arXiv subjects

Julian McAuley

Publications and source records attributed to Julian McAuley.

At least 325 records · Page 18Linked to original sources

arXiv2017

Deduplication in a massive clinical note dataset

Duplication, whether exact or partial, is a common issue in many datasets. In clinical notes data, duplication (and near duplication) can arise for many reasons, such as the pervasive use of templates, copy-pasting, or notes being generated by automated procedures. A key challenge in removing such near duplicates is the size of such datasets; our own dataset consists of more than 10 million notes. To detect and correct such duplicates requires algorithms that both accurate and highly scalable. We describe a solution based on Minhashing with Locality Sensitive Hashing. In this paper, we present the theory behind this method and present a database-inspired approach to make the method scalable. We also present a clustering technique using disjoint sets to produce dense clusters, which speeds up our algorithm.

cs.DB↗

arXiv2016

Predicting risky behavior in social communities

Predicting risk profiles of individuals in networks (e.g.~susceptibility to a particular disease, or likelihood of smoking) is challenging for a variety of reasons. For one, `local' features (such as an individual's demographic information) may lack sufficient information to make informative predictions; this is especially problematic when predicting `risk,' as the relevant features may be precisely those that an individual is disinclined to reveal in a survey. Secondly, even if such features are available, they still may miss crucial information, as `risk' may be a function not just of an individual's features but also those of their friends and social communities. Here, we predict individual's risk profiles as a function of both their local features and those of their friends. Instead of modeling influence from the social network directly (which proved difficult as friendship links may be sparse and partially observed), we instead model influence by discovering social communities in the network that may be related to risky behavior. The result is a model that predicts risk as a function of local features, while making up for their deficiencies and accounting for social influence by uncovering community structure in the network. We test our model by predicting risky behavior among adolescents from the Add health data set, and hometowns among users in a Facebook ego net. Compared to prediction by features alone, our model demonstrates better predictive accuracy when measured as a whole, and in particular when measured as a function of network "richness."

cs.SI↗

arXiv2016

Modeling Ambiguity, Subjectivity, and Diverging Viewpoints in Opinion Question Answering Systems

Product review websites provide an incredible lens into the wide variety of opinions and experiences of different people, and play a critical role in helping users discover products that match their personal needs and preferences. To help address questions that can't easily be answered by reading others' reviews, some review websites also allow users to pose questions to the community via a question-answering (QA) system. As one would expect, just as opinions diverge among different reviewers, answers to such questions may also be subjective, opinionated, and divergent. This means that answering such questions automatically is quite different from traditional QA tasks, where it is assumed that a single `correct' answer is available. While recent work introduced the idea of question-answering using product reviews, it did not account for two aspects that we consider in this paper: (1) Questions have multiple, often divergent, answers, and this full spectrum of answers should somehow be used to train the system; and (2) What makes a `good' answer depends on the asker and the answerer, and these factors should be incorporated in order for the system to be more personalized. Here we build a new QA dataset with 800 thousand questions---and over 3.1 million answers---and show that explicitly accounting for personalization and ambiguity leads both to quantitatively better answers, but also a more nuanced view of the range of supporting, but subjective, opinions.

cs.IR↗

arXiv2016

Learning Compatibility Across Categories for Heterogeneous Item Recommendation

Identifying relationships between items is a key task of an online recommender system, in order to help users discover items that are functionally complementary or visually compatible. In domains like clothing recommendation, this task is particularly challenging since a successful system should be capable of handling a large corpus of items, a huge amount of relationships among them, as well as the high-dimensional and semantically complicated features involved. Furthermore, the human notion of "compatibility" to capture goes beyond mere similarity: For two items to be compatible---whether jeans and a t-shirt, or a laptop and a charger---they should be similar in some ways, but systematically different in others. In this paper we propose a novel method, Monomer, to learn complicated and heterogeneous relationships between items in product recommendation settings. Recently, scalable methods have been developed that address this task by learning similarity metrics on top of the content of the products involved. Here our method relaxes the metricity assumption inherent in previous work and models multiple localized notions of 'relatedness,' so as to uncover ways in which related items should be systematically similar, and systematically different. Quantitatively, we show that our system achieves state-of-the-art performance on large-scale compatibility prediction tasks, especially in cases where there is substantial heterogeneity between related items. Qualitatively, we demonstrate that richer notions of compatibility can be learned that go beyond similarity, and that our model can make effective recommendations of heterogeneous content.

