Accepted Contributions

List of all long papers accepted for RecSys 2018 (in alphabetical order).
Proceedings will be available in the ACM Digital Library prior to the conference.

No matches were found!
  • LPAdaptive Collaborative Topic Modeling for Online Recommendation
    by Marie Al-Ghossein, Pierre-Alexandre Murena, Talel Abdessalem, Anthony Barré, Antoine Cornuéjols

    Collaborative filtering (CF) mainly suffers from rating sparsity and from the cold-start problem. Auxiliary information like texts and images has been leveraged to alleviate these problems, resulting in hybrid recommender systems (RS). Due to the abundance of data continuously generated in real-world applications, it has become essential to design online RS that are able to handle user feedback and the availability of new items in real-time. These systems are also required to adapt to drifts when a change in the data distribution is detected. In this paper, we propose an adaptive collaborative topic modeling approach, CoAWILDA, as a hybrid system relying on adaptive online Latent Dirichlet Allocation (AWILDA) to model new available items arriving as a document stream and incremental matrix factorization for CF. The topic model is maintained up-to-date in an online fashion and is retrained in batch when a drift is detected, using documents automatically selected by an adaptive windowing technique. Our experiments on real-world datasets prove the effectiveness of our approach for online recommendation.

  • LPCalibrated Recommendations
    by Harald Steck

    When a user has watched, say, 70 romance movies and 30 action movies, then it is reasonable to expect the personalized list of recommended movies to be comprised of about 70% romance and 30% action movies as well. This important property is known as calibration, and recently received renewed attention in the context of fairness in machine learning. In the recommended list of items, calibration ensures that the various (past) areas of interest of a user are reflected with their corresponding proportions. Calibration is especially important in light of the fact that recommender systems optimized toward accuracy (e.g., ranking metrics) in the usual offline-setting can easily lead to recommendations where the lesser interests of a user get crowded out by the user’s main interests-which we show empirically as well as in thought-experiments. This can be prevented by calibrated recommendations. To this end, we outline metrics for quantifying the degree of calibration, as well as a simple yet effective re-ranking algorithm for post-processing the output of any recommender system.

  • LPCategorical-Attributes-Based Item Classification for Recommender Systems
    by Qian Zhao, Jilin Chen, Minmin Chen, Sagar Jain, Alex Beutel, Francois Belletti, Ed Chi

    Many techniques to utilize side information of users and/or items as inputs to recommenders to improve recommendation, especially on cold-start items/users, have been developed over the years. In this work, we test the approach of utilizing item side information, specifically categorical attributes, in the output of recommendation models either through multi-task learning or hierarchical classification. We first demonstrate the efficacy of these approaches for both matrix factorization and neural networks with a medium-size real-word data set. We then show that they improve a neural-network based production model in an industrial-scale recommender system. We demonstrate the robustness of the hierarchical classification approach by introducing noise in building the hierarchy. Lastly, we investigate the generalizability of hierarchical classification on a simulated dataset by building two user models in which we can fully control the generative process of user-item interactions.

  • LPCausal Embeddings for Recommendation
    by Stephen Bonner, Flavian Vaslie

    Many current applications use recommendations in order to modify the natural user behavior, such as to increase the number of sales or the time spent on a website. This results in a gap between the final recommendation objective and the classical setup where recommendation candidates are evaluated by their coherence with past user behavior, by predicting either the missing entries in the user-item matrix, or the most likely next event. To bridge this gap, we optimize a recommendation policy for the task of increasing the desired outcome versus the organic user behavior. We show this is equivalent to learning to predict recommendation outcomes under a fully random recommendation policy. To this end, we propose a new domain adaptation algorithm that learns from logged data containing outcomes from a biased recommendation policy and predicts recommendation outcomes according to random exposure. We compare our method against state-of-the-art factorization methods and new approaches of causal recommendation and show significant improvements.

