The National Center for Biotechnology Information (NCBI) Taxonomy is extensively used in biomedical and ecological research. Typical demands include computing the lowest common ancestor, determining descendant relationships, and listing the descendants of a node. However, existing tools often suffer from inefficient runtime performance. To address this challenge, our paper introduces a novel indexing method, BIT, designed specifically for tree-like data. BIT first encodes the tree-like structure into a bit-vector using the Polychotomic encoding algorithm, subsequently storing the bit-vector in a bitmap. By employing parallel bit operations, BIT significantly accelerates the speed of typical computational tasks. Experimental results on public datasets demonstrate that BIT outperforms baseline systems in task execution performance.

As data grows exponentially, its diversity also increases, including both structured forms and unstructured forms like audio, images, and videos. Advances in AI have improved our ability to analyze unstructured data, leading to the use of multimodal hybrid queries that blend structured and unstructured data. However, database systems struggle due to the lack of adequate data models for multimodal data and languages for these hybrid queries. This paper extends the property graph model to represent multimodal data and their semantic information, introducing essential functions for hybrid graph queries. A high-level graph query language, CypherPlus, is presented, capable of expressing hybrid queries like “Give me the friends of the friends of Mary, who have blond hair and are younger than 30 years old.” A Neo4j-based implementation and experiments over synthetic and real-world datasets demonstrate the approach’s plausibility.

Dynamic graphs are increasingly being utilized in domain knowledge modeling and large-scale scientific data management. Managing dynamic graph data requires a graph database system that can handle constantly changing volumes and data versions, while maintaining an acceptable query latency related to versioning. To understand how the design of storage structures affects database performance and assist scientific application developers in finding the optimal storage structure for their dynamic graph application scenarios, we have designed an easy-to-use benchmark framework called SciDG. We also conducted a study on the latencies of five fundamental version-related queries for various scientific application scenarios using SciDG. We evaluated the performance of databases based on three distinct storage principles: Sp-DB, Dp-DB, and Tp-DB. The experimental results indicate that SciDG is a valuable tool for assessing the strengths and weaknesses of different storage structures for dynamic graphs in various scenarios. Additionally, it assists scientists in selecting the most suitable dynamic graph database system for their work.

Graph model are increasingly popular among modern applications for its ability to model complex relationships between entities. Users tend to query the data as a graph with graph operations (e.g., graph navigation and exploration). However, a large fraction of the data resides in relational databases or other storage systems. Challenges arise in uniformly querying multiple heterogeneous data sources as a graph. Traditional solutions are limited by time-consuming data integration, expensive development effort, and incomplete query requirements. Thus, we developed Lynx, a general graph query framework, to simplify querying graph data by converting complex statements into basic graph operations. Instead of connecting directly to the data sources, Lynx retrieves data through user-implemented interfaces for those graph operations. We demonstrate Lynx's capabilities through real-world scenarios, showcasing Lynx's ability to process graph queries on multiple heterogeneous data sources and also to be used as a generic graph query engine development framework.

Large-scale multi-label text classification (LMTC) aims to associate a document with its relevant labels from a large candidate set. Most existing LMTC approaches rely on massive human-annotated training data, which are often costly to obtain and suffer from a long-tailed label distribution (i.e., many labels occur only a few times in the training set). In this paper, we study LMTC under the zero-shot setting, which does not require any annotated documents with labels and only relies on label surface names and descriptions. To train a classifier that calculates the similarity score between a document and a label, we propose a novel metadata-induced contrastive learning (MICoL) method. Different from previous text-based contrastive learning techniques, MICoL exploits document metadata (e.g., authors, venues, and references of research papers), which are widely available on the Web, to derive similar document–document pairs. Experimental results on two large-scale datasets show that: (1) MICoL significantly outperforms strong zero-shot text classification and contrastive learning baselines; (2) MICoL is on par with the state-of-the-art supervised metadata-aware LMTC method trained on 10K–200K labeled documents; and (3) MICoL tends to predict more infrequent labels than supervised methods, thus alleviates the deteriorated performance on long-tailed labels.

Information overload is a prevalent challenge in many high-value domains. A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months. In general, biomedical literature expands by two papers every minute, totalling over a million new papers every year. Search in the biomedical realm, and many other vertical domains is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. We propose a general approach for vertical search based on domain-specific pretraining and present a case study for the biomedical domain. Despite being substantially simpler and not using any relevance labels for training or development, our method performs comparably or better than the best systems in the official TREC-COVID evaluation, a COVID-related biomedical search competition. Using distributed computing in modern cloud infrastructure, our system can scale to tens of millions of articles on PubMed and has been deployed as Microsoft Biomedical Search, a new search experience for biomedical literature: https://aka.ms/biomedsearch.

