Martha Larson

Collaborative Filtering beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges

Over the past two decades, a large amount of research effort has been devoted to developing algorithms that generate recommendations. The resulting research progress has established the importance of the user-item (U-I) matrix, which encodes the individual preferences of users for items in a collection, for recommender systems. The U-I matrix provides the basis for collaborative filtering (CF) techniques, the dominant framework for recommender systems. Currently, new recommendation scenarios are emerging that offer promising new information that goes beyond the U-I matrix. This information can be divided into two categories related to its source: rich side information concerning users and items, and interaction information associated with the interplay of users and items. In this survey, we summarize and analyze recommendation scenarios involving information sources and the CF algorithms that have been recently developed to address them. We provide a comprehensive introduction to a large body of research, more than 200 key references, with the aim of supporting the further development of recommender systems exploiting information beyond the U-I matrix. On the basis of this material, we identify and discuss what we see as the central challenges lying ahead for recommender system technology, both in terms of extensions of existing techniques as well as of the integration of techniques and technologies drawn from other research areas.

CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering

In this paper we tackle the problem of recommendation in the scenarios with binary relevance data, when only a few (k) items are recommended to individual users. Past work on Collaborative Filtering (CF) has either not addressed the ranking problem for binary relevance datasets, or not specifically focused on improving top-k recommendations. To solve the problem we propose a new CF approach, Collaborative Less-is-More Filtering (CLiMF). In CLiMF the model parameters are learned by directly maximizing the Mean Reciprocal Rank (MRR), which is a well-known information retrieval metric for measuring the performance of top-k recommendations. We achieve linear computational complexity by introducing a lower bound of the smoothed reciprocal rank metric. Experiments on two social network datasets demonstrate the effectiveness and the scalability of CLiMF, and show that CLiMF significantly outperforms a naive baseline and two state-of-the-art CF methods.

TFMAP: optimizing MAP for top-n context-aware recommendation

In this paper, we tackle the problem of top-N context-aware recommendation for implicit feedback scenarios. We frame this challenge as a ranking problem in collaborative filtering (CF). Much of the past work on CF has not focused on evaluation metrics that lead to good top-N recommendation lists in designing recommendation models. In addition, previous work on context-aware recommendation has mainly focused on explicit feedback data, i.e., ratings. We propose TFMAP, a model that directly maximizes Mean Average Precision with the aim of creating an optimally ranked list of items for individual users under a given context. TFMAP uses tensor factorization to model implicit feedback data (e.g., purchases, clicks) with contextual information. The optimization of MAP in a large data collection is computationally too complex to be tractable in practice. To address this computational bottleneck, we present a fast learning algorithm that exploits several intrinsic properties of average precision to improve the learning efficiency of TFMAP, and to ensure its scalability. We experimentally verify the effectiveness of the proposed fast learning algorithm, and demonstrate that TFMAP significantly outperforms state-of-the-art recommendation approaches.

List-wise learning to rank with matrix factorization for collaborative filtering

A ranking approach, ListRank-MF, is proposed for collaborative filtering that combines a list-wise learning-to-rank algorithm with matrix factorization (MF). A ranked list of items is obtained by minimizing a loss function that represents the uncertainty between training lists and output lists produced by a MF ranking model. ListRank-MF enjoys the advantage of low complexity and is analytically shown to be linear with the number of observed ratings for a given user-item matrix. We also experimentally demonstrate the effectiveness of ListRank-MF by comparing its performance with that of item-based collaborative recommendation and a related state-of-the-art collaborative ranking approach (CoFiRank).

Automatic tagging and geotagging in video collections and communities

Automatically generated tags and geotags hold great promise to improve access to video collections and online communities. We overview three tasks offered in the MediaEval 2010 benchmarking initiative, for each, describing its use scenario, definition and the data set released. For each task, a reference algorithm is presented that was used within MediaEval 2010 and comments are included on lessons learned. The Tagging Task, Professional involves automatically matching episodes in a collection of Dutch television with subject labels drawn from the keyword thesaurus used by the archive staff. The Tagging Task, Wild Wild Web involves automatically predicting the tags that are assigned by users to their online videos. Finally, the Placing Task requires automatically assigning geo-coordinates to videos. The specification of each task admits the use of the full range of available information including user-generated metadata, speech recognition transcripts, audio, and visual features.

