We increasingly depend on a variety of data-driven algorithmic systems to assist us in many aspects of life. Search engines and recommender systems among others are used as sources of information and to help us in making all sort of decisions from selecting restaurants and books, to choosing friends and careers. This has given rise to important concerns regarding the fairness of such systems. In this work, we aim at presenting a toolkit of definitions, models and methods used for ensuring fairness in rankings and recommendations. Our objectives are threefold: (a) to provide a solid framework on a novel, quickly evolving and impactful domain, (b) to present related methods and put them into perspective and (c) to highlight open challenges and research paths for future work.
1 November 2012 in Proceedings of the VLDB Endowment
To handle the overwhelming amount of information currently available, personalization systems allow users to specify the information that interests them through preferences. Most often, users have different preferences depending on context. In this paper, we introduce a model for expressing such contextual preferences. Context is modeled as a set of multidimensional attributes. We formulate the context resolution problem as the problem of (a) identifying those preferences that qualify to encompass the context state of a query and (b) selecting the most appropriate among them. We also propose an algorithm for context resolution that uses a data structure, called the profile tree, that indexes preferences based on their associated context. Finally, we evaluate our approach from two perspectives: usability and performance.
6 April 2018 in IEEE Transactions on Knowledge and Data Engineering
Graphs offer a natural model for the relationships and interactions among entities, such as those occurring among users in social and cooperation networks, and proteins in biological networks. Since most such networks are dynamic, to capture their evolution over time, we assume a sequence of graph snapshots where each graph snapshot represents the state of the network at a different time instance. Given this sequence, we seek to find the top-k most durable matches of an input graph pattern query, that is, the matches that exist for the longest period of time. The straightforward way to address this problem is to apply a state-of-the-art graph pattern matching algorithm at each snapshot and then aggregate the results. However, for large networks and long sequences, this approach is computationally expensive, since all matches have to be generated at each snapshot, including those appearing only once. We propose a new approach that uses a compact representation of the sequence of graph snapshots, appropriate time indexes to prune the search space and strategies to determine the duration of the seeking matches. Finally, we present experiments with real datasets that illustrate the efficiency and effectiveness of our approach.