Multi-label text classification refers to the problem of assigning each given document its most relevant labels from a label set. Commonly, the metadata of the given documents and the hierarchy of the labels are available in real-world applications. However, most existing studies focus on only modeling the text information, with a few attempts to utilize either metadata or hierarchy signals, but not both of them. In this paper, we bridge the gap by formalizing the problem of metadata-aware text classification in a large label hierarchy (e.g., with tens of thousands of labels). To address this problem, we present the MATCH1 solution—an end-to-end framework that leverages both metadata and hierarchy information. To incorporate metadata, we pre-train the embeddings of text and metadata in the same space and also leverage the fully-connected attentions to capture the interrelations between them. To leverage the label hierarchy, we propose different ways to regularize the parameters and output probability of each child label by its parents. Extensive experiments on two massive text datasets with large-scale label hierarchies demonstrate the effectiveness of MATCH over the state-of-the-art deep learning baselines.

Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications. For example, online retailers (e.g., Amazon and eBay) use taxonomies for product recommendation, and web search engines (e.g., Google and Bing) leverage taxonomies to enhance query understanding. Enormous efforts have been made on constructing taxonomies either manually or semi-automatically. However, with the fast-growing volume of web content, existing taxonomies will become outdated and fail to capture emerging knowledge. Therefore, in many applications, dynamic expansions of an existing taxonomy are in great demand. In this paper, we study how to expand an existing taxonomy by adding a set of new concepts. We propose a novel self-supervised framework, named TaxoExpan, which automatically generates a set of ⟨query concept, anchor concept⟩ pairs from the existing taxonomy as training data. Using such self-supervision data, TaxoExpan learns a model to predict whether a query concept is the direct hyponym of an anchor concept. We develop two innovative techniques in TaxoExpan: (1) a position-enhanced graph neural network that encodes the local structure of an anchor concept in the existing taxonomy, and (2) a noise-robust training objective that enables the learned model to be insensitive to the label noise in the self-supervision data. Extensive experiments on three large-scale datasets from different domains demonstrate both the effectiveness and the efficiency of TaxoExpan for taxonomy expansion.

We present the design and methodology for the large scale hybrid paper recommender system used by Microsoft Academic. The system provides recommendations for approximately 160 million English research papers and patents. Our approach handles incomplete citation information while also alleviating the cold-start problem that often affects other recommender systems. We use the Microsoft Academic Graph (MAG), titles, and available abstracts of research papers to build a recommendation list for all documents, thereby combining co-citation and content based approaches. Tuning system parameters also allows for blending and prioritization of each approach which, in turn, allows us to balance paper novelty versus authority in recommendation results. We evaluate the generated recommendations via a user study of 40 participants, with over 2400 recommendation pairs graded and discuss the quality of the results using [email protected] and nDCG scores. We see that there is a strong correlation between participant scores and the similarity rankings produced by our system but that additional focus needs to be put towards improving recommender precision, particularly for content based recommendations. The results of the user survey and associated analysis scripts are made available via GitHub and the recommendations produced by our system are available as part of the MAG on Azure to facilitate further research and light up novel research paper recommendation applications.

Progress in science has advanced the development of human society across history, with dramatic revolutions shaped by information theory, genetic cloning, and artificial intelligence, among the many scientific achievements produced in the 20th century. However, the way that science advances itself is much less well-understood. In this work, we study the evolution of scientific development over the past century by presenting an anatomy of 89 million digitalized papers published between 1900 and 2015. We find that science has benefited from the shift from individual work to collaborative effort, with over 90% of the world-leading innovations generated by collaborations in this century, nearly four times higher than they were in the 1900s. We discover that rather than the frequent myopic- and self-referencing that was common in the early 20th century, modern scientists instead tend to look for literature further back and farther around. Finally, we also observe the globalization of scientific development from 1900 to 2015, including 25-fold and 7-fold increases in international collaborations and citations, respectively, as well as a dramatic decline in the dominant accumulation of citations by the US, the UK, and Germany, from ~95% to ~50% over the same period. Our discoveries are meant to serve as a starter for exploring the visionary ways in which science has developed throughout the past century, generating insight into and an impact upon the current scientific innovations and funding policies.

Many aspects and properties of Recommender Systems have been well studied in the past decade, however, the impact of User Fatigue has been mostly ignored in the literature. User fatigue represents the phenomenon that a user quickly loses the interest on the recommended item if the same item has been presented to this user multiple times before. The direct impact caused by the user fatigue is the dramatic decrease of the Click Through Rate (CTR, i.e., the ratio of clicks to impressions). In this paper, we present a comprehensive study on the research of the user fatigue in online recommender systems. By analyzing user behavioral logs from Bing Now news recommendation, we find that user fatigue is a severe problem that greatly affects the user experience. We also notice that different users engage differently with repeated recommendations. Depending on the previous users' interaction with repeated recommendations, we illustrate that under certain condition the previously seen items should be demoted, while some other times they should be promoted. We demonstrate how statistics about the analysis of the user fatigue can be incorporated into ranking algorithms for personalized recommendations. Our experimental results indicate that significant gains can be achieved by introducing features that reflect users' interaction with previously seen recommendations (up to 15% enhancement on all users and 34% improvement on heavy users).