Abstract-In this paper, we propose a scalable and highly efficient index structure for the reachability problem over graphs. We build on the well-known node interval labeling scheme where the set of vertices reachable from a particular node is compactly encoded as a collection of node identifier ranges. We impose an explicit bound on the size of the index and flexibly assign approximate reachability ranges to nodes of the graph such that the number of index probes to answer a query is minimized. The resulting tunable index structure generates a better range labeling if the space budget is increased, thus providing a direct control over the trade off between index size and the query processing performance. By using a fast recursive querying method in conjunction with our index structure, we show that, in practice, reachability queries can be answered in the order of microseconds on an off-the-shelf computer -even for the case of massive-scale real world graphs. Our claims are supported by an extensive set of experimental results using a multitude of benchmark and real-world web-scale graph datasets.
Wikipedia entity pages are a valuable source of information for direct consumption and for knowledge-base construction, update and maintenance. Facts in these entity pages are typically supported by references. Recent studies show that as much as 20\% of the references are from online news sources. However, many entity pages are incomplete even if relevant information is already available in existing news articles. Even for the already present references, there is often a delay between the news article publication time and the reference time. In this work, we therefore look at Wikipedia through the lens of news and propose a novel news-article suggestion task to improve news coverage in Wikipedia, and reduce the lag of newsworthy references. Our work finds direct application, as a precursor, to Wikipedia page generation and knowledge-base acceleration tasks that rely on relevant and high quality input sources. We propose a two-stage supervised approach for suggesting news articles to entity pages for a given state of Wikipedia. First, we suggest news articles to Wikipedia entities (article-entity placement) relying on a rich set of features which take into account the \emph{salience} and \emph{relative authority} of entities, and the \emph{novelty} of news articles to entity pages. Second, we determine the exact section in the entity page for the input article (article-section placement) guided by class-based section templates. We perform an extensive evaluation of our approach based on ground-truth data that is extracted from external references in Wikipedia. We achieve a high precision value of up to 93\% in the \emph{article-entity} suggestion stage and upto 84\% for the \emph{article-section placement}. Finally, we compare our approach against competitive baselines and show significant improvements
No abstract
There has been significant progress in unsupervised network representation learning (UNRL) approaches over graphs recently with flexible random-walk approaches, new optimization objectives and deep architectures. However, there is no common ground for systematic comparison of embeddings to understand their behavior for different graphs and tasks. We argue that most of the UNRL approaches either model and exploit neighborhood or what we call context information of a node. These methods largely differ in their definitions and exploitation of context. Consequently, we propose a framework that casts a variety of approaches -random walk based, matrix factorization and deep learning based -into a unified context-based optimization function. We systematically group the methods based on their similarities and differences. We study their differences which we later use to explain their performance differences (on downstream tasks).We conduct a large-scale empirical study considering 9 popular and recent UNRL techniques and 11 real-world datasets with varying structural properties and two common tasks -node classification and link prediction. We find that for non-attributed graphs there is no single method that is a clear winner and that the choice of a suitable method is dictated by certain properties of the embedding methods, task and structural properties of the underlying graph. In addition we also report the common pitfalls in evaluation of UNRL methods and come up with suggestions for experimental design and interpretation of results. Comprehensive Experimental Evaluation.In our evaluation of UNRL methods we investigate the conceptual differences between the embedding approaches that result in performance differences on downstream tasks. First, using graphs with diverse structural characteristics we argue about the utility of several approaches. We carefully chose 11 large arXiv:1903.07902v5 [cs.LG]
Wikipedia tables represent an important resource, where information is organized w.r.t table schemas consisting of columns. In turn each column, may contain instance values that point to other Wikipedia articles or primitive values (e.g. numbers, strings etc.).In this work, we focus on the problem of interlinking Wikipedia tables for two types of table relations: equivalent and subPartOf. Through such relations, we can further harness semantically related information by accessing related tables or facts therein. Determining the relation type of a table pair is not trivial, as it is dependent on the schemas, the values therein, and the semantic overlap of the cell values in the corresponding tables.We propose TableNet, an approach that constructs a knowledge graph of interlinked tables with subPartOf and equivalent relations. TableNet consists of two main steps: (i) for any source table we provide an efficient algorithm to find all candidate related tables with high coverage, and (ii) a neural based approach, which takes into account the table schemas, and the corresponding table data, we determine with high accuracy the table relation for a table pair. We perform an extensive experimental evaluation on the entire Wikipedia with more than 3.2 million tables. We show that with more than 88% we retain relevant candidate tables pairs for alignment. Consequentially, with an accuracy of 90% we are able to align tables with subPartOf or equivalent relations. Comparisons with existing competitors show that TableNet has superior performance in terms of coverage and alignment accuracy. ACM Reference Format:
Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional blackboxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models which correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is therefore crucial to understand how and which models conform to human understanding of tasks. In this paper we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.
An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph. In many cases citations are either outdated or missing altogether. In this work we address the problem of finding and updating news citations for statements in entity pages. We propose a two-stage supervised approach for this problem. In the first step, we construct a classifier to find out whether statements need a news citation or other kinds of citations (web, book, journal, etc.). In the second step, we develop a news citation algorithm for Wikipedia statements, which recommends appropriate citations from a given news collection. Apart from IR techniques that use the statement to query the news collection, we also formalize three properties of an appropriate citation, namely: (i) the citation should entail the Wikipedia statement, (ii) the statement should be central to the citation, and (iii) the citation should be from an authoritative source. We perform an extensive evaluation of both steps, using 20 million articles from a real-world news collection. Our results are quite promising, and show that we can perform this task with high precision and at scale
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.