). This problem becomes overwhelmingly complex for multiple distributed assets as the search space grows exponentially to design such plans. The RPP is formalized as a Team Discrete Markov Decision Process (TDMDP) and we propose a Multi-agent Multi-objective Reinforcement Learning (MaMoRL) framework for solving it. We investigate challenges in deploying the solution in real-world settings and study approximation opportunities. We experimentally demonstrate MaMoRL's effectiveness on multiple real-world and synthetic grids, as well as for transfer learning. MaMoRL is deployed for use by the Naval Research Laboratory - Marine Meteorology Division (NRL-MMD), Monterey, CA.

Given m users (voters), where each user casts her preference for a single item (candidate) over n items (candidates) as a ballot, the preference aggregation problem returns k items (candidates) that have the k highest number of preferences (votes). Our work studies this problem considering complex fairness constraints that have to be satisfied via proportionate representations of different values of the group protected attribute(s) in the top- k results. Precisely, we study the margin finding problem under single ballot substitutions , where a single substitution amounts to removing a vote from candidate i and assigning it to candidate j and the goal is to minimize the number of single ballot substitutions needed to guarantee that the top-k results satisfy the fairness constraints. We study several variants of this problem considering how top- k fairness constraints are defined, (i) MFBinaryS and MFMultiS are defined when the fairness (proportionate representation) is defined over a single, binary or multivalued, protected attribute, respectively; (ii) MF-Multi2 is studied when top- k fairness is defined over two different protected attributes; (iii) MFMulti3+ investigates the margin finding problem, considering 3 or more protected attributes. We study these problems theoretically, and present a suite of algorithms with provable guarantees. We conduct rigorous large scale experiments involving multiple real world datasets by appropriately adapting multiple state-of-the-art solutions to demonstrate the effectiveness and scalability of our proposed methods.

Peer groups leverage the presence of knowledgeable individuals in order to increase the knowledge level of other participants. The `smart' formation of peer groups can thus play a crucial role in educational settings, including online social networks and learning platforms. Indeed, the targeted groups formation problem, where the objective is to maximize a measure of aggregate knowledge, has received considerable attention in recent literature. In this paper we initiate a dynamic variant of the problem that, unlike previous works, allows the change of group composition over time while still targeting to maximize the aggregated knowledge level. The problem is studied in a principled way, using a realistic learning gain function and for two different interaction modes among the group members. On the algorithmic side, we present DyGroups, a generic algorithmic framework that is greedy in nature and highly scalable. We present non-trivial proofs to demonstrate theoretical guarantees for DyGroups in a special case. We also present real peer learning experiments with humans, and perform synthetic data experiments to demonstrate the effectiveness of our proposed solutions by comparing against multiple appropriately selected baseline algorithms.

How will we work, live, and thrive in the post-pandemic future? The rapid mushrooming of online job markets has been transforming the definition of work and workplaces. After the pandemic, as we "cope with the new normal", the future world of work may change forever and become predominantly virtual. This makes an unprecedented pool of talent available at our beck and calls to work on "gigs" that disband when the job is over; this also is the time of destabilization and changing nature of job security. As scientists, we have a big responsibility and a tremendous opportunity in shaping the Future of Work (FoW) post pandemic, by designing effective platforms that support productive employment, mitigate social costs, and provide an effective and safe learning environment.

In this paper, we revisit a suite of popular proximity problems (such as, KNN, clustering, minimum spanning tree) that repeatedly perform distance computations to compare distances during their execution. Our effort here is to design principled solutions to minimize distance computations for such problems in general metric spaces, especially for the scenarios where calling an expensive oracle to resolve unknown distances are the dominant cost of the algorithms for these problems. We present a suite of techniques, including a novel formulation of the problem, that studies how distance comparisons between objects could be modelled as a system of linear inequalities that assists in saving distance computations, multiple graph based solutions, as well as a practitioners guide to adopt our solution frameworks to proximity problems. We compare our designed solutions conceptually and empirically with respect to a broad range of existing works. We finally present a comprehensive set of experimental results using multiple large scale real-world datasets and a suite of popular proximity algorithms to demonstrate the effectiveness of our proposed approaches.

