We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.

Semi-Supervised Classification with Graph Convolutional Networks

We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily exploited by statistical models. DeepWalk generalizes recent advancements in language modeling and unsupervised feature learning (or deep learning) from sequences of words to graphs.DeepWalk uses local information obtained from truncated random walks to learn latent representations by treating walks as the equivalent of sentences. We demonstrate DeepWalk's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, Flickr, and YouTube. Our results show that DeepWalk outperforms challenging baselines which are allowed a global view of the network, especially in the presence of missing information. DeepWalk's representations can provide F1 scores up to 10% higher than competing methods when labeled data is sparse. In some experiments, DeepWalk's representations are able to outperform all baseline methods while using 60% less training data.DeepWalk is also scalable. It is an online learning algorithm which builds useful incremental results, and is trivially parallelizable. These qualities make it suitable for a broad class of real world applications such as network classification, and anomaly detection.

/pdf/deepwalk-online-learning-of-social-representations-4qo03z5zdj.pdf

DeepWalk: online learning of social representations

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial–temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

/pdf/a-comprehensive-survey-on-graph-neural-networks-4lw9i4v183.pdf

A Comprehensive Survey on Graph Neural Networks

Sentiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, Web mining, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance to business and society as a whole. The growing importance of sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. For the first time in human history, we now have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis systems are being applied in almost every business and social domain because opinions are central to almost all human activities and are key influencers of our behaviors. Our beliefs and perceptions of reality, and the choices we make, are largely conditioned on how others see and evaluate the world. For this reason, when we need to make a decision we often seek out the opinions of others. This is true not only for individuals but also for organizations. This book is a comprehensive introductory and survey text. It covers all important topics and the latest developments in the field with over 400 references. It is suitable for students, researchers and practitioners who are interested in social media analysis in general and sentiment analysis in particular. Lecturers can readily use it in class for courses on natural language processing, social media analysis, text mining, and data mining. Lecture slides are also available online.

/pdf/sentiment-analysis-and-opinion-mining-8314pykwrf.pdf

Sentiment Analysis and Opinion Mining

25. Multiple Imputation for Nonresponse in Surveys. By D. B. Rubin. ISBN 0 471 08705 X. Wiley, Chichester, 1987. 258 pp. £30.25.

Multiple Imputation for Nonresponse in Surveys

Many real-world applications produce networked data such as the world-wide web (hypertext documents connected via hyperlinks), social networks (for example, people connected by friendship links), communication networks (computers connected via communication links) and biological networks (for example, protein interaction networks). A recent focus in machine learning research has been to extend traditional machine learning classification techniques to classify nodes in such networks. In this article, we provide a brief introduction to this area of research and how it has progressed during the past decade. We introduce four of the most widely used inference algorithms for classifying networked data and empirically compare them on both synthetic and real-world data.

/pdf/collective-classification-in-network-data-ao4inwtwyv.pdf

Collective Classification in Network Data

Recommender systems have become a popular technique for helping users select desirable books, movies, music and other items. Most research in the area has focused on developing and evaluating algorithms for efficiently producing accurate recommendations. However, the ability to effectively explain its recommendations to users is another important aspect of a recommender system. The only previous investigation of methods for explaining recommendations showed that certain styles of explanations were effective at convincing users to adopt recommendations (i.e. promotion) but failed to show that explanations actually helped users make more accurate decisions (i.e. satisfaction). We present two new methods for explaining recommendations of contentbased and/or collaborative systems and experimentally show that they actually improve user’s estimation of item quality.

/pdf/explaining-recommendations-satisfaction-vs-promotion-2d2ihbomvq.pdf

Explaining Recommendations: Satisfaction vs. Promotion

We introduce a novel active learning algorithm for classification of network data. In this setting, training instances are connected by a set of links to form a network, the labels of linked nodes are correlated, and the goal is to exploit these dependencies and accurately label the nodes. This problem arises in many domains, including social and biological network analysis and document classification, and there has been much recent interest in methods that collectively classify the nodes in the network. While in many cases labeled examples are expensive, often network information is available. We show how an active learning algorithm can take advantage of network structure. Our algorithm effectively exploits the links between instances and the interaction between the local and collective aspects of a classifier to improve the accuracy of learning from fewer labeled examples. We experiment with two real-world benchmark collective classification domains, and show that we are able to achieve extremely accurate results even when only a small fraction of the data is labeled.

/pdf/active-learning-for-networked-data-2d5or71xto.pdf

Active Learning for Networked Data

The problems of object classification (labeling the nodes of a graph) and link prediction (predicting the links in a graph) have been largely studied independently. Commonly, object classification is performed assuming a complete set of known links and link prediction is done assuming a fully observed set of node attributes. In most real world domains, however, attributes and links are often missing or incorrect. Object classification is not provided with all the links relevant to correct classification and link prediction is not provided all the labels needed for accurate link prediction. In this paper, we propose an approach that addresses these two problems by interleaving object classification and link prediction in a collective algorithm. We investigate empirically the conditions under which an integrated approach to object classification and link prediction improves performance, and find that performance improves over a wide range of network types, and algorithm settings.

/pdf/combining-collective-classification-and-link-prediction-4y4hq340ag.pdf

Combining Collective Classification and Link Prediction

Most of the empirical evaluations of active learning approaches in the literature have focused on a single classifier and a single performance measure We present an extensive empirical evaluation of common active learning baselines using two probabilistic classifiers and several performance measures on a number of large datasets In addition to providing important practical advice, our findings highlight the importance of overlooked choices in active learning experiments in the literature For example, one of our findings shows that model selection is as important as devising an active learning approach, and choosing one classifier and one performance measure can often lead to unexpected and unwarranted conclusions Active learning should generally improve the model's capability to distinguish between instances of different classes, but our findings show that the improvements provided by active learning for one performance measure often came at the expense of another measure We present several such results, raise questions, guide users and researchers to better alternatives, caution against unforeseen side effects of active learning, and suggest future research directions

Mustafa Bilgic

Papers

Collective Classification in Network Data

Explaining Recommendations: Satisfaction vs. Promotion

Active Learning for Networked Data

Combining Collective Classification and Link Prediction

Active learning: an empirical study of common baselines