Accepted Contributions

List of all long papers accepted for RecSys 2017 (in alphabetical order).
Proceedings are available in the ACM Digital Library.

No matches were found!
  • LP3D Convolutional Networks for Session-based Recommendation with Content Features by Trinh Xuan Tuan and Tu Minh Phuong

    In many real-life recommendation settings, user profiles and past activities are not available. The recommender system should make predictions based on session data, e.g. session clicks and descriptions of clicked items. Conventional recommendation approaches, which rely on user-item interaction data, cannot deliver accurate results in these situations. In this paper, we describe a method that combines session clicks and content features such as item descriptions and item categories to generate recommendations. To model these data, which are usually of different types and nature, we use 3-dimensional convolutional neural networks with character-level encoding of all input data. While 3D architectures provide a natural way to capture spatio-temporal patterns, character-level networks allow modeling different data types using their raw textual representation, thus reducing feature engineering effort. We applied the proposed method to predict add-to-cart events in e-commerce websites, which is more difficult then just predicting next clicks. On two real data sets, our method outperformed several baselines and a state-of-the-art method based on recurrent neural networks.

  • LPA Gradient-based Adaptive Learning Framework for Efficient Personal Recommendation by Yue Ning, Yue Shi, Liangjie Hong, Huzefa Rangwala and Naren Ramakrishnan

    Recommending personalized content to users is a long-standing challenge to many online services including Facebook, Yahoo, Linkedin and Twitter. Traditional recommendation models such as latent factor models and feature-based models are usually trained for all users and optimize an “average” experience for them, yielding sub-optimal solutions. Although multi-task learning provides an opportunity to learn personalized models per user, learning algorithms are usually tailored to specific models (e.g., generalized linear model, matrix factorization and etc.), creating obstacles for a unified engineering interface, which is important for large Internet companies. In this paper, we present an empirical framework to learn user-specific personal models for content recommendation by utilizing gradient information from a global model. Our proposed method can potentially benefit any model that can be optimized through gradients, offering a lightweight yet generic alternative to conventional multi-task learning algorithms for user personalization. We demonstrate the effectiveness of the proposed framework by incorporating it in three popular machine learning algorithms including logistic regression, gradient boosting decision tree and matrix factorization. Our extensive empirical evaluation shows that the proposed framework can significantly improve the efficiency of personalized recommendation in real-world datasets.

  • LPAdditive Co-Clustering with Social Influence for Recommendation by Xixi Du, Huafeng Liu and Liping Jing

    Recommender system is a popular tool to accurately and actively provide users with potentially interesting information. For capturing the users’ preferences and approximating the missing data, matrix completion and approximation are widely adopted. Except for the typical low-rank factorization-based methods, the additive co-clustering approach (ACCAMS) is recently proposed to succinctly approximate large-scale rating matrix. Although ACCAMS efficiently produces effective recommendation result, it still suffers from the cold-start problem. To address this issue, we propose a Social Influence Additive Co-Clustering method (SIACC) by making use of user-item rating data and user-user social relations.

    The main idea of SIACC is to extract the social influences from the social network, integrate them to additive co-clustering for effectively determining the user clusters and item clusters, minimize the loss error by backfitting the residuals of data approximation in the previous iteration, and finally improve the recommendation performance. In order to take advantage of social influence, we present a graph-regularized weighted-Fuzzy C-Means algorithm (gwFCM) to cluster users. gwFCM has ability to identify user groups from both rating and social information. Specifically, gwFCM makes sure that a pair of users have similar cluster membership if they have direct social relation (denoted as local social influence), and that the user with higher reputation (denoted as global social influence) plays a dominate role in clustering process. The reasonable user clusters obtained by gwFCM can benefit the item clustering, which will leverage the additive co-clustering processing and further improve the recommendation performance. A series of experiments on three real-world datasets have shown that SIACC outperforms the existing popular recommendation methods (PMF and ACCAMS) and social recommendation methods (SoReg, TrustMF, Locabal and SPF), especially on the cold-start users recommendation and running time.