In various Web applications, users consume content in a series of sessions. That is prevalent in online music listening, where a session is a channel and channels are listened to in sequence, or in crowdsourcing, where a session is a set of tasks and task sets are completed in sequence. Content diversity can be defined in more than one way, e.g., based on artists or genres for music, or on requesters or rewards in crowdsourcing. A user may prefer to experience diversity within or across sessions. Naturally, intra-session diversity is set-based, whereas, inter-session diversity is sequence-based. This novel multi-session diversity gives rise to four bi-objective problems with the goal of minimizing or maximizing inter and intra diversities. Given the hardness of those problems, we propose to formulate a constrained optimization problem that optimizes inter diversity, subject to the constraint of intra diversity. We develop an efficient algorithm to solve our problem. Our experiments with human subjects on two real datasets, music and crowdsourcing, show our diversity formulations do serve different user needs, and yield high user satisfaction. Our large data experiments on real and synthetic data empirically demonstrate that our solution satisfy the theoretical bounds and is highly scalable, compared to baselines.

We study recommendation of deployment strategies to task requesters that are consistent with their deployment parameters: a lower-bound on the quality of the crowd contribution, an upper-bound on the latency of task completion, and an upper-bound on the cost incurred by paying workers. We propose BatchStrat, an optimization-driven middle layer that recommends deployment strategies to a batch of requests by accounting for worker availability. We develop computationally efficient algorithms to recommend deployments that maximize task throughput and pay-off, and empirically validate its quality and scalability.

Our work contributes to aiding requesters in deploying collaborative tasks in crowdsourcing. We initiate the study of recommending deployment strategies for collaborative tasks to requesters that are consistent with deployment parameters they desire: a lower-bound on the quality of the crowd contribution, an upper-bound on the latency of task completion, and an upper-bound on the cost incurred by paying workers. A deployment strategy is a choice of value for three dimensions: Structure (whether to solicit the workforce sequentially or simultaneously), Organization (to organize it collaboratively or independently), and Style (to rely solely on the crowd or to combine it with machine algorithms). We propose StratRec, an optimization-driven middle layer that recommends deployment strategies and alternative deployment parameters to requesters by accounting for worker availability. Our solutions are grounded in discrete optimization and computational geometry techniques that produce results with theoretical guarantees. We present extensive experiments on Amazon Mechanical Turk, and conduct synthetic experiments to validate the qualitative and scalability aspects of StratRec.

We investigate online group formation where members seek to increase their learning potential via collaboration. We capture two common learning models: LpA where each member learns from all higher skilled ones, and LpD where the least skilled member learns from the most skilled one. We formulate the problem of forming groups with the purpose of optimizing peer learning under different affinity structures: AffD where group affinity is the smallest between all members, and AffC where group affinity is the smallest between a designated member (e.g., the least skilled or the most skilled) and all others. This gives rise to multiple variants of a multiobjective optimization problem. We propose principled modeling of these problems and investigate theoretical and algorithmic challenges. We first present hardness results, and then develop computationally efficient algorithms with constant approximation factors. Our real-data experiments demonstrate with statistical significance that forming groups considering affinity improves learning. Our extensive synthetic experiments demonstrate the qualitative and scalability aspects of our solutions.