  • LPComfRide: A Smartphone based System for Comfortable Public Transport Recommendation
    by Rohit Verma, Surjya Ghosh, Saketh Mahankali, Niloy Ganguly, Bivas Mitra, Sandip Chakraborty

    Passenger comfort is a major factor influencing a commuter’s decision to avail public transport. Existing studies suggest that factors like overcrowding, jerkiness, traffic congestion etc. correlate well to passenger’s (dis)comfort. An online survey conducted with more than 300 participants from 12 different countries reveals that different personalized and context dependent factors influence passenger comfort during a travel by public transport. Leveraging on these findings, we identify correlations between comfort level and these dynamic parameters, and implement a smartphone based application, ComfRide, which recommends the most comfortable route based on user’s preference honoring her travel time constraint. We use a ‘Dynamic Input/Output Automata’ based composition model to capture both the wide varieties of comfort choices from the commuters and the impact of environment on the comfort parameters. Evaluation of ComfRide, involving 50 participants over 28 routes in a state capital of India, reveals that recommended routes have on average 30% better comfort level than Google map recommended routes, when a commuter gives priority to specific comfort parameters of her choice.

  • LPDeep Reinforcement Learning for Page-wise Recommendations
    by Xiangyu Zhao, Long Xia, Liang Zhang, Zhuoye Ding, Dawei Yin, Jiliang Tang

    Recommender systems can mitigate the information overload problem by suggesting users’ personalized items. In real-world recommendations such as e-commerce, a typical interaction between the system and its users is — users are recommended a page of items and provide feedback; and then the system recommends a new page of items. To effectively capture such interaction for recommendations, we need to solve two key problems — (1) how to update recommending strategy according to user’s real-time feedback, and 2) how to generate a page of items with proper display, which pose tremendous challenges to traditional recommender systems. In this paper, we study the problem of page-wise recommendations aiming to address aforementioned two challenges simultaneously. In particular, we propose a principled approach to jointly generate a set of complementary items and the corresponding strategy to display them in a 2-D page; and propose a novel page-wise recommendation framework based on deep reinforcement learning, DeepPage, which can optimize a page of items with proper display based on real-time feedback from users. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.

  • LPEffects of Personal Characteristics on the Music Recommender with Different Controllability
    by Yucheng Jin, Nava Tintarev, Katrien Verbert

    Previous research has found that enabling users to control the recommendation process increases user satisfaction with recommendations. However, providing additional controls also increases cognitive load, and different users have different needs for control. Therefore, in this study, we investigate the effect of two personal characteristics: musical sophistication and visual memory capacity. We designed a visual user interface, on top of a commercial music recommender, that incorporates different controls: interactions with recommendations (i.e., the output of a recommender system), the user profile (i.e., the top listened songs), and algorithm parameters (i.e., weights in an algorithm). We created eight experimental settings with all possible combinations of these three user controls and conducted a between-subjects study (N=240), to explore how these controls influence cognitive load and recommendation acceptance for different personal characteristics. We found that controlling recommendations is the most favorable single control element. In addition, controlling recommendations and algorithm parameters is the most beneficial setting with multiple controls. Moreover, the participants with high musical sophistication are more likely to accept recommendations, suggesting that they perceive recommendations to be of higher quality. However, we found no effect of visual working memory on either cognitive load or recommendation acceptance. This work contributes an understanding of how to design control that hit the sweet spot between the perceived quality of recommendations and acceptable cognitive load.

  • LPEliciting Pairwise Preferences in Recommender Systems
    by Saikishore Kalloori, Francesco Ricci, Rosella Gennari

    Preference data in the form of ratings or likes for items are widely used in many Recommender Systems (RSs). However, previous research has shown that even item comparisons, which generate pairwise preference data, can be used to model user preferences. Moreover, pairwise preferences can be effectively combined with ratings to compute recommendations. In such hybrid approaches, the RS requires to elicit from the user both types of preference data. In this work, we aim at identifying how and when to elicit pairwise preferences, i.e., when this form of user preference data is more meaningful for the user to express and more beneficial for the system. We conducted an online A/B test and compared a rating-only based system variant with another variant that allows the user to enter both types of preferences. Our results demonstrate that pairwise preferences are valuable and useful especially when the user is focusing on a specific type of items and by incorporating pairwise preferences, the system can generate better recommendations than a state of the art rating-only based solution. Additionally, our results indicate that there exists a dependency between the user’s personality and the perceived system usability and the satisfaction for the preference elicitation procedure, which varies if only ratings or a combination of ratings and pairwise preferences are elicited.