  • LPEducational Question Routing in Online Student Communities by Jakub Macina, Ivan Srba, Joseph Jay Williams and Maria Bielikova

    Students’ performance in Massive Open Online Courses (MOOCs) is enhanced by high quality discussion forums or recently emerging educational Community Question Answering (CQA) systems. Nevertheless, only a small number of students answer questions asked by their peers. This results in instructor overload, and many unanswered questions. To increase students’ participation, we present an approach for recommendation of new questions to students who are likely to provide answers. Existing approaches to such question routing proposed for non-educational CQA systems tend to rely on a few experts, which is not suitable because we want students to be engaged as it positively influences their learning outcomes. In tackling this novel educational question routing problem, our method (1) goes beyond previous question-answering data as it incorporate additional non-QA data from the course (to improve prediction accuracy and to involve a larger part of community) and (2) applies constraints on users’ workload (to prevent user overloading). We use an ensemble classifier for predicting students’ willingness to answer a question, as well as the students’ expertise for answering. We conducted an online evaluation of the proposed method using an A/B test in our CQA system deployed at an edX MOOC. The proposed method outperformed a baseline method (non-educational question routing enhanced with workload restriction) in recommendation accuracy, involving more community members, and average number of contributions.

  • LPEffective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System by Alain Starke, Martijn Willemsen and Chris Snijders

    People often struggle to find appropriate energy-saving measures to take in the household. Although recommender studies show that tailoring a system’s interaction method to the domain knowledge of the user can increase energy savings, they did not actually tailor the conservation advice itself. We present two large user studies in which we support users to make an energy-efficient behavioral change by presenting tailored energy-saving advice. Both systems use a one-dimensional, ordinal Rasch scale, which orders 79 energy-saving measures on their behavioral difficulty and link this to a user’s energy-saving ability for tailored advice. We established that recommending Rasch-based advice can reduce a user’s effort, increase system support and, in turn, increase choice satisfaction and lead to the adoption of more energy-saving measures. Moreover, follow-up surveys four weeks later point out that tailoring advice on its feasibility can lead to behavioral change.

  • LPExpediting Exploration by Attribute-to-Feature Mapping for Cold-Start Recommendations by Deborah Cohen, Michal Aharon, Yair Koren, Oren Somekh and Raz Nissim

    The item cold-start problem is inherent to collaborative filtering (CF) recommenders where items and users are represented by vectors in a latent space. It emerges since CF recommenders rely solely on historical user interactions to characterize their item inventory. As a result, an effective serving of new and trendy items to users may be delayed until enough user feedback is received, thus, reducing both users’ and content suppliers’ satisfaction.

    To mitigate this problem, many commercial recommenders apply random exploration and devote a small portion of their traffic to explore new items and gather interactions from random users. Alternatively, content or context information is combined into the CF recommender, resulting in a hybrid system. Another hybrid approach is to learn a mapping between the item attribute space and the CF latent feature space, and use it to characterize the new items providing initial estimates for their latent vectors.

    In this paper, we adopt the attribute-to-feature mapping approach to expedite random exploration of new items and present LearnAROMA – an advanced algorithm for learning the mapping, previously proposed in the context of classification. In particular, LearnAROMA learns a Gaussian distribution over the mapping matrix. Numerical evaluation demonstrates that this learning technique achieves more accurate initial estimates than logistic regression methods. We then consider a random exploration setting, in which new items are further explored as user interactions arrive. To leverage the initial latent vector estimates with the incoming interactions, we propose DynamicBPR – an algorithm for updating the new item latent vectors without retraining the CF model. Numerical evaluation reveals that DynamicBPR achieves similar accuracy as a CF model trained on all the ratings, using 70% less exploring users than conventional random exploration.