In this paper, we present a semi-automated, “human-in-the-loop” framework for attribute design that assists human analysts to transform raw attributes into effective derived attributes for classification problems. Our proposed framework is optimization guided and fully agnostic to the underlying classification model. We present an algebra with various operators (arithmetic, relational, and logical) to transform raw attributes into derived attributes and solve two technical problems: (a) the top-k buckets design problem aims at presenting human analysts with k buckets, each bucket containing promising choices of raw attributes that she can focus on only without having to look at all raw attributes; and (b) the top-l snippets generation problem, which iteratively aids human analysts with top-l derived attributes involving an attribute. For the former problem, we present an effective exact bottom-up algorithm that is empowered by pruning capability, as well as random walk based heuristic algorithms that are intuitive and work well in practice. For the latter, we present a greedy heuristic algorithm that is scalable and effective. Rigorous evaluations are conducted involving 6 different real world datasets to showcase that our framework generates effective derived attributes compared to fully manual or fully automated methods.

The goal of this tutorial is to make the audience aware of various discipline-specific research activities that could be characterized to be part of online labor markets and advocate for a unified framework that is interdisciplinary in nature and requires convergence of different research disciplines. We will discuss how such a framework could bring transformative effect on the nexus of humans, technology, and the future of work.

Current crowdsourcing platforms provide little support for worker feedback. Workers are sometimes invited to post free text describing their experience and preferences in completing tasks. They can also use forums such as Turker Nation1 to exchange preferences on tasks and requesters. In fact, crowdsourcing platforms rely heavily on observing workers and inferring their preferences implicitly. On the contrary, we believe that asking workers to indicate their preferences explicitly will allow us to improve different processes in crowdsourcing platforms. We initiate a study that leverages explicit elicitation from workers to capture the evolving nature of worker preferences and we propose an optimization framework to better understand and estimate task completion time. We design a Worker model to estimate task completion time whose accuracy is improved iteratively by requesting worker preferences for task factors, such as, required skills, task payment, and task relevance. We develop efficient solutions with guarantees, run extensive experiments with large-scale real-world data that show the benefit of explicit preference elicitation over implicit ones with statistical significance.

International audience

Task assignment is a central component in crowdsourcing. Organizational studies have shown that worker motivation in completing tasks has a direct impact on the quality of individual contributions. In this work, we examine motivation-aware task assignment in the presence of a set of workers. We propose to model motivation as a balance between task relevance and task diversity and argue that an adaptive approach to task assignment can best capture the evolving nature of motivation. Worker motivation is observed and task assignment is revisited appropriately across iterations. We prove the problem to be NP-hard as well as MaxSNP-Hard and develop efficient approximation algorithms with provable guarantees. Our experiments with synthetic data examine the scalability of our algorithms, and our live real data experiments show that capturing motivation using relevance and diversity leads to high crowdwork quality.

We propose to demonstrate CrowdCur \xspace, a system that allows platform administrators, requesters, and workers to conduct various analytics of interest. CrowdCur \xspace includes a worker curation component that relies on explicit feedback elicitation to best capture workers' preferences, a task curation component that monitors task completion and aggregates their statistics, and an OLAP-style component to query and combine analytics by a worker, by task type, etc. Administrators can fine tune their system's performance. Requesters can compare platforms and better choose the set of workers to target. Workers can compare themselves to others and find tasks and requesters that suit them best.

International audience

We address the problem of top-k search on graphs with multiple nodal attributes, which we call WAGs (short for Weighted Attribute Graphs). For example, a co-authorship network is a WAG, where each author is a node; each attribute corresponds to a particular topic (e.g., databases, data mining, and machine learning); and the amount of expertise in a particular topic is represented by a non-negative weight on that attribute. A typical search in this setting may be: find three coauthors (i.e., a triangle) where each author's expertise is greater than 50% in at least one topic area (i.e., attribute). We show that the problem of retrieving the optimal answer for graph search on WAGs is NP-complete. Moreover, we propose a fast and effective top-k graph search algorithm for WAGs. In an extensive experimental study, our proposed algorithm exhibits significant speed-up over competing approaches. On average, our proposed method achieves 7× faster query processing than the best competitor.