  • LPEnhancing Structural Diversity in Social Networks by Recommending Weak Ties
    by Javier Sanz-Cruzado, Pablo Castells

    Contact recommendation has become a common functionality in online social platforms, and an established research topic in the social networks and recommender systems fields. Predicting and recommending links has been mainly addressed to date as an accuracy-targeting problem. In this paper we put forward a different perspective, considering that correctly predicted links may not be all equally valuable. Contact recommendation brings an opportunity to drive the structural evolution towards desirable properties of the network as a whole, beyond the sum of the isolated gains for the individual users to whom recommendations are delivered –global properties that we may want to assess and promote as explicit recommendation targets.

    In this perspective, we research the definition of relevant diversity metrics drawing from social network analysis concepts, and linking to prior diversity notions in recommender systems. In particular, we elaborate on the notion of weak tie recommendation as a means to enhance the structural diversity of networks. In order to show the signification of the proposed metrics, we report experiments with Twitter data illustrating how state of the art contact recommendation methods compare in terms of our metrics; we examine the tradeoff with accuracy, and we show that diverse link recommendations result in a corresponding diversity enhancement in the flow of information through the network, with potential implications in mitigating filter bubbles.

  • LPExplore, Exploit, and Explain: Personalizing Explainable Recommendations with Bandits
    by James McInerney, Benjamin Lacker, Samantha Hansen, Karl Higley, Hugues Bouchard, Alois Gruson, Rishabh Mehrotra

    The multi-armed bandit is an important framework for balancing exploration with exploitation in recommendation. Exploitation recommends content (e.g., products, movies, music playlists) with the highest predicted user engagement and has traditionally been the focus of recommender systems. Exploration recommends content with uncertain predicted user engagement for the purpose of gathering more information. The importance of exploration has been recognized in recent years, particularly in settings with new users, new items, non-stationary preferences and attributes. In parallel, explaining recommendations (“recsplanations”) is crucial if users are to understand their recommendations. Existing work has looked at bandits and explanations independently. We provide the first method that combines both in a principled manner. In particular, our method is able to jointly (1) learn which explanations each user responds to; (2) learn the best content to recommend for each user; and (3) balance exploration with exploitation to deal with uncertainty. Experiments with historical log data and tests with live production traffic in a large-scale music recommendation service show a significant improvement in user engagement.

  • LPExploring Author Gender in Book Rating and Recommendation
    by Michael D. Ekstrand, Mucun Tian, Mohammed Imran R. Kazi, Hoda Mehrpouyan, Daniel Kluver

    Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items. Many of the patterns in rating datasets reflect important real-world differences between the various users and items in the data; other patterns may be irrelevant or possibly undesirable for social or ethical reasons, particularly if they reflect undesired discrimination, such as discrimination in publishing or purchasing against authors who are women or ethnic minorities. In this work, we examine the response of collaborative filtering recommender algorithms to the distribution of their input data with respect to a dimension of social concern, namely content creator gender. Using publicly-available book ratings data, we measure the distribution of the genders of the authors of books in user rating profiles and recommendation lists produced from this data. We find that common collaborative filtering algorithms differ in the gender distribution of their recommendation lists, and in the relationship of that output distribution to user profile distribution.

  • LPGeneration Meets Recommendation: Proposing Novel Items for Groups of Users
    by Thanh Vinh Vo, Harold Soh

    Consider a movie studio aiming to produce a set of new movies for summer release: What types of movies it should produce? Who would the movies appeal to? How many movies should it make? Similar issues are encountered by a variety of organizations, e.g., mobile-phone manufacturers and online magazines, who have to create new (non-existent) items to satisfy groups of users with different preferences. In this paper, we present a joint problem formalization of these interrelated issues, and propose novel generative methods that address these questions simultaneously. Specifically, we leverage on the latent space obtained by training a deep generative model—the Variational Autoencoder (VAE)—via a loss function that incorporates both rating performance and item reconstruction terms. We use a greedy search algorithm that utilize this learned latent space to jointly obtain K plausible new items, and user groups that would find the items appealing. An evaluation of our methods on a synthetic dataset indicates that our approach is able to generate novel items similar to highly-desirable unobserved items. As a case study on real-world data, we applied our method to the MART abstract art and Movielens Tag Genome dataset, which resulted in a promising results: small but diverse sets of proposed items.