  • LPExploiting Socio-Economic Models for Lodging Recommendation in the Sharing Economy by Raul Sanchez-Vazquez, Jordan Silva and Rodrygo L.T. Santos

    Recent years have witnessed the emergence of sharing economy marketplaces, which enable users to share goods and services in a peer-to-peer fashion. A prominent example in the travel industry is Airbnb, which connects guests with hosts, allowing both to exchange cultural experiences in addition to the economic transaction. Nonetheless, Airbnb guest profiles are typically sparse, which limits the applicability of traditional lodging recommendation approaches. Inspired by recent socio-economic analyses of repurchase intent behavior on Airbnb, we propose a context-aware learning-to-rank approach for lodging recommendation, aimed to infer the user’s perception of several dimensions involved in choosing which lodging to book. In particular, we devise features aimed to capture the user’s price sensitivity as well as their perceived value of a particular lodging, the risk involved in choosing it rather than other available options, the authenticity of the cultural experience it could provide, and its overall perception by other users through word of mouth. Through a comprehensive evaluation using publicly available Airbnb data, we demonstrate the effectiveness of our proposed approach compared to a number of alternative recommendation baselines, including a simulation of Airbnb’s own recommender.

  • LPFairness-Aware Group Recommendation with Pareto Efficiency by Xiao Lin, Min Zhang, Yongfeng Zhang, Zhaoquan Gu, Yiqun Liu and Shaoping Ma

    Group recommendation has attracted significant research efforts for its importance in benefiting a group of users. This paper investigates the Group Recommendation problem from a novel aspect which tries to maximize the satisfaction of each group member while minimizing the unfairness between them.

    In this work, we present several semantics of the individual utility and propose two concepts of social welfare and fairness for modeling the overall utilities and the balance of group members. We formulate the problem as a multiple objective optimization problem and show its computational complexity (NP-Hardness Analysis) in different semantics. Given the multiple-objective nature of fairness-aware group recommendation problem, we provide an optimization framework for fairness-aware group recommendation from the perspective of Pareto Efficiency. We conduct extensive experiments on real-world datasets (one of which contains real group structures and purchase histories) and evaluate our algorithm with standard accuracy metrics. The results indicate that considering fairness in group recommendation can enhance the recommendation accuracy.

  • LPFewer Flops at the Top: Accuracy, Diversity, and Regularization in Two-Class Collaborative Filtering by Bibek Paudel, Thilo Haas and Abraham Bernstein

    In most existing recommender systems, implicit or explicit interactions are treated as positive links and all unknown interactions are treated as negative links. The goal is to suggest new links that will be perceived as positive links. However, as signed social networks and newer content services become common, it is important to distinguish between positive and negative preferences. Even in existing applications, the cost of a negative recommendation could be high when people are looking for new jobs, friends, or places to live.

    In this work, we develop novel probabilistic latent factor models to recommend positive links and compare with existing methods on five different openly available datasets. Our models are able to produce better ranking lists and are effective in the task of ranking positive links at the top and negative links at the bottom. Moreover, we find that modeling signed social networks and user preferences this way has the advantage of increasing diversity of recommendations. We also investigate the effect of regularization on the quality of recommendations, a matter that has not received enough attention in the literature. We find that regularization parameter heavily affects the quality of recommendations in terms of both accuracy and diversity.

  • LPFolding: Why Good Models Sometimes Make Spurious Recommendations by Doris Xin, Nicolas Mayoraz, Hubert Pham, Karthik Lakshmanan and John R. Anderson

    In recommender systems based on low rank factorization of a partially observed user-item matrix, a common phenomenon that plagues many otherwise effective models is the interleaving of good and spurious recommendations in the top-K results. A single incongruous recommendation can dramatically impact the perceived quality of a recommender system. In this work, we investigate folding, a major contributing factor to spurious recommendations. Folding refers to the unintentional overlap of disparate groups of users and items in the low-rank embedding vector space, induced by improper handling of missing data. We formally define a metric that quantifies the severity of folding in a trained system, to assist in diagnosing its potential to shock users with inappropriate recommendations. The folding metric complements existing information retrieval metrics that focus on the number of good recommendations and their ranks but ignore the impact of undesired recommendations. We motivate our definition of the folding metric on synthetic data and evaluate its effectiveness on both synthetic and real world datasets. We study the relationship between the folding metric and other characteristics of recommender systems and observe that optimizing for goodness metrics can lead to high folding and thus more spurious recommendations.