Today, crowdsourcing is used to "taskify" any job ranging from simple receipt transcription to collaborative editing, fan-subbing, citizen science, and citizen journalism. The crowd is typically volatile, its arrival and departure asynchronous, and its levels of attention and accuracy diverse. Tasks vary in complexity and may necessitate the participation of workers with varying degrees of expertise. Sometimes, workers need to collaborate explicitly and build on each other's contributions to complete a single task. For example, in disaster reporting, CrowdMap allows geographically closed people with diverse and complementary skills, to work together to report details about the course of a typhoon or the aftermath of an earthquake. This uber-ization of human labor requires the understanding of workers motivation in completing a task, their ability to work together in collaborative tasks, as well as, helping workers find relevant tasks. For over 40 years, organization studies have thoroughly examined human factors that affect workers in physical workplaces. More recently, computer scientists have developed algorithms that verify and leverage those findings in a virtual marketplace, in this case, a crowdsourcing platform. The goal of this tutorial is to review those two areas and discuss how their combination may improve workers' experience, task throughput and outcome quality for both micro-tasks and collaborative tasks. We will start with a coverage of motivation theory, team formation, and learning worker profiles. We will then address open research questions that result from this review.

Collaborative crowdsourcing is an emerging paradigm where a set of workers, often with diverse and complementary skills, form groups and work together to complete complex tasks. While crowdsourcing has been used successfully in many applications, collaboration is essential for achieving a high quality outcome for a number of emerging applications such as text translation, citizen journalism and surveillance tasks. However, no crowdsourcing platform today enables the end-to-end deployment of collaborative tasks. We demonstrate Crowd4U, a volunteer-based system that enables the deployment of diverse crowdsourcing tasks with complex data-flows, in a declarative manner. In addition to treating workers and tasks as rich entities, Crowd4U also provides an easy-to-use form-based task UI. Crowd4U implements worker-to-task assignment algorithms that are appropriate for each kind of task. Once workers are assigned to tasks, appropriate worker collaboration schemes are enforced in order to enable effective result coordination.

International audience

International audience

A number of emerging applications, such as, collaborative document editing, sentence translation, and citizen journalism require workers with complementary skills and expertise to form groups and collaborate on complex tasks. While existing research has investigated task assignment for knowledge intensive crowdsourcing, they often ignore the aspect of collaboration among workers, that is central to the success of such tasks. Research in behavioral psychology has indicated that large groups hinder successful collaboration. Taking that into consideration, our work is one of the first to investigate and formalize the notion of collaboration among workers and present theoretical analyses to understand the hardness of optimizing task assignment. We propose efficient approximation algorithms with provable theoretical guarantees and demonstrate the superiority of our algorithms through a comprehensive set of experiments using real-world and synthetic datasets. Finally, we conduct a real world collaborative sentence translation application using Amazon Mechanical Turk that we hope provides a template for evaluating collaborative crowdsourcing tasks in micro-task based crowdsourcing platforms.

Congestive Heart Failure (CHF) is a serious chronic condition often leading to 50% mortality within 5 years. Improper treatment and post-discharge care of CHF patients leads to repeat frequent hospitalizations (i.e., readmissions). Accurately predicting patient's risk-of-readmission enables care-providers to plan resources, perform factor analysis, and improve patient quality of life. In this paper, we describe a supervised learning framework, Dynamic Hierarchical Classification (DHC) for patient's risk-of-readmission prediction. Learning the hierarchy of classifiers is often the most challenging component of such classification schemes. The novelty of our approach is to algorithmically generate various layers and combine them to predict overall 30-day risk-of-readmission. While the components of DHC are generic, in this work, we focus on congestive heart failure (CHF), a pressing chronic condition. Since healthcare data is diverse and rich and each source and feature-subset provides different insights into a complex problem, our DHC based prediction approach intelligently leverages each source and feature-subset to optimize different objectives (such as, Recall or AUC) for CHF risk-of-readmission. DHC's algorithmic layering capability is trained and tested over two real world datasets and is currently integrated into the clinical decision support tools at MultiCare Health System (MHS), a major provider of healthcare services in the northwestern US. It is integrated into a QlikView App (with EMR integration planned for Q2) and currently scores patients everyday, helping to mitigate readmissions and improve quality of care, leading to healthier outcomes and cost savings.