  • LPGet Me The Best: Get Me The Best: Predicting Best Answerers in Community Question Answering sites
    by Rohan Ravindra Tondulkar, Manisha Dubey, Maunendra Sankar Desarkar

    There has been a massive rise in the use of Community Question and Answering (CQA) forums to get solutions to various technical and non-technical queries. One common problem faced in CQA is the small number of experts, which leaves many questions unanswered. This paper addresses the challenging problem of predicting the best answerer for a new question and thereby recommending the best expert for the same. Although there are work in the literature that aim to find possible answerers for questions posted in CQA, very few algorithms exist for finding the best answerer whose answer will satisfy the information need of the original Poster. For finding answerers, existing approaches mostly use features based on content and tags associated with the questions. There are few approaches that additionally consider the users’ history. In this paper, we propose an approach that considers a comprehensive set of features including but not limited to text representation, tag based similarity as well as multiple user-based features that target users’ availability, agility as well as expertise for predicting the best answerer for a given question. We also include features that give incentives to users who answer less but more important questions over those who answer a lot of questions of less importance. A learning to rank algorithm is used to find the weight for each feature. Experiments conducted on a real dataset from Stack Exchange show the efficacy of the proposed method in terms of multiple evaluation metrics for accuracy, robustness and real time performance.

  • LPItem Recommendation on Monotonic Behavior Chains
    by Mengting Wan, Julian McAuley

    ‘Explicit’ and ‘implicit’ feedback in recommender systems have been studied for many years, as two relatively isolated areas. However many real-world systems involve a spectrum of both implicit and explicit signals, ranging from clicks and purchases, to ratings and reviews. A natural question is whether implicit signals (which are dense but noisy) might help to predict explicit signals (which are sparse but reliable), or vice versa. Thus in this paper, we propose an item recommendation framework which jointly models this spectrum of interactions. Our main observation is that in many settings, feedback signals exhibit monotonic dependency structures, i.e., any signal necessarily implies the presence of a weaker (or more implicit) signal (a ‘review’ action implies a ‘purchase’ action, which implies a ‘click’ action, etc.). We refer to these structures as ‘monotonic behavior chains,’ for which we develop new algorithms that exploit these dependencies. Using several new and existing datasets that exhibit a variety of feedback types, we demonstrate the quantitative performance of our approaches. We also perform qualitative analysis to uncover the relationships between different stages of implicit vs. explicit signals.

  • LPInteractive Recommendation via Deep Neural Memory Augmented Contextual Bandits
    by Yilin Shen, Yue Deng, Avik Ray, Hongxia Jin

    Personalized recommendation with user interactions has become increasingly popular nowadays in many applications with dynamic change of contents (news, media, etc.). Existing approaches model user interactive recommendation as a contextual bandit problem to balance the trade-off between exploration and exploitation. However, these solutions require a large number of interactions with each user to provide high quality personalized recommendations. To mitigate this limitation, we design a novel deep neural memory augmented mechanism to model and track the history state for each user based on his previous interactions. As such, the user’s preferences on new items can be quickly learned within a small number of interactions. Moreover, we develop new algorithms to leverage large amount of all users’ history data for offline model training and online model fine tuning for each user with the focus of policy evaluation. Extensive experiments on different synthetic and real-world datasets validate that our proposed approach consistently outperforms a variety of state-of-the-art approaches.