  • LPGetting Deep Recommenders Fit: Bloom Embeddings for Sparse Binary Input/Output Networks by Joan Serrà and Alexandros Karatzoglou

    Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these algorithms tend to have large input and output dimensionalities that dominate their overall size. This makes them difficult to train, due to the limited memory of graphical processing units, and difficult to deploy on mobile devices with limited hardware. To address these difficulties, we propose Bloom embeddings, a compression technique that can be applied to the input and output of neural network models dealing with sparse high-dimensional binary-coded instances. Bloom embeddings are computationally efficient, and do not seriously compromise the accuracy of the model up to 1/5 compression ratios. In some cases, they even improve over the original accuracy, with relative increases up to 12%. We evaluate Bloom embeddings on 7 data sets and compare it against 4 alternative methods, obtaining favorable results. We also discuss a number of further advantages of Bloom embeddings, such as ‘on-the-fly’ constant-time operation, zero or marginal space requirements, training time speedups, or the fact that they do not require any change to the core model architecture or training configuration.

  • LPInterpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction by Sungyong Seo, Jing Huang, Hao Yang and Yan Liu

    Recently, many e-commerce websites have encouraged their users to rate shopping items and write review text. This review text information has been very useful for understanding user preferences and item properties and it enhances the capability to make personalized recommendations of these websites. In this paper, we propose to model user preferences and item properties using convolutional neural networks (CNNs) with dual local and global attention, motivated by the superiority of CNNs to extract complex features. By using aggregated review text from a user and aggregated review text for an item, our model can learn the unique features (embedding) of each user and each item. These features are then used to predict ratings. We train these user and item networks jointly and this enables the interaction between users and items in a similar way to matrix factorization. The local attention gives us insight on a user’s preferences or an item’s properties. The global attention helps CNNs focus on semantic meanings of the whole review text. Thus, the combined local and global attentions enable an interpretable and better-learned representation of users and items. We validate the proposed models by applying popular review datasets in Yelp and Amazon and compare the results with matrix factorization (MF), the hidden factors as topics (HFT) model, and the recently proposed convolutional matrix factorization (ConvMF+). The proposed CNNs with dual attention model outperforms HFT and ConvMF+ in terms of mean square errors (MSE). In addition, we compare the user/item embeddings learned from these models for classification and recommendation. These results also confirm the superior quality of user/item embeddings learned from our model.

  • LPLearning to Rank with Trust and Distrust in Recommender Systems by Dimitrios Rafailidis and Fabio Crestani

    The sparsity of users’ preferences can significantly degrade the quality of recommendations in the collaborative filtering strategy. To account for the fact that the selections of social friends and foes may improve the recommendation accuracy, we propose a learning to rank model that exploits users’ trust and distrust relationships. Our learning to rank model focusses on the performance at the top of the list, with the recommended items that end-users will actually see. In our model, we try to push the relevant items of users and their friends at the top of the list, while ranking low those of their foes. Furthermore, we propose a weighting strategy to capture the correlations of users’ preferences with friends’ trust and foes’ distrust degrees in two intermediate trust- and distrust-preference user latent spaces, respectively. Our experiments on the Epinions dataset show that the proposed learning to rank model significantly outperforms other state-of-the-art methods in the presence of sparsity in users’ preferences and when a part of trust and distrust relationships is not available. Furthermore, we demonstrate the crucial role of our weighting strategy in our model, to balance well the influences of friends and foes on users’ preferences.