There has been significant recent interest in the area of group recommendations, where, given groups of users of a recommender system, one wants to recommend top-$k$ items to a group that maximize the satisfaction of the group members, according to a chosen semantics of group satisfaction. Examples semantics of satisfaction of a recommended itemset to a group include the so-called least misery (LM) and aggregate voting (AV). We consider the complementary problem of how to form groups such that the users in the formed groups are most satisfied with the suggested top-k recommendations. We assume that the recommendations will be generated according to one of the two group recommendation semantics -- LM or AV. Rather than assuming groups are given, or rely on ad hoc group formation dynamics, our framework allows a strategic approach for forming groups of users in order to maximize satisfaction. We show that the problem is NP-hard to solve optimally under both semantics. Furthermore, we develop two efficient algorithms for group formation under LM and show that they achieve bounded absolute error. We develop efficient heuristic algorithms for group formation under AV. We validate our results and demonstrate the scalability and effectiveness of our group formation algorithms on two large real data sets.

Many emerging applications such as collaborative editing, multi-player games, or fan-subbing require to form a team of experts to accomplish a task together. Existing research has investigated how to assign workers to such team-based tasks to ensure the best outcome assuming the skills of individual workers to be known. In this work, we investigate how to estimate individual worker's skill based on the outcome of the team-based tasks they have undertaken. We consider two popular skill aggregation functions and estimate the skill of the workers, where skill is either a deterministic value or a probability distribution. We propose efficient solutions for worker skill estimation using continuous and discrete optimization techniques. We present comprehensive experiments and validate the scalability and effectiveness of our proposed solutions using multiple real-world datasets.

We address the problem of search on graphs with multiple nodal attributes. We call such graphs weighted attribute graphs (WAGs). Nodes of a WAG exhibit multiple attributes with varying, non-negative weights. WAGs are ubiquitous in real-world applications. For example, in a co-authorship WAG, each author is a node; each attribute corresponds to a particular topic (e.g., databases, data mining, and machine learning); and the amount of expertise in a particular topic is represented by a non-negative weight on that attribute. A typical search in this setting specifies both connectivity between nodes and constraints on weights of nodal attributes. For example, a user's search may be: find three coauthors (i.e., a triangle) where each author's expertise is greater than 50 percent in at least one topic area (i.e., attribute). We propose a ranking function which unifies ranking between the graph structure and attribute weights of nodes. We prove that the problem of retrieving the optimal answer for graph search on WAGs is NP-complete. Moreover, we propose a fast and effective top-k graph search algorithm for WAGs. In an extensive experimental study with multiple real-world graphs, our proposed algorithm exhibits significant speed-up over competing approaches. On average, our proposed method is more than 7χ faster in query processing than the best competitor.

We present a system called ALIAS, that is designed to search for duplicate authors from Microsoft Academic Search Engine dataset. Author-ambiguity is a prevalent problem in this dataset, as many authors publish under several variations of their own name, or dif-ferent authors share similar or same name. ALIAS takes an author name as an input (who may or may not exist in the corpus), and out-puts a set of author names from the database, that are determined as duplicates of the input author. It also provides a confidence score with each output. Additionally, ALIAS has the feature of finding a Top-k list of similar authors, given an input author name. The un-derlying techniques heavily rely on a mix of learning, mining, and efficient search techniques, including partitioning, clustering, su-pervised learning using ensemble algorithms, and indexing to per-form efficient search to enable fast response for near real time user interaction. While the system is designed using Academic Search Engine data, the proposed solution is generic and could be extended to other problems in the category of entity disambiguation. In this demonstration paper, we describe different components of ALIAS and the intelligent algorithms associated with each of these com-ponents to perform author name disambiguation or similar authors finding. 1.