  • LPInterpreting User Inaction in Recommender Systems
    by Qian Zhao, Martijn Willemsen, Gediminas Adomavicius, F. Maxwell Harper, Joseph A. Konstan

    Temporally, users browse and interact with items in recommender systems. However, for most systems, the majority of the displayed items do not elicit any action from users. In other words, the user-system interaction process includes three aspects: browsing, action, and inaction. Prior recommender systems literature has focused more on actions than on browsing or inaction. In this work, we deployed a field survey in a live movie recommender system to interpret what inaction means from both the user’s and the system’s perspective, guided by psychological theories of human decision making. We further systematically study factors to infer the reasons of user inaction and demonstrate with offline data sets that this descriptive and predictive inaction model can provide benefits for recommender systems in terms of both action prediction and recommendation timing.

  • LPJudging Similarity: A User-Centric Study of Related Item Recommendations
    by Yuan Yao, F. Maxwell Harper

    Related item recommenders operate in the context of a particular item. For instance, a music system’s page about the artist Radiohead might recommend other similar artists such as The Flaming Lips. Often central to these recommendations is the computation of similarity between pairs of items. Prior work has explored many algorithms and features that allow for the computation of similarity scores, but little work has evaluated these approaches from a user-centric perspective. In this work, we build and evaluate six similarity scoring algorithms that span a range of activity- and content-based approaches. We evaluate the performance of these algorithms using both offline metrics and a new set of more than 22,000 user-contributed evaluations. We integrate these results with a survey of more than 700 participants concerning their expectations about item similarity and related item recommendations. We find that content-based algorithms outperform ratings- and clickstream-based algorithms in terms of how well they match user expectations for similarity and recommendation quality. Our results yield a number of implications to guide the construction of related item recommendation algorithms.

  • LPMultistakeholder Recommendation with Provider Constraints
    by Ozge Surer, Robin Burke, Edward C. Malthouse

    Recommender systems are typically designed to optimize the utility of the end user. In many settings, however, the end user is not the only stakeholder and this exclusive focus may produce unsatisfactory results for the others. One such setting is found in multisided platforms, which act as middlemen bringing together buyers and sellers. In such platforms, it may be necessary to jointly optimize the value for both buyers and sellers. This paper proposes a constraint-based integer programming optimization model, in which different sets of constraints are used to reflect the goals of multiple stakeholders. This model is applied as a post-processing step, so it can easily be added onto an existing recommendation system to make it multistakeholder aware. For computational tractability with larger data sets, we reformulate the integer problem using the Lagrangian dual and use subgradient optimization. In experiments with two data sets, we evaluate empirically the interaction between the utilities of buyers and sellers and show that our approximation can achieve good upper and lower bounds in practical situations.

  • LPNeural Gaussian Mixture Model for Review-based Rating Prediction
    by Dong Deng, Liping Jing, Jian Yu, Sun Shaolong, Haofei Zhou

    Reviews has been proven to be an important information in recommendation. Different from the overall user-item rating matrix, it can provide textual information that exhibits why a user likes an item or not. Recently, more and more researchers have paid attention on review-based rating prediction. There are two challenging issues: how to extract representative features to characterize users / items from reviews and how to leverage them for recommendation system. In this paper, we propose a Neural Gaussian Mixture Model for review-based rating prediction task (NGMM). Among it, the textual review information is used to construct two parallel neural networks for users and items respectively, so that the users’ preferences and items’ properties can be sufficiently extracted and written as two latent vectors. A shared layer is introduced on the top to couple these two networks together and model user-item rating based on the features learned from reviews. Specifically, each rating is modeled via a Gaussian mixture model, where each Gaussian component has zero variance, the mean described by the corresponding component in user’s latent vector and the weight indicated by the corresponding component in item’s latent vector. Extensive experiments are conducted on five real-world Amazon review datasets. The experimental results have demonstrated that our proposed NGMM model achieves the state-of-the-art performance in review-based rating prediction task.