  • LPMetalearning for Context-aware Filtering: Selection of Tensor Factorization Algorithms by Tiago Cunha, Carlos Soares and André C.P.L.F. de Carvalho

    This work addresses the problem of selecting Tensor Factorization algorithms for the Context-aware Filtering recommendation task using a metalearning approach. The most important challenge of applying metalearning on new problems is the development of useful measures able to characterize the data, i.e. metafeatures. We propose an extensive and exhaustive set of metafeatures to characterize Context-aware Filtering recommendation task. These metafeatures take advantage of the tensor’s hierarchical structure via slice operations. The algorithm selection task is addressed as a Label Ranking problem, which ranks the Tensor Factorization algorithms according to their expected performance, rather than simply selecting the algorithm that is expected to obtain the best performance. A comprehensive experimental work is conducted on both levels, baselevel and metalevel (Tensor Factorization and Label Ranking, respectively). The results show that the proposed metafeatures lead to metamodels that tend to rank Tensor Factorization algorithms accurately and that the selected algorithms present high recommendation performance.

  • LPModeling the Assimilation-Contrast Effects in Online Product Rating Systems: Debiasing and Recommendations by Xiaoying Zhang, Junzhou Zhao and John C.S. Lui

    The unbiasedness of online product ratings, an important property to ensure that users’ ratings indeed reflect their true evaluations to products, is vital both in shaping consumer purchase decisions and providing reliable recommendations. Recent experimental studies showed that distortions from historical ratings would ruin the unbiasedness of subsequent ratings. How to “discover” the distortions from historical ratings in each single rating (or at the micro-level), and perform the “de-biasing operations” in real rating systems are the main objectives of this work. Using 42 million real customer ratings, we first show that users either “assimilate” or “contrast” to historical ratings under different scenarios: users conform to historical ratings if historical ratings are not far from the product quality (assimilation), while users deviate from historical ratings if they are significantly different from the product quality (contrast). This phenomenon can be explained by the well-known psychological argument: the “Assimilate-Contrast” theory. However, none of the existing works on modeling historical ratings’ influence have taken this into account, and this motivates us to propose the Historical Influence Aware Latent Factor Model (HIALF), the first model for real rating systems to capture and mitigate historical distortions in each single rating. HIALF also allows us to study the influence patterns of historical ratings from a modeling perspective, and it perfectly matches the assimilation and contrast effects we previously observed. Also, HIALF achieves significant improvements in predicting subsequent ratings, and accurately predicts the relationships revealed in previous empirical measurements on real ratings. Finally, we show that HIALF can contribute to better recommendations by decoupling users’ real preference from distorted ratings, and reveal the intrinsic product quality for wiser consumer purchase decisions.

  • LPMPR: Multi-Objective Pairwise Ranking by Rasaq Otunba, Raimi A. Rufai and Jessica Lin

    The recommendation challenge can be posed as the problem of predicting either item ratings or item rankings. The latter approach has proven more effective. Pairwise learning-to-rank techniques have been relatively successful. Hence, they are popularly used for learning recommender model parameters such as those in collaborative filtering (CF) models. The model parameters are learned by optimizing close smooth approximations of the non-smooth information retrieval (IR) metrics such as Mean Area Under ROC curve (AUC).

    Targeted campaigns are an alternative to item recommendations for increasing conversion. The user ranking task is referred to as audience retrieval. It is used in targeted campaigns to rank push campaign recipients based on their potential to convert. In this work, we consider the task of efficiently learning a ranking model that provides item recommendations and user rankings simultaneously. We adopt pairwise learning for this task. We refer to our novel approach as multi-objective pairwise ranking (MPR).

    We describe our approach and evaluate its performance by experiments.

  • LPPractical Lessons from Developing a Large-Scale Recommender System at Zalando by Antonino Freno

    Developing a real-world recommender system, i.e. for use in large-scale online retail, poses a number of different challenges. Interestingly, only a small part of these challenges are of algorithmic nature, such as how to select the most accurate model for a given use case. Instead, most technical problems usually arise from operational constraints, such as: adaptation to novel use cases; cost and complexity of system maintenance; capability of reusing pre-existing signal and integrating heterogeneous data sources.