cs.IR↗

arXiv2016

Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation

Predicting personalized sequential behavior is a key task for recommender systems. In order to predict user actions such as the next product to purchase, movie to watch, or place to visit, it is essential to take into account both long-term user preferences and sequential patterns (i.e., short-term dynamics). Matrix Factorization and Markov Chain methods have emerged as two separate but powerful paradigms for modeling the two respectively. Combining these ideas has led to unified methods that accommodate long- and short-term dynamics simultaneously by modeling pairwise user-item and item-item interactions. In spite of the success of such methods for tackling dense data, they are challenged by sparsity issues, which are prevalent in real-world datasets. In recent years, similarity-based methods have been proposed for (sequentially-unaware) item recommendation with promising results on sparse datasets. In this paper, we propose to fuse such methods with Markov Chains to make personalized sequential recommendations. We evaluate our method, Fossil, on a variety of large, real-world datasets. We show quantitatively that Fossil outperforms alternative algorithms, especially on sparse datasets, and qualitatively that it captures personalized dynamics and is able to make meaningful recommendations.

cs.IR↗

arXiv2016

Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation

Understanding users' interactions with highly subjective content---like artistic images---is challenging due to the complex semantics that guide our preferences. On the one hand one has to overcome `standard' recommender systems challenges, such as dealing with large, sparse, and long-tailed datasets. On the other, several new challenges present themselves, such as the need to model content in terms of its visual appearance, or even social dynamics, such as a preference toward a particular artist that is independent of the art they create. In this paper we build large-scale recommender systems to model the dynamics of a vibrant digital art community, Behance, consisting of tens of millions of interactions (clicks and `appreciates') of users toward digital art. Methodologically, our main contributions are to model (a) rich content, especially in terms of its visual appearance; (b) temporal dynamics, in terms of how users prefer `visually consistent' content within and across sessions; and (c) social dynamics, in terms of how users exhibit preferences both towards certain art styles, as well as the artists themselves.

cs.IR↗

arXiv2016

Sherlock: Sparse Hierarchical Embeddings for Visually-aware One-class Collaborative Filtering

Building successful recommender systems requires uncovering the underlying dimensions that describe the properties of items as well as users' preferences toward them. In domains like clothing recommendation, explaining users' preferences requires modeling the visual appearance of the items in question. This makes recommendation especially challenging, due to both the complexity and subtlety of people's 'visual preferences,' as well as the scale and dimensionality of the data and features involved. Ultimately, a successful model should be capable of capturing considerable variance across different categories and styles, while still modeling the commonalities explained by `global' structures in order to combat the sparsity (e.g. cold-start), variability, and scale of real-world datasets. Here, we address these challenges by building such structures to model the visual dimensions across different product categories. With a novel hierarchical embedding architecture, our method accounts for both high-level (colorfulness, darkness, etc.) and subtle (e.g. casualness) visual characteristics simultaneously.

cs.IR↗

arXiv2016

Generative Concatenative Nets Jointly Learn to Write and Classify Reviews

A recommender system's basic task is to estimate how users will respond to unseen items. This is typically modeled in terms of how a user might rate a product, but here we aim to extend such approaches to model how a user would write about the product. To do so, we design a character-level Recurrent Neural Network (RNN) that generates personalized product reviews. The network convincingly learns styles and opinions of nearly 1000 distinct authors, using a large corpus of reviews from BeerAdvocate.com. It also tailors reviews to describe specific items, categories, and star ratings. Using a simple input replication strategy, the Generative Concatenative Network (GCN) preserves the signal of static auxiliary inputs across wide sequence intervals. Without any additional training, the generative model can classify reviews, identifying the author of the review, the product category, and the sentiment (rating), with remarkable accuracy. Our evaluation shows the GCN captures complex dynamics in text, such as the effect of negation, misspellings, slang, and large vocabularies gracefully absent any machinery explicitly dedicated to the purpose.

cs.CL↗

arXiv2016

Fashionista: A Fashion-aware Graphical System for Exploring Visually Similar Items

To build a fashion recommendation system, we need to help users retrieve fashionable items that are visually similar to a particular query, for reasons ranging from searching alternatives (i.e., substitutes), to generating stylish outfits that are visually consistent, among other applications. In domains like clothing and accessories, such considerations are particularly paramount as the visual appearance of items is a critical feature that guides users' decisions. However, existing systems like Amazon and eBay still rely mainly on keyword search and recommending loosely consistent items (e.g. based on co-purchasing or browsing data), without an interface that makes use of visual information to serve the above needs. In this paper, we attempt to fill this gap by designing and implementing an image-based query system, called Fashionista, which provides a graphical interface to help users efficiently explore those items that are not only visually similar to a given query, but which are also fashionable, as determined by visually-aware recommendation approaches. Methodologically, Fashionista learns a low-dimensional visual space as well as the evolution of fashion trends from large corpora of binary feedback data such as purchase histories of Women's Clothing & Accessories from Amazon, which we use for this demonstration.