  • LPNo More Ready-made Deals: Constructive Recommendation for Telco Service Bundling
    by Paolo Dragone, Giovanni Pellegrini, Michele Vescovi, Katya Tentori, Andrea Passerini

    We propose a new constraint-based recommendation system for service and product bundling in the domain of telecommunication and multimedia. Using this system, users can easily generate the combined service plan (including broadband, mobile connection, media content subscription, and device leasing, akin to those commonly offered by telco operators) that best suits their needs within a vast range of candidates. The system exploits the recent constructive preference elicitation framework, which brings together the benefits of constraint-based recommenders and data-driven preference learning algorithms. The feasible space of possible plans is implicitly defined by a set of variables (components) and constraints, which allows us to flexibly model an exponentially large solution domain (bundle offers) without the need of explicitly enumerating a-priori all admissible configurations. The preferences of the user are modeled by a utility function over the components of the plan. The utility parameters are estimated by interacting with the user via coactive learning. Recommendations are generated by structured-output prediction, which in our case translates into solving a constraint optimization problem to find the feasible configuration with the highest utility. In this paper, we detail the structure of our system, the underlying learning technique, as well as the methodology and results of an empirical validation study which involved more than 130 participants. The system turned out to be highly usable with respect to both time and number of interactions, and its outputs were found much more satisfactory than those obtained with standard techniques used in the market.

  • LPOn the Robustness and Discriminative Power of IR Metrics for Top-N Recommendation
    by Daniel Valcarce, Alejandro Bellogin, Javier Parapar, Pablo Castells

    The evaluation of Recommender Systems is still an open issue in the field. Despite its limitations, offline evaluation usually constitutes the first step in assessing recommendation methods due to its reduced costs and high reproducibility. Selecting the appropriate metric is a central issue in offline evaluation. Among the properties of recommendation systems, ranking accuracy attracts the most attention nowadays. In this paper, we aim to shed light on the advantages of different ranking metrics which were previously used in Information Retrieval and are now typically used for assessing top-N recommender systems. We propose methodologies for comparing the robustness and the discriminative power of different metrics. On the one hand, we study the influence of cut-offs and we find that deeper cut-offs offer greater robustness and discriminative power. On the other hand, we find that precision offers high robustness and Normalised Discounted Cumulative Gain provides the best discriminative power.

  • LPOptimally Balancing Receiver and Recommended Users’ Importance in Reciprocal Recommender Systems
    by Akiva Kleinerman, Rosenfeld Ariel, Francesco Ricci, Sarit Kraus

    Online platforms which assist people in finding a suitable partner or match, such as online dating and job recruiting environments, have become increasingly popular in the last decade. Many of these platforms include recommender systems which aim to help users discover other people who will be also interested in them. These recommender systems benefit from contemplating the interest of both sides of the recommended match, however the question of how to optimally balance the interest and the response of both sides remains open. In this study we present a novel recommendation method for recommending people to people. For each user receiving a recommendation, our method finds the optimal balance of two criteria: a) the user’s likelihood to accept the recommendation; and b) the recommended user’s likelihood to positively respond. We extensively evaluate our recommendation method with a group of active users from an operational online dating site. We find that our method is significantly more effective in increasing the number of successful interactions compared to a current state-of-the-art recommendation method.

  • LPPreference Elicitation as an Optimization Problem
    by Anna Sepliarskaia, Julia Kiseleva, Filip Radlinski, Maarten de Rijke

    The new user cold-start problem arises when a recommender system does not yet have any information about a user. A common solution to this problem is to generate a user profile as part of the sign-up process, by asking the user to rate several items. We propose a new elicitation method to generate a static preference questionnaire (SPQ) that asks a new user to make pairwise comparisons between items by posing relative preference questions. Using a latent factor model, SPQ improves personalized recommendations by choosing a minimal and diverse set of static preference questions to ask any new user. We are the first to rigorously prove which optimization task should be solved in order to select the next preference question for static questionnaires. Our theoretical results are confirmed by extensive experimentation. We test the performance of SPQ on two real-world datasets, under two experimental conditions: simulated, when users behave according to LFM, and real, in which there is no user rating model. SPQ reduces the questionnaire length that is necessary to make accurate recommendations for new users by up to a factor of three compared to state-of-the-art preference elicitation methods. Moreover, solving the right optimization task, SPQ shows better performance than baselines with dynamically generated questions.