    In this paper, we describe the system we developed in order to address those constraints at Zalando, which is one of the most popular online fashion retailers in Europe. In particular, we explain how moving from a collaborative filtering approach to a learning-to-rank model helped us to effectively tackle the challenges mentioned above, while improving at the same time the quality of our recommendations. A fairly detailed description of our software architecture is provided, along with an overview of the algorithmic approach. On the other hand, we present some of the offline and online experiments that we ran in order to validate our models.

  • LPRecommending Personalised News in Short User Sessions by Elena Viorica Epure, Benjamin Kille, Jon Espen Ingvaldsen, Rebecca Deneckere, Camille Salinesi and Sahin Albayrak

    News organizations employ personalized recommenders to target news articles to specific readers and thus foster engagement. Existing approaches rely on extensive user profiles. However, though often available, authentication is a rare choice of readers consulting news publishers’ websites. This paper proposes an approach for such cases. It provides a basic degree of personalization while complying with the key characteristics of news recommendation including news popularity, recency and the dynamics of reading behavior. We extent existing research on the dynamics of news reading behavior by focusing not only on the progress of reading interests over time but also on their relations. Reading interests are considered in three categories: short, medium and long-term. Combinations of these are evaluated in terms of added value to the recommendation’s performance and ensured news variety. The experiments with 17-month data logs from a German news publisher show that most frequent relations between news reading interests are constant in time but their probabilities change. Also, recommendations based on short-term with long-term interests result in increased accuracy while recommendations based on short-term with medium-term interests yield a higher news variety.

  • LPRecommending Product Sizes to Customers by Vivek Varadarajan Sembium, Rajeev Rastogi, Atul Saroop and Srujana Merugu

    We propose a novel latent factor model for recommending product size fits {Small, Fit, Large} to customers. Latent factors for customers and products in our model correspond to their physical true size, and are learnt from past product purchase and returns data. The outcome for a customer, product pair is predicted based on the difference between customer and product true sizes, and efficient algorithms are proposed for computing customer and product true size values that minimize two loss function variants. In experiments with Amazon shoe datasets, we show that our latent factor models incorporating personas, and leveraging return codes show a 17-21% AUC improvement compared to baselines. In an online A/B test, recommendations produced by our algorithms show an improvement of 33 basis points in percentage of Fit transactions over control.

  • LPSecure Multi-Party Protocols for Item-Based Collaborative Filtering by Erez Shmueli and Tamir Tassa

    Recommender systems have become extremely common in recent years, and are utilized in a variety of domains such as movies, music, news, products, restaurants, etc. While a typical recommender system bases its recommendations solely on users’ preference data collected by the system itself, the quality of recommendations can significantly be improved if several recommender systems (or vendors) share their data. However, such data sharing poses significant privacy and security challenges, both to the vendors and the users. In this paper we propose secure protocols for distributed item-based Collaborative Filtering. Our protocols allow to compute both the predicted ratings of items and their predicted rankings, without compromising privacy nor predictions’ accuracy. Unlike previous solutions in which the secure protocols are executed solely by the vendors, our protocols assume the existence of a mediator that performs intermediate computations on encrypted data supplied by the vendors. Such a mediated setting is advantageous over the non-mediated one since it enables each vendor to communicate solely with the mediator. This yields reduced communication costs and it allows each vendor to issue recommendations to its clients without being dependent on the availability and willingness of the other vendors to collaborate.

  • LPSequential User-based Recurrent Neural Network Recommendations by Tim Donkers, Benedikt Loepp and Jürgen Ziegler

    Recurrent Neural Networks are powerful tools for modeling sequences. They are flexibly extensible and can incorporate various kinds of information including temporal order. These properties make them well suited for generating sequential recommendations. In this paper, we extend Recurrent Neural Networks by considering unique characteristics of the Recommender Systems domain. One of these characteristics is the explicit notion of the user recommendations are specifically generated for. We show how individual users can be represented in addition to sequences of consumed items in a new type of Gated Recurrent Unit to effectively produce personalized next item recommendations. Offline experiments on two real-world datasets indicate that our extensions clearly improve objective performance when compared to state-of-the-art recommender algorithms and to a conventional Recurrent Neural Network.

