Previous work on recommender systems mainly focus on fitting the ratings provided by users. However, the response patterns, i.e., some items are rated while others not, are generally ignored. We argue that failing to observe such response patterns can lead to biased parameter estimation and sub-optimal model performance. Although several pieces of work have tried to model users' response patterns, they miss the effectiveness and interpretability of the successful matrix factorization collaborative filtering approaches. To bridge the gap, in this paper, we unify explicit response models and PMF to establish the Response Aware Probabilistic Matrix Factorization (RAPMF) framework. We show that RAPMF subsumes PMF as a special case. Empirically we demonstrate the merits of RAPMF from various aspects.

Multi-modal data collections, such as corpora of paired images and text snippets, require analysis methods beyond single-view component and topic models. For continuous observations the current dominant approach is based on extensions of canonical correlation analysis, factorizing the variation into components shared by the different modalities and those private to each of them. For count data, multiple variants of topic models attempting to tie the modalities together have been presented. All of these, however, lack the ability to learn components private to one modality, and consequently will try to force dependencies even between minimally correlating modalities. In this work we combine the two approaches by presenting a novel HDP-based topic model that automatically learns both shared and private topics. The model is shown to be especially useful for querying the contents of one domain given samples of the other.

In spectral clustering, one defines a similarity matrix for a collection of data points, transforms the matrix to get the Laplacian matrix, finds the eigenvectors of the Laplacian matrix, and obtains a partition of the data using the leading eigenvectors. The last step is sometimes referred to as rounding, where one needs to decide how many leading eigenvectors to use, to determine the number of clusters, and to partition the data points. In this paper, we propose a novel method for rounding. The method differs from previous methods in three ways. First, we relax the assumption that the number of clusters equals the number of eigenvectors used. Second, when deciding the number of leading eigenvectors to use, we not only rely on information contained in the leading eigenvectors themselves, but also use subsequent eigenvectors. Third, our method is model-based and solves all the three subproblems of rounding using a class of graphical models called latent tree models. We evaluate our method on both synthetic and real-world data. The results show that our method works correctly in the ideal case where between-clusters similarity is 0, and degrades gracefully as one moves away from the ideal case.

A key feature of the AAMAS conference is its emphasis on ties to real-world applications. The focus of this article is to provide a broad overview of application-focused papers published at the AAMAS 2010 and 2011 conferences. More specifically, recent applications at AAMAS could be broadly categorized as belonging to research areas of security, sustainability and safety. We outline the domains of applications, key research thrusts underlying each such application area, and emerging trends.

The current paper introduces a new parallel computing technique based on ant colony optimization for a dynamic routing problem. In the dynamic traveling salesman problem the distances between cities as travel times are no longer fixed. The new technique uses a parallel model for a problem variant that allows a slight movement of nodes within their Neighborhoods. The algorithm is tested with success on several large data sets.

We present a combinatorial characterization of the Bethe entropy function of a factor graph, such a characterization being in contrast to the original, analytical, definition of this function. We achieve this combinatorial characterization by counting valid configurations in finite graph covers of the factor graph. Analogously, we give a combinatorial characterization of the Bethe partition function, whose original definition was also of an analytical nature. As we point out, our approach has similarities to the replica method, but also stark differences. The above findings are a natural backdrop for introducing a decoder for graph-based codes that we will call symbolwise graph-cover decoding, a decoder that extends our earlier work on blockwise graph-cover decoding. Both graph-cover decoders are theoretical tools that help towards a better understanding of message-passing iterative decoding, namely blockwise graph-cover decoding links max-product (min-sum) algorithm decoding with linear programming decoding, and symbolwise graph-cover decoding links sum-product algorithm decoding with Bethe free energy function minimization at temperature one. In contrast to the Gibbs entropy function, which is a concave function, the Bethe entropy function is in general not concave everywhere. In particular, we show that every code picked from an ensemble of regular low-density parity-check codes with minimum Hamming distance growing (with high probability) linearly with the block length has a Bethe entropy function that is convex in certain regions of its domain.

This paper describes our ongoing effort to build an empathizing and adaptive storyteller system. The system under development aims to utilize emotional expressions generated from an avatar or a humanoid robot in addition to the listener’s responses which are monitored in real time, in order to deliver a story in an effective manner. We conducted a pilot study and the results were analyzed in two ways: first, through a survey questionnaire analysis based on the participant’s subjective ratings; second, through automated video analysis based on the participant’s emotional facial expression and eye blinking. The survey questionnaire results show that male participants have a tendency of more empathizing with a story character when a virtual storyteller is present, as compared to audio-only narration. The video analysis results show that the number of eye blinking of the participants is thought to be reciprocal to their attention.

Narrative Intelligence (NI) can help computational systems interact with users, such as through story generation, interactive narratives, and believable virtual characters. However, existing NI techniques generally require manually coded domain knowledge, restricting their scalability. An approach that intelligently, automatically and economically acquires script-like knowledge in any domain with strategic crowdsourcing will ease this bottleneck and broaden the application territory of narrative intelligence. This doctoral consortium paper defines the research problem, describes its significance, proposes a feasible research plan towards a Ph.D. dissertation, and reports on its current progress.

The Intentional Fast-Forward (IFF) planner is an attempt to apply fast forward-chaining state-space search methods to intentional planning---planning such that every action is directed toward some character's goal. The IFF heuristic is based on Hoffmann's original Fast Forward heuristic (2001), which solves a simplified version of the problem and uses that solution as a guide for the real problem. IFF incorporates constraints imposed by intentional planning to narrow down the set of steps which can be taken next, and it identifies fruitless branches of the search space early.

Feature selection is a technique to screen out less important features. Many existing supervised feature selection algorithms use redundancy and relevancy as the main criteria to select features. However, feature interaction, potentially a key characteristic in real-world problems, has not received much attention. As an attempt to take feature interaction into account, we propose L1-LSMI, an L1-regularization based algorithm that maximizes a squared-loss variant of mutual information between selected features and outputs. Numerical results show that L1-LSMI performs well in handling redundancy, detecting non-linear dependency, and considering feature interaction.