  • LPProviding Explanations for Recommendations in Reciprocal Environments
    by Akiva Kleinerman, Rosenfeld Ariel, Sarit Kraus

    Automated platforms which support users in finding a mutually beneficial match, such as online dating and job recruitment sites, are becoming increasingly popular. These platforms often include recommender systems that assist users in finding a suitable match. While recommender systems which provide explanations for their recommendations have shown many benefits, explanation methods have yet to be adapted and tested in recommending suitable matches. In this paper, we introduce and extensively evaluate the use of reciprocal explanations– explanations which provide reasoning as to why both parties are expected to benefit from the match. Through an extensive empirical evaluation, in both simulated and real-world dating platforms with 287 human participants, we find that when the acceptance of a recommendation involves a significant cost (e.g., monetary or emotional), reciprocal explanations outperform standard explanation methods which consider the recommendation receiver alone. However, to the contrary of to what one may expect, when the cost of accepting a recommendation is negligible, reciprocal explanations are shown to be less effective than the traditional explanation methods.

  • LPQuality-Aware Neural Complementary Item Recommendation
    by Yin Zhang, Haokai Lu, Wei Niu, James Caverlee

    Complementary item recommendation finds products that go well with one another (e.g., a camera and a specific lens). While they are ubiquitous, the dimensions by which items go together can vary by both product and category, making it difficult to detect complementary items at scale. Moreover, in practice, user preferences for complementary items can be complex combinations of item quality and evidence of complementarity. Hence, we propose a new neural complementary recommender Encore that can jointly learn complementary item relationships and user preferences. Specifically, Encore (i) effectively combines and balances both stylistic and functional evidence of complementary items across item categories; (ii) naturally models item latent quality for complementary items through Bayesian inference of customer ratings; and (iii) builds a novel neural network model to learn the complex (non-linear) relationships between items for flexible and scalable complementary product recommendations. Through experiments over large Amazon datasets, we find that Encore effectively learns complementary item relationships, leading to an improvement in accuracy of 15.5% on average versus the next-best alternative.

  • LPRecurrent Knowledge Graph Embedding for Effective Recommendation
    by Zhu Sun, Jie Yang, Jie Zhang, Alessandro Bozzon, LongKai Huang, Chi Xu

    Knowledge graphs (KGs) have proven to be effective to improve recommendation. Existing methods mainly rely on hand-engineered features from KGs, which requires domain knowledge. This paper presents RKGE, a KG embedding approach that automatically learns semantic representations of entities and paths between entities for characterizing user preferences towards items. Specifically, RKGE employs a novel recurrent network architecture that contains a batch of recurrent networks to model the semantics of paths linking a same entity pair, which are seamlessly fused into recommendation. It further employs a pooling operator to discriminate the saliency of different paths in characterizing user preferences towards items. Extensive validation shows the superiority of RKGE against the state-of-the-art. Furthermore, we show that RKGE provides meaningful explanations for recommendation results.

  • LPSpectral Collaborative Filtering
    by Lei Zheng, Chun-Ta Lu, Fei Jiang, Jiawei Zhang, Philip Yu

    Despite the popularity of Collaborative Filtering (CF), CF-based methods are haunted by the cold-start problem, which has a significantly negative impact on users’ experiences with Recommender Systems (RS). In this paper, to overcome the aforementioned drawback, we first formulate the relationships between users and items as a bipartite graph. Then, we propose a new spectral convolution operation directly performing in the spectral domain, where not only the proximity information of a graph but also the connectivity information hidden in the graph are revealed. With the proposed spectral convolution operation, we build a deep recommendation model called Spectral Collaborative Filtering (SpectralCF). Benefiting from the rich information of connectivity existing in the spectral domain, SpectralCF is capable of discovering deep connections between users and items and therefore, alleviates the cold-start problem for CF. To the best of our knowledge, SpectralCF is the first CF-based method directly learning from the spectral domains of user-item bipartite graphs. We apply our method on several standard datasets. It is shown that SpectralCF significantly outperforms state-of-the-art models. Code and data are available at

  • LPThe Art of Drafting: A Team-Oriented Hero Recommendation System for Multiplayer Online Battle Arena Games
    by Zhengxing Chen, Truong-Huy D. Nguyen, Yuyu Xu, Chris Amato, Seth Cooper, Yizhou Sun, Magy Seif El-Nasr