cs.IR↗

arXiv2016

Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering

Building a successful recommender system depends on understanding both the dimensions of people's preferences as well as their dynamics. In certain domains, such as fashion, modeling such preferences can be incredibly difficult, due to the need to simultaneously model the visual appearance of products as well as their evolution over time. The subtle semantics and non-linear dynamics of fashion evolution raise unique challenges especially considering the sparsity and large scale of the underlying datasets. In this paper we build novel models for the One-Class Collaborative Filtering setting, where our goal is to estimate users' fashion-aware personalized ranking functions based on their past feedback. To uncover the complex and evolving visual factors that people consider when evaluating products, our method combines high-level visual features extracted from a deep convolutional neural network, users' past feedback, as well as evolving trends within the community. Experimentally we evaluate our method on two large real-world datasets from Amazon.com, where we show it to outperform state-of-the-art personalized ranking measures, and also use it to visualize the high-level fashion trends across the 11-year span of our dataset.

cs.AI↗

arXiv2015

Addressing Complex and Subjective Product-Related Queries with Customer Reviews

Online reviews are often our first port of call when considering products and purchases online. When evaluating a potential purchase, we may have a specific query in mind, e.g. `will this baby seat fit in the overhead compartment of a 747?' or `will I like this album if I liked Taylor Swift's 1989?'. To answer such questions we must either wade through huge volumes of consumer reviews hoping to find one that is relevant, or otherwise pose our question directly to the community via a Q/A system. In this paper we hope to fuse these two paradigms: given a large volume of previously answered queries about products, we hope to automatically learn whether a review of a product is relevant to a given query. We formulate this as a machine learning problem using a mixture-of-experts-type framework---here each review is an `expert' that gets to vote on the response to a particular query; simultaneously we learn a relevance function such that `relevant' reviews are those that vote correctly. At test time this learned relevance function allows us to surface reviews that are relevant to new queries on-demand. We evaluate our system, Moqa, on a novel corpus of 1.4 million questions (and answers) and 13 million reviews. We show quantitatively that it is effective at addressing both binary and open-ended queries, and qualitatively that it surfaces reviews that human evaluators consider to be relevant.

cs.IR↗

arXiv2015

VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback

Modern recommender systems model people and items by discovering or `teasing apart' the underlying dimensions that encode the properties of items and users' preferences toward them. Critically, such dimensions are uncovered based on user feedback, often in implicit form (such as purchase histories, browsing logs, etc.); in addition, some recommender systems make use of side information, such as product attributes, temporal information, or review text. However one important feature that is typically ignored by existing personalized recommendation and ranking methods is the visual appearance of the items being considered. In this paper we propose a scalable factorization model to incorporate visual signals into predictors of people's opinions, which we apply to a selection of large, real-world datasets. We make use of visual features extracted from product images using (pre-trained) deep networks, on top of which we learn an additional layer that uncovers the visual dimensions that best explain the variation in people's feedback. This not only leads to significantly more accurate personalized ranking methods, but also helps to alleviate cold start issues, and qualitatively to analyze the visual dimensions that influence people's opinions.

cs.IR↗

arXiv2015

Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences

With the rapid proliferation of smart mobile devices, users now take millions of photos every day. These include large numbers of clothing and accessory images. We would like to answer questions like `What outfit goes well with this pair of shoes?' To answer these types of questions, one has to go beyond learning visual similarity and learn a visual notion of compatibility across categories. In this paper, we propose a novel learning framework to help answer these types of questions. The main idea of this framework is to learn a feature transformation from images of items into a latent space that expresses compatibility. For the feature transformation, we use a Siamese Convolutional Neural Network (CNN) architecture, where training examples are pairs of items that are either compatible or incompatible. We model compatibility based on co-occurrence in large-scale user behavior data; in particular co-purchase data from Amazon.com. To learn cross-category fit, we introduce a strategic method to sample training data, where pairs of items are heterogeneous dyads, i.e., the two elements of a pair belong to different high-level categories. While this approach is applicable to a wide variety of settings, we focus on the representative problem of learning compatible clothing style. Our results indicate that the proposed framework is capable of learning semantic information about visual style and is able to generate outfits of clothes, with items from different categories, that go well together.