Tags as bridges between domains: improving recommendation with tag-induced cross-domain collaborative filtering

Recommender systems generally face the challenge of making predictions using only the relatively few user ratings available for a given domain. Cross-domain collaborative filtering (CF) aims to alleviate the effects of this data sparseness by transferring knowledge from other domains. We propose a novel algorithm, Tag-induced Cross-Domain Collaborative Filtering (TagCDCF), which exploits user-contributed tags that are common to multiple domains in order to establish the cross-domain links necessary for successful cross-domain CF. TagCDCF extends the state-of-the-art matrix factorization by introducing a constraint involving tag-based similarities between pairs of users and pairs of items across domains. The method requires no common users or items across domains. Using two publicly available CF data sets as different domains, we experimentally demonstrate that TagCDCF substantially outperforms other state-of-the-art single domain CF and cross-domain CF approaches. Additional experiments show that TagCDCF addresses data sparseness and illustrate the influence of the number of tags used by users in both domains.

Mining mood-specific movie similarity with matrix factorization for context-aware recommendation

Context-aware recommendation seeks to improve recommendation performance by exploiting various information sources in addition to the conventional user-item matrix used by recommender systems. Recommendations should also usually strive to satisfy a specific purpose. Within the Moviepilot mood track of the context-aware movie recommendation challenge, we propose a novel movie similarity measure that is specific to the movie property demanded by the challenge, i.e., movie mood. Our measure is further exploited by a joint matrix factorization model for recommendation. We experimentally validate the effectiveness of the proposed algorithm in exploiting mood-specific movie similarity for the recommendation with respect to several evaluation metrics, demonstrating that it could outperform several state-of-the-art approaches. In particular, mood-specific movie similarity is demonstrated to be more beneficial than general mood-based movie similarity, for the purpose of mood-specific recommendation.

Using coherence-based measures to predict query difficulty

We investigate the potential of coherence-based scores to predict query difficulty. The coherence of a document set associated with each query word is used to capture the quality of a query topic aspect. A simple query coherence score, QC-1, is proposed that requires the average coherence contribution of individual query terms to be high. Two further query scores, QC-2 and QC-3, are developed by constraining QC- 1 in order to capture the semantic similarity among query topic aspects. All three query coherence scores show the correlation with average precision necessary to make them good predictors of query difficulty. Simple and efficient, the measures require no training data and are competitive with language model-based clarity scores.

Pairwise geometric matching for large-scale object retrieval

Spatial verification is a key step in boosting the performance of object-based image retrieval. It serves to eliminate unreliable correspondences between salient points in a given pair of images, and is typically performed by analyzing the consistency of spatial transformations between the image regions involved in individual correspondences. In this paper, we consider the pairwise geometric relations between correspondences and propose a strategy to incorporate these relations at significantly reduced computational cost, which makes it suitable for large-scale object retrieval. In addition, we combine the information on geometric relations from both the individual correspondences and pairs of correspondences to further improve the verification accuracy. Experimental results on three reference datasets show that the proposed approach results in a substantial performance improvement compared to the existing methods, without making concessions regarding computational efficiency.

Generating Visual Summaries of Geographic Areas Using Community-Contributed Images

In this paper, we present a novel approach for automatic visual summarization of a geographic area that exploits user-contributed images and related explicit and implicit metadata collected from popular content-sharing websites. By means of this approach, we search for a limited number of representative but diverse images to represent the area within a certain radius around a specific location. Our approach is based on the random walk with restarts over a graph that models relations between images, visual features extracted from them, associated text, as well as the information on the uploader and commentators. In addition to introducing a novel edge weighting mechanism, we propose in this paper a simple but effective scheme for selecting the most representative and diverse set of images based on the information derived from the graph. We also present a novel evaluation protocol, which does not require input of human annotators, but only exploits the geographical coordinates accompanying the images in order to reflect conditions on image sets that must necessarily be fulfilled in order for users to find them representative and diverse. Experiments performed on a collection of Flickr images, captured around 207 locations in Paris, demonstrate the effectiveness of our approach.