Explore the vast range of titles available.

Data-driven phenotype analyses on Electronic Health Record (EHR) data have recently drawn benefits across many areas of clinical practice, uncovering new links in the medical sciences that can potentially affect the well-being of millions of patients. In this paper, EHR data is used to discover novel relationships between diseases by studying their comorbidities (co-occurrences in patients). A novel embedding model is designed to extract knowledge from disease comorbidities by learning from a large-scale EHR database comprising more than 35 million inpatient cases spanning nearly a decade, revealing significant improvements on disease phenotyping over current computational approaches. In addition, the use of the proposed methodology is extended to discover novel disease-gene associations by including valuable domain knowledge from genome-wide association studies. To evaluate our approach, its effectiveness is compared against a held-out set where, again, it revealed very compelling results. For selected diseases, we further identify candidate gene lists for which disease-gene associations were not studied previously. Thus, our approach provides biomedical researchers with new tools to filter genes of interest, thus, reducing costly lab studies.

This paper studies supervised clustering in the context of label ranking data. The goal is to partition the feature space into K clusters, such that they are compact in both the feature and label ranking space. This type of clustering has many potential applications. For example, in target marketing we might want to come up with K different offers or marketing strategies for our target audience. Thus, we aim at clustering the customers’ feature space into K clusters by leveraging the revealed or stated, potentially incomplete customer preferences over products, such that the preferences of customers within one cluster are more similar to each other than to those of customers in other clusters. We establish several baseline algorithms and propose two principled algorithms for supervised clustering. In the first baseline, the clusters are created in an unsupervised manner, followed by assigning a representative label ranking to each cluster. In the second baseline, the label ranking space is clustered first, followed by partitioning the feature space based on the central rankings. In the third baseline, clustering is applied on a new feature space consisting of both features and label rankings, followed by mapping back to the original feature and ranking space. The RankTree principled approach is based on a Ranking Tree algorithm previously proposed for label ranking prediction. Our modification starts with K random label rankings and iteratively splits the feature space to minimize the ranking loss, followed by re-calculation of the K rankings based on cluster assignments. The MM-PL approach is a multi-prototype supervised clustering algorithm based on the Plackett-Luce (PL) probabilistic ranking model. It represents each cluster with a union of Voronoi cells that are defined by a set of prototypes, and assign each cluster with a set of PL label scores that determine the cluster central ranking. Cluster membership and ranking prediction for a new instance are determined by cluster membership of its nearest prototype. The unknown cluster PL parameters and prototype positions are learned by minimizing the ranking loss, based on two variants of the expectation-maximization algorithm. Evaluation of the proposed algorithms was conducted on synthetic and real-life label ranking data by considering several measures of cluster goodness: (1) cluster compactness in feature space, (2) cluster compactness in label ranking space and (3) label ranking prediction loss. Experimental results demonstrate that the proposed MM-PL and RankTree models are superior to the baseline models. Further, MM-PL is has shown to be much better than other algorithms at handling situations with significant fraction of missing label preferences.

Timely Fault Detection and Diagnosis in complex manufacturing systems is critical to ensure safe and effective operation of plant equipment. Process fault is defined as a deviation from normal process behavior, defined within the limits of safe production. The quantifiable objectives of Fault Detection include achieving low detection delay time, low false positive rate, and high detection rate. Once a fault has been detected pinpointing the type of fault is needed for purposes of fault mitigation and returning to normal process operation. This is known as Fault Diagnosis. Data-driven Fault Detection and Diagnosis methods emerged as an attractive alternative to traditional mathematical model-based methods, especially for complex systems due to difficulty in describing the underlying process. A distinct feature of data-driven methods is that no a priori information about the process is necessary. Instead, it is assumed that historical data, containing process features measured in regular time intervals (e.g., power plant sensor measurements), are available for development of fault detection/diagnosis model through generalization of data. The goal of my research was to address the shortcomings of the existing data-driven methods and contribute to solving open problems, such as: 1) decentralized fault detection and diagnosis; 2) fault detection in the cold start setting; 3) optimizing the detection delay and dealing with noisy data annotations. 4) developing models that can adapt to concept changes in power plant dynamics. For small-scale sensor networks, it is reasonable to assume that all measurements are available at a central location (sink) where fault predictions are made. This is known as a centralized fault detection approach. For large-scale networks, decentralized approach is often used, where network is decomposed into potentially overlapping blocks and each block provides local decisions that are fused at the sink. The appealing properties of the decentralized approach include fault tolerance, scalability, and reusability. When one or more blocks go offline due to maintenance of their sensors, the predictions can still be made using the remaining blocks. In addition, when the physical facility is reconfigured, either by changing its components or sensors, it can be easier to modify part of the decentralized system impacted by the changes than to overhaul the whole centralized system. The scalability comes from reduced costs of system setup, update, communication, and decision making. Main challenges in decentralized monitoring include process decomposition and decision fusion. We proposed a decentralized model where the sensors are partitioned into small, potentially overlapping, blocks based on the Sparse Principal Component Analysis (PCA) algorithm, which preserves strong correlations among sensors, followed by training local models at each block, and fusion of decisions based on the proposed Maximum Entropy algorithm. Moreover, we introduced a novel framework for adding constraints to the Sparse PCA problem. The constraints limit the set of possible solutions by imposing additional goals to be reached trough optimization along with the existing Sparse PCA goals. The experimental results on benchmark fault detection data show that Sparse PCA can utilize prior knowledge, which is not directly available in data, in order to produce desirable network partitions, with a pre-defined limit on communication cost and/or robustness.