cs.CV↗

arXiv2015

Inferring Networks of Substitutable and Complementary Products

In a modern recommender system, it is important to understand how products relate to each other. For example, while a user is looking for mobile phones, it might make sense to recommend other phones, but once they buy a phone, we might instead want to recommend batteries, cases, or chargers. These two types of recommendations are referred to as substitutes and complements: substitutes are products that can be purchased instead of each other, while complements are products that can be purchased in addition to each other. Here we develop a method to infer networks of substitutable and complementary products. We formulate this as a supervised link prediction task, where we learn the semantics of substitutes and complements from data associated with products. The primary source of data we use is the text of product reviews, though our method also makes use of features such as ratings, specifications, prices, and brands. Methodologically, we build topic models that are trained to automatically discover topics from text that are successful at predicting and explaining such relationships. Experimentally, we evaluate our system on the Amazon product catalog, a large dataset consisting of 9 million products, 237 million links, and 144 million reviews.

cs.SI↗

arXiv2015

Image-based Recommendations on Styles and Substitutes

Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance. Some pairs of objects might be seen as being alternatives to each other (such as two pairs of jeans), while others may be seen as being complementary (such as a pair of jeans and a matching shirt). This information guides many of the choices that people make, from buying clothes to their interactions with each other. We seek here to model this human sense of the relationships between objects based on their appearance. Our approach is not based on fine-grained modeling of user annotations but rather on capturing the largest dataset possible and developing a scalable method for uncovering human notions of the visual relationships within. We cast this as a network inference problem defined on graphs of related images, and provide a large-scale dataset for the training and evaluation of the same. The system we develop is capable of recommending which clothes and accessories will go well together (and which will not), amongst a host of other applications.

cs.CV↗

arXiv2014

Detecting Cohesive and 2-mode Communities in Directed and Undirected Networks

Networks are a general language for representing relational information among objects. An effective way to model, reason about, and summarize networks, is to discover sets of nodes with common connectivity patterns. Such sets are commonly referred to as network communities. Research on network community detection has predominantly focused on identifying communities of densely connected nodes in undirected networks. In this paper we develop a novel overlapping community detection method that scales to networks of millions of nodes and edges and advances research along two dimensions: the connectivity structure of communities, and the use of edge directedness for community detection. First, we extend traditional definitions of network communities by building on the observation that nodes can be densely interlinked in two different ways: In cohesive communities nodes link to each other, while in 2-mode communities nodes link in a bipartite fashion, where links predominate between the two partitions rather than inside them. Our method successfully detects both 2-mode as well as cohesive communities, that may also overlap or be hierarchically nested. Second, while most existing community detection methods treat directed edges as though they were undirected, our method accounts for edge directions and is able to identify novel and meaningful community structures in both directed and undirected networks, using data from social, biological, and ecological domains.

cs.SI↗

arXiv2014

Community Detection in Networks with Node Attributes

Community detection algorithms are fundamental tools that allow us to uncover organizational principles in networks. When detecting communities, there are two possible sources of information one can use: the network structure, and the features and attributes of nodes. Even though communities form around nodes that have common edges and common attributes, typically, algorithms have only focused on one of these two data modalities: community detection algorithms traditionally focus only on the network structure, while clustering algorithms mostly consider only node attributes. In this paper, we develop Communities from Edge Structure and Node Attributes (CESNA), an accurate and scalable algorithm for detecting overlapping communities in networks with node attributes. CESNA statistically models the interaction between the network structure and the node attributes, which leads to more accurate community detection as well as improved robustness in the presence of noise in the network structure. CESNA has a linear runtime in the network size and is able to process networks an order of magnitude larger than comparable approaches. Last, CESNA also helps with the interpretation of detected communities by finding relevant node attributes for each community.

cs.SI↗

arXiv2013

From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews

Recommending products to consumers means not only understanding their tastes, but also understanding their level of experience. For example, it would be a mistake to recommend the iconic film Seven Samurai simply because a user enjoys other action movies; rather, we might conclude that they will eventually enjoy it -- once they are ready. The same is true for beers, wines, gourmet foods -- or any products where users have acquired tastes: the `best' products may not be the most `accessible'. Thus our goal in this paper is to recommend products that a user will enjoy now, while acknowledging that their tastes may have changed over time, and may change again in the future. We model how tastes change due to the very act of consuming more products -- in other words, as users become more experienced. We develop a latent factor recommendation system that explicitly accounts for each user's level of experience. We find that such a model not only leads to better recommendations, but also allows us to study the role of user experience and expertise on a novel dataset of fifteen million beer, wine, food, and movie reviews.

cs.SI↗