Bandit algorithms have gained increased attention in recommender systems, as they provide effective and scalable recommendations. These algorithms use reward functions, usually based on a numeric variable such as click-through rates, as the basis for optimization. On a popular music streaming service, a contextual bandit algorithm is used to decide which content to recommend to users, where the reward function is a binarization of a numeric variable that defines success based on a static threshold of user streaming time: 1 if the user streamed for at least 30 seconds and 0 otherwise. We explore alternative methods to provide a more informed reward function, based on the assumptions that streaming time distribution heavily depends on the type of user and the type of content being streamed. To automatically extract user and content groups from streaming data, we employ ”co-clustering”, an unsupervised learning technique to simultaneously extract clusters of rows and columns from a co-occurrence matrix. The streaming distributions within the co-clusters are then used to define rewards specific to each co-cluster. Our proposed co-clustered based reward functions lead to improvement of over 25% in expected stream rate, compared to the standard binarized rewards.
{"title":"Deriving User- and Content-specific Rewards for Contextual Bandits","authors":"Paolo Dragone, Rishabh Mehrotra, M. Lalmas","doi":"10.1145/3308558.3313592","DOIUrl":"https://doi.org/10.1145/3308558.3313592","url":null,"abstract":"Bandit algorithms have gained increased attention in recommender systems, as they provide effective and scalable recommendations. These algorithms use reward functions, usually based on a numeric variable such as click-through rates, as the basis for optimization. On a popular music streaming service, a contextual bandit algorithm is used to decide which content to recommend to users, where the reward function is a binarization of a numeric variable that defines success based on a static threshold of user streaming time: 1 if the user streamed for at least 30 seconds and 0 otherwise. We explore alternative methods to provide a more informed reward function, based on the assumptions that streaming time distribution heavily depends on the type of user and the type of content being streamed. To automatically extract user and content groups from streaming data, we employ ”co-clustering”, an unsupervised learning technique to simultaneously extract clusters of rows and columns from a co-occurrence matrix. The streaming distributions within the co-clusters are then used to define rewards specific to each co-cluster. Our proposed co-clustered based reward functions lead to improvement of over 25% in expected stream rate, compared to the standard binarized rewards.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77590749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Users are usually involved in multiple social networks, without explicit anchor links that reveal the correspondence among different accounts of the same user across networks. Anchor link prediction aims to identify the hidden anchor links, which is a fundamental problem for user profiling, information cascading, and cross-domain recommendation. Although existing methods perform well in the accuracy of anchor link prediction, the pairwise search manners on inferring anchor links suffer from big challenge when being deployed in practical systems. To combat the challenges, in this paper we propose a novel embedding and matching architecture to directly learn binary hash code for each node. Hash codes offer us an efficient index to filter out the candidate node pairs for anchor link prediction. Extensive experiments on synthetic and real world large-scale datasets demonstrate that our proposed method has high time efficiency without loss of competitive prediction accuracy in anchor link prediction.
{"title":"Learning Binary Hash Codes for Fast Anchor Link Retrieval across Networks","authors":"Yongqing Wang, Huawei Shen, Jinhua Gao, Xueqi Cheng","doi":"10.1145/3308558.3313430","DOIUrl":"https://doi.org/10.1145/3308558.3313430","url":null,"abstract":"Users are usually involved in multiple social networks, without explicit anchor links that reveal the correspondence among different accounts of the same user across networks. Anchor link prediction aims to identify the hidden anchor links, which is a fundamental problem for user profiling, information cascading, and cross-domain recommendation. Although existing methods perform well in the accuracy of anchor link prediction, the pairwise search manners on inferring anchor links suffer from big challenge when being deployed in practical systems. To combat the challenges, in this paper we propose a novel embedding and matching architecture to directly learn binary hash code for each node. Hash codes offer us an efficient index to filter out the candidate node pairs for anchor link prediction. Extensive experiments on synthetic and real world large-scale datasets demonstrate that our proposed method has high time efficiency without loss of competitive prediction accuracy in anchor link prediction.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"69 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90390654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yiming Zhang, Yujie Fan, Wei Song, Shifu Hou, Yanfang Ye, X. Li, Liang Zhao, C. Shi, Jiabin Wang, Qi Xiong
Due to its anonymity, there has been a dramatic growth of underground drug markets hosted in the darknet (e.g., Dream Market and Valhalla). To combat drug trafficking (a.k.a. illicit drug trading) in the cyberspace, there is an urgent need for automatic analysis of participants in darknet markets. However, one of the key challenges is that drug traffickers (i.e., vendors) may maintain multiple accounts across different markets or within the same market. To address this issue, in this paper, we propose and develop an intelligent system named uStyle-uID leveraging both writing and photography styles for drug trafficker identification at the first attempt. At the core of uStyle-uID is an attributed heterogeneous information network (AHIN) which elegantly integrates both writing and photography styles along with the text and photo contents, as well as other supporting attributes (i.e., trafficker and drug information) and various kinds of relations. Built on the constructed AHIN, to efficiently measure the relatedness over nodes (i.e