  • LPThe Magic Barrier Revisited: Accessing Natural Limitations of Recommender Assessment by Kevin Jasberg and Sergej Sizov

    Recommender systems nowadays have many applications and are of great economic benefit. Hence, it is imperative for a success-oriented company to compare different of such systems and select the better one from them. For this purpose, various metrics of predictive accuracy are commonly used, such as the Root Mean Square Error (RMSE), or precision and recall, just to name a few of them. All these metrics more or less measure how well a recommender system can predict human behaviour.

    Unfortunately, human behaviour is always associated with some degree of uncertainty, making the evaluation of recommender systems difficult, since it is not clear whether a deviation is system-induced or just originates from the natural variability of human decision making. At this point, some Authors speculated that we may be reaching some magic barrier where this variability may prevent us from getting much more accurate.

    In this article, we will extend the existing theory of the Magic Barrier into a new probabilistic but yet pragmatic model. In particular, we will use methods from metrology and physics to develop easy-to-handle quantities for computation to describe the Magic Barrier for different accuracy metrics and provide suggestions for common application. This discussion is substantiated by comprehensive experiments with real users and large-scale simulations on a high performance cluster.

  • LPTranslation-based Recommendation by Ruining He, Wang-Cheng Kang and Julian McAuley

    Modeling the complex interactions between users and items as well as amongst items themselves is at the core of designing successful recommender systems. One classical setting is predicting users’ personalized sequential behavior (or ‘next-item’ recommendation), where the challenges mainly lie in modeling ‘third-order’ interactions between a user, her previously visited item(s), and the next item to consume. Existing methods typically decompose these higher-order interactions into a combination pairwise relationships, by way of which user preferences (user-item interactions) and sequential patterns (item-item interactions) are captured by separate components. In this paper, we propose a unified method, TransRec, to model such third-order relationships for large-scale sequential prediction. Methodologically, we embed items into a ‘transition space’ where users are modeled as translation vectors operating on item sequences. Empirically, this approach outperforms the state-of-the-art on a wide spectrum of real-world datasets.

  • LPTransNets: Learning to Transform for Recommendation by Rose Catherine and William Cohen

    Recently, deep learning methods have been shown to improve the performance of recommender systems over traditional methods, especially when review text is available. For example, a recent model, DeepCoNN, uses neural nets to learn one latent representation for the text of all reviews written by a target user, and a second latent representation for the text of all reviews for a target item, and then combines these latent representations to obtain state-of-the-art performance on recommendation tasks. We show that (unsurprisingly) much of the predictive value of review text comes from reviews of the target user for the target item. We then introduce a way in which this information can be used in recommendation, even when the target user’s review for the target item is not available. Our model, called TransNets, extends the DeepCoNN model by introducing an additional latent layer representing the target user-target item pair. We then regularize this layer, at training time, to be similar to another latent representation of the target user’s review of the target item. We show that TransNets and extensions of it improve substantially over the previous state-of-the-art.

  • LPUnderstanding How People Use Natural Language to Ask for Recommendations by Jie Kang, Kyle Condiff, Shuo Chang, Joseph A. Konstan, Loren Terveen, F. Maxwell Harper

    The technical barriers for conversing with recommender systems using natural language are vanishing. Already, there are commercial systems that facilitate interactions with an AI agent. For instance, it is possible to say “what should I watch” to an Apple TV remote to get recommendations. In this research, we investigate how users initially interact with a new natural language recommender to deepen our understanding of the range of inputs that these technologies can expect. We deploy a natural language interface to a recommender system, we observe users’ first interactions and follow-up queries, and we measure the differences between speaking- and typing-based interfaces. We employ qualitative methods to derive a categorization of users’ first queries (objective, subjective, and navigation) and follow-up queries (refine, reformulate, start over). We employ quantitative methods to determine the differences between speech and text, finding that speech inputs are typically longer and more conversational.

Back to Program

Diamond Supporter
Platinum Supporters
Gold Supporter
Silver Supporter
Special Supporters