    Multiplayer Online Battle Arena (MOBA) games have received increasing popularity recently. In a match of such games, players compete in two teams of five, each controlling an in-game avatars, known as heroes, selected from a roster of more than 100. The selection of heroes, also known as pick or draft, takes place before the match starts and alternates between the two teams until each player has selected one hero. Heroes are designed with different strengths and weaknesses to promote team cooperation in a game. Intuitively, heroes in a strong team should complement each other’s strengths and suppressing those of opponents. Hero drafting is therefore a challenging problem due to the complex hero-to-hero relationships to consider. In this paper, we propose a novel hero recommendation system that suggests heroes to add to an existing team while maximizing the team’s prospect for victory. To that end, we model the drafting between two teams as a combinatorial game and use Monte Carlo Tree Search (MCTS) for estimating the values of hero combinations. Our empirical evaluation shows that hero teams drafted by our recommendation algorithm have significantly higher win rate against teams constructed by other baseline and state-of-the-art strategies.

  • LPTranslation-based Factorization Machines for Sequential Recommendation
    by Rajiv Pasricha, Julian McAuley

    Sequential recommendation algorithms aim to predict users’ future behavior given their historical interactions over time. A recent line of work has achieved state-of-the-art performance on sequential recommendation tasks by adapting ideas from metric learning and knowledge-base completion. These algorithms replace inner products with low-dimensional embeddings and distance functions, employing a simple translation dynamic to model user behavior over time.

    In this paper, we propose TransFM, a model that combines translation and metric-based approaches for sequential recommendation with Factorization Machines (FMs). Doing so allows us to reap the benefits of FMs (in particular, the ability to straightforwardly incorporate content-based features), while enhancing the state-of-the-art performance of translation-based models is sequential settings. Specifically, we learn an embedding and translation space for each feature dimension, replacing the inner product with the squared Euclidean distance to measure interaction strength between features. Like FMs, we show that the model equation for TransFM can be computed in linear time and optimized using classical techniques. As TransFM operates on arbitrary feature vectors, additional content information can be easily incorporated without significant changes to the model itself. Empirically, the performance of TransFM significantly increases when taking content features into account, outperforming state-of-the-art models on the sequential recommendation task for a wide variety of datasets.

  • LPUnbiased Offline Recommender Evaluation for Missing-Not-At-Random Implicit Feedback
    by Longqi Yang, Yin Cui, Yuan Xuan, Chenyang Wang, Serge Belongie, Deborah Estrin

    Implicit-feedback recommenders (ImplicitRec) leverage positive-only user-item interactions, such as clicks, to learn personalized user preferences. Recommenders are often evaluated and compared offline using datasets collected from online platforms. These platforms are subject to popularity bias (i.e., popular items are more likely to be presented and interacted with), and therefore logged ground truth data is Missing-Not-At-Random (MNAR). As a result, the existing Average-Over-All (AOA) evaluation is biased towards accurately recommending trendy items. Prior research on debiasing MNAR data for explicit-rating recommenders (ExplicitRec) are not directly applicable due to the fact that negative user opinion is not available in implicit feedback. In this paper, we (a) show that existing offline evaluations for ImplicitRec are biased and (b) develop an unbiased and practical offline evaluator for implicit MNAR datasets using the inverse-propensity-weighting technique. Through extensive experiments using three real world datasets and four classical and state-of-the-art algorithms, we show that (a) popularity bias is widely manifested in item presentation and interaction; (b) evaluation bias due to MNAR data pervasively exists in most ImplicitRec; and (c) the unbiased estimator can correct the potential inaccurate judgements of algorithms’ relative utilities.

  • LPWhy I like it: Multi-task Learning for Recommendation and Explanation
    by Yichao Lu, Ruihai Dong, Barry Smyth

    We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction, and adversarial sequence to sequence learning for explanation generation. The result is evaluated using real-world datasets to demonstrate improved rating prediction performance, compared to state-of-the-art alternatives, while producing effective, personalized explanations.

Back to Program

Diamond Supporter
Platinum Supporters
Gold Supporters
Silver Supporters
Special Supporter