We describe the Crowd4U initiative, which aims at constructing an all-academic open and generic platform for microvolunteering and crowdsourcing worldwide. Crowd4U provides a microtask-based platform in which most workers are volunteers at universities and other research institutions. Crowd4U is open in the sense that the platform can interact with other platforms, researchers can register their tasks, and the underlying code is not a black box. It is generic as it allows to register virtually any task. Crowd4U has already been used by several projects for public and academic purposes.

We examine the problem of enabling the flexibility of updating one's preferences in group recommendation. In our setting, any group member can provide a vector of preferences that, in addition to past preferences and other group members' preferences, will be accounted for in computing group recommendation. This functionality is essential in many group recommendation applications, such as travel planning, online games, book clubs, or strategic voting, as it has been previously shown that user preferences may vary depending on mood, context, and company (i.e., other people in the group). Preferences are enforced in an feedback box that replaces preferences provided by the users by a potentially different feedback vector that is better suited for maximizing the individual satisfaction when computing the group recommendation. The feedback box interacts with a traditional recommendation box that implements a group consensus semantics in the form of Aggregated Voting or Least Misery, two popular aggregation functions for group recommendation. We develop efficient algorithms to compute robust group recommendations that are appropriate in situations where users have changing preferences. Our extensive empirical study on real world data-sets validates our findings.

In this paper, we describe a novel framework to recommend personalized intervention strategies to minimize 30-day readmission risk for heart failure (HF) patients, as they move through the provider's cardiac care protocol. We design principled solutions by learning the structure and parameters of a multi-layer hierarchical Bayesian network from underlying high-dimensional patient data. Next, we generate and summarize the rules leading to personalized interventions which can be applied to individual patients as they progress from admit to discharge. We present comprehensive experimental results as well as interesting case studies to demonstrate the effectiveness of our proposed framework using large real-world patient datasets on Microsoft Azure for Research platform.

We present IQR, a system that demonstrates optimization based interactive relaxations for queries that return an empty answer. Given an empty answer, IQR dynamically suggests one relaxation of the original query conditions at a time to the user, based on certain optimization objectives, and the user responds by either accepting or declining the relaxation, until the user arrives at a non-empty answer, or a non-empty answer is impossible to achieve with any further relaxations. The relaxation suggestions hinge on a proba- bilistic framework that takes into account the probability of the user accepting a suggested relaxation, as well as how much that relaxation serves towards the optimization objec- tive. IQR accepts a wide variety of optimization objectives - user centric objectives, such as, minimizing the number of user interactions (i.e., effort) or returning relevant results, as well as seller centric objectives, such as, maximizing profit. IQR offers principled exact and approximate solutions for gen- erating relaxations that are demonstrated using multiple, large real datasets.

Microsoft Academic Search is a free search engine specific to scholarly material. It currently covers more than 50 million publications and over 19 million authors across a variety of domains. One of the main challenges in correctly indexing this material is author name ambiguity and the resulting noise in author profiles. KDD Cup 2013 invited participants to tackle this problem in 2 ways: (1) by automatically determining which papers in an author profile are truly written by a given author, and (2) by identifying which author profiles need to be merged because they belong to the same author. This paper presents a brief account of the contest and the lessons learned.