Web search has become an inevitable part of everyday life. Improving and monetizing web search has been a focus of major Internet players. Understanding the context of web search query is an important aspect of this task as it represents unobserved facts that add meaning to an otherwise incomplete query.The context of a query consists of user's location, local time, search history, behavioral segments, installed apps on their phone and so on. Queries that either explicitly use location context (eg: \"best hotels in New York City\") or implicitly refer to the user's physical location (e.g. \"coffee shops near me\") are becoming increasingly common on mobile devices. Understanding and representing the user's interest location and/or physical location is essential for providing a relevant user experience. In this study, we developed a simple and powerful neural embedding based framework to represent a user's query and their location in a single low-dimensional space. We show that this representation is able to capture the subtle interactions between the user's query intent and query/physical location, while improving the ad ranking and query-ad relevance scores over other location-unaware approaches and location-aware approaches.

Airbnb is a leader in offering travel accommodations. Airbnb has historically relied on structured data to understand, rank, and recommend listings to guests due to the limited capabilities and associated complexity arising from extracting meaningful information from text and images. With the rise of representation learning, leveraging rich information from text and photos has become easier. A popular approach has been to create embeddings for text documents and images to enable use cases of computing similarities between listings or using embeddings as features in an ML model. However, an Airbnb listing has diverse unstructured data: multiple images, various unstructured text documents such as title, description, and reviews, making this approach challenging. Specifically, it is a non-trivial task to combine multiple embeddings of different pieces of information to reach a single representation. This paper proposes BiListing, for Bimodal Listing, an approach to align text and photos of a listing by leveraging large-language models and pretrained language-image models. The BiListing approach has several favorable characteristics: capturing unstructured data into a single embedding vector per listing and modality, enabling zero-shot capability to search inventory efficiently in user-friendly semantics, overcoming the cold start problem, and enabling listing-to-listing search along a single modality, or both. We conducted offline and online tests to leverage the BiListing embeddings in the Airbnb search ranking model, and successfully deployed it in production, achieved 0.425% of NDCB gain, and drove tens of millions in incremental revenue.

Correctly pricing products or services in an online marketplace presents a challenging problem and one of the critical factors for the success of the business. When users are looking to buy an item they typically search for it. Query relevance models are used at this stage to retrieve and rank the items on the search page from most relevant to least relevant. The presented items are naturally \"competing\" against each other for user purchases. We provide a practical two-stage model to price this set of retrieved items for which distributions of their values are learned. The initial output of the pricing strategy is a price vector for the top displayed items in one search event. We later aggregate these results over searches to provide the supplier with the optimal price for each item. We applied our solution to large-scale search data obtained from Airbnb Experiences marketplace. Offline evaluation results show that our strategy improves upon baseline pricing strategies on key metrics by at least +20% in terms of booking regret and +55% in terms of revenue potential.

Email classification is still a mostly manual task. Consequently, most Web mail users never define a single folder. Recently however, automatic classification offering the same categories to all users has started to appear in some Web mail clients, such as AOL or Gmail. We adopt this approach, rather than previous (unsuccessful) personalized approaches because of the change in the nature of consumer email traffic, which is now dominated by (non-spam) machine-generated email. We propose here a novel approach for (1) automatically distinguishing between personal and machine-generated email and (2) classifying messages into latent categories, without requiring users to have defined any folder. We report how we have discovered that a set of 6 \"latent\" categories (one for human- and the others for machine-generated messages) can explain a significant portion of email traffic. We describe in details the steps involved in building a Web-scale email categorization system, from the collection of ground-truth labels, the selection of features to the training of models. Experimental evaluation was performed on more than 500 billion messages received during a period of six months by users of Yahoo mail service, who elected to be part of such research studies. Our system achieved precision and recall rates close to 90% and the latent categories we discovered were shown to cover 70% of both email traffic and email search queries. We believe that these results pave the way for a change of approach in the Web mail industry, and could support the invention of new large-scale email discovery paradigms that had not been possible before.

With mobile shopping surging in popularity, people are spending ever more money on digital purchases through their mobile devices and phones. However, few large-scale studies of mobile shopping exist. In this paper we analyze a large data set consisting of more than 776M digital purchases made on Apple mobile devices that include songs, apps, and in-app purchases. We find that 61% of all the spending is on in-app purchases and that the top 1% of users are responsible for 59% of all the spending. These big spenders are more likely to be male and older, and less likely to be from the US. We study how they adopt and abandon individual app, and find that, after an initial phase of increased daily spending, users gradually lose interest: the delay between their purchases increases and the spending decreases with a sharp drop toward the end. Finally, we model the in-app purchasing behavior in multiple steps: 1) we model the time between purchases; 2) we train a classifier to predict whether the user will make a purchase from a new app or continue purchasing from the existing app; and 3) based on the outcome of the previous step, we attempt to predict the exact app, new or existing, from which the next purchase will come. The results yield new insights into spending habits in the mobile digital marketplace.

We consider the problem of learning distributed representations for documents in data streams. The documents are represented as low-dimensional vectors and are jointly learned with distributed vector representations of word tokens using a hierarchical framework with two embedded neural language models. In particular, we exploit the context of documents in streams and use one of the language models to model the document sequences, and the other to model word sequences within them. The models learn continuous vector representations for both word tokens and documents such that semantically similar documents and words are close in a common vector space. We discuss extensions to our model, which can be applied to personalized recommendation and social relationship mining by adding further user layers to the hierarchy, thus learning user-specific vectors to represent individual preferences. We validated the learned representations on a public movie rating data set from MovieLens, as well as on a large-scale Yahoo News data comprising three months of user activity logs collected on Yahoo servers. The results indicate that the proposed model can learn useful representations of both documents and word tokens, outperforming the current state-of-the-art by a large margin.