Developing holistic predictive modeling solutions for risk prediction is extremely challenging in healthcare informatics. Risk prediction involves integration of clinical factors with socio-demographic factors, health conditions, disease parameters, hospital care quality parameters, and a variety of variables specific to each health care provider making the task increasingly complex. Unsurprisingly, many of such factors need to be extracted independently from different sources, and integrated back to improve the quality of predictive modeling. Such sources are typically voluminous, diverse, and vary significantly over the time. Therefore, distributed and parallel computing tools collectively termed big data have to be developed. In this work, we study big data driven solutions to predict the 30-day risk of readmission for congestive heart failure (CHF) incidents. First, we extract useful factors from National Inpatient Dataset (NIS) and augment it with our patient dataset from Multicare Health System (MHS). Then, we develop scalable data mining models to predict risk of readmission using the integrated dataset. We demonstrate the effectiveness and efficiency of the open-source predictive modeling framework we used, describe the results from various modeling algorithms we tested, and compare the performance against baseline non-distributed, non-parallel, non-integrated small data results previously published to demonstrate comparable accuracy over millions of records.

We present a system called Risk-O-Meter to predict and an- alyze clinical risk via data imputation, visualization, predic- tive modeling, and association rule exploration. Clinical risk calculators provide information about a person's chance of having a disease or encountering a clinical event. Such tools could be highly useful to educate patients to understand and monitor their health conditions. Unlike existing risk calcu- lators that are primarily designed for domain experts, Risk- O-Meter is useful to patients who are unfamiliar with medi- cal terminologies, or providers who have limited information about a patient. Risk-O-Meter is designed in a way such that it is flexible enough to accept limited or incomplete data in- puts, and still manages to predict the clinical risk efficiently and effectively. Current version of Risk-O-Meter evaluates 30-day risk of hospital readmission. However, the proposed system framework is applicable to general clinical risk pre- dictions. In this demonstration paper, we describe different components of Risk-O-Meter and the intelligent algorithms associated with each of these components to evaluate risk of readmission using incomplete patient data inputs.

We propose a principled optimization-based interactive query relaxation framework for queries that return no answers. Given an initial query that returns an empty answer set, our framework dynamically computes and suggests alternative queries with less conditions than those the user has initially requested, in order to help the user arrive at a query with a non-empty answer, or at a query for which no matter how many additional conditions are ignored, the answer will still be empty. Our proposed approach for suggesting query relaxations is driven by a novel probabilistic framework based on optimizing a wide variety of application-dependent objective functions. We describe optimal and approximate solutions of different optimization problems using the framework. We analyze these solutions, experimentally verify their efficiency and effectiveness, and illustrate their advantage over the existing approaches.

Planning an itinerary when traveling to a city involves substantial effort in choosing Points-of-Interest (POIs), deciding in which order to visit them, and accounting for the time it takes to visit each POI and transit between them. Several online services address different aspects of itinerary planning but none of them provides an interactive interface where users give feedbacks and iteratively construct their itineraries based on personal interests and time budget. In this paper, we formalize interactive itinerary planning as an iterative process where, at each step: (1) the user provides feedback on POIs selected by the system, (2) the system recommends the best itineraries based on all feedback so far, and (3) the system further selects a new set of POIs, with optimal utility, to solicit feedback for, at the next step. This iterative process stops when the user is satisfied with the recommended itinerary. We show that computing an itinerary is NP-complete even for simple itinerary scoring functions, and that POI selection is NP-complete. We develop heuristics and optimizations for a specific case where the score of an itinerary is proportional to the number of desired POIs it contains. Our extensive experiments show that our algorithms are efficient and return high quality itineraries.

Users often search spatial databases like yellow page data using keywords to find businesses near their current location. Typing the entire query is cumbersome and prone to errors, especially from mobile phones. We address this problem by introducing type-ahead search functionality on spatial databases. Like keyword search on spatial data, type-ahead search needs to be location-aware, i.e., with every letter being typed, it needs to return spatial objects whose names (or descriptions) are valid completions of the query string typed so far, and which rank highest in terms of proximity to the user's location and other static scores. Existing solutions for type-ahead search cannot be used directly as they are not location-aware. We show that a straight-forward combination of existing techniques for performing type-ahead search with those for performing proximity search perform poorly. We propose a formal model for query processing cost and develop novel techniques that optimize that cost. Our empirical evaluations on real and synthetic datasets demonstrate the effectiveness of our techniques. To the best of our knowledge, this is the first work on location-aware type-ahead search.

Facetedpedia is a faceted search system that dynamically discovers query-dependent faceted interfaces for Wikipedia search result articles. In this paper, we give an overview of Facetedpedia, present the system architecture and implementation techniques, and elaborate on a demonstration scenario.

Nowadays, online shopping has become a daily activity. Web users purchase a variety of items ranging from books to electronics. The large supply of online products calls for sophisticated techniques to help users explore available items. We propose to build composite items which associate a central item with a set of packages, formed by satellite items, and help users explore them. For example, a user shopping for an iPhone (i.e., the

This paper proposes Facetedpedia, a faceted retrieval system for information discovery and exploration in Wikipedia. Given the set of Wikipedia articles resulting from a keyword query, Facetedpedia generates a faceted interface for navigating the result articles. Compared with other faceted retrieval systems, Facetedpedia is fully automatic and dynamic in both facet generation and hierarchy construction, and the facets are based on the rich semantic information from Wikipedia. The essence of our approach is to build upon the collaborative vocabulary in Wikipedia, more specifically the intensive internal structures (hyperlinks) and folksonomy (category system). Given the sheer size and complexity of this corpus, the space of possible choices of faceted interfaces is prohibitively large. We propose metrics for ranking individual facet hierarchies by user's navigational cost, and metrics for ranking interfaces (each with k facets) by both their average pairwise similarities and average navigational costs. We thus develop faceted interface discovery algorithms that optimize the ranking metrics. Our experimental evaluation and user study verify the effectiveness of the system.

Extracting information and insights from large databases is a time-consuming activity and has received considerable research attention recently. In this demo, we present DynaCet - a domain independent system that provides effective minimum-effort based dynamic faceted search solutions over enterprise databases. At every step, Dynacet suggests facets depending on the user response in the previous step. Facets are selected based on their ability to rapidly drill down to the most promising tuples, as well as on the ability of the user to provide desired values for them. The benefits provided include faster access to information stored in databases while taking into consideration the variance in user knowledge and preferences.

We study the problem of group recommendation. Recommendation is an important information exploration paradigm that retrieves interesting items for users based on their profiles and past activities. Single user recommendation has received significant attention in the past due to its extensive use in Amazon and Netflix. How to recommend to a group of users who may or may not share similar tastes, however, is still an open problem. The need for group recommendation arises in many scenarios: a movie for friends to watch together, a travel destination for a family to spend a holiday break, and a good restaurant for colleagues to have a working lunch. Intuitively, items that are ideal for recommendation to a group may be quite different from those for individual members. In this paper, we analyze the desiderata of group recommendation and propose a formal semantics that accounts for both item relevance to a group and disagreements among group members. We design and implement algorithms for efficiently computing group recommendations. We evaluate our group recommendation method through a comprehensive user study conducted on Amazon Mechanical Turk and demonstrate that incorporating disagreements is critical to the effectiveness of group recommendation. We further evaluate the efficiency and scalability of our algorithms on the MovieLens data set with 10M ratings.

In this paper, we propose minimum-effort driven navigational techniques for enterprise database systems based on the faceted search paradigm. Our proposed techniques dynamically suggest facets for drilling down into the database such that the cost of navigation is minimized. At every step, the system asks the user a question or a set of questions on different facets and depending on the user response, dynamically fetches the next most promising set of facets, and the process repeats. Facets are selected based on their ability to rapidly drill down to the most promising tuples, as well as on the ability of the user to provide desired values for them. Our facet selection algorithms also work in conjunction with any ranked retrieval model where a ranking function imposes a bias over the user preferences for the selected tuples. Our methods are principled as well as efficient, and our experimental study validates their effectiveness on several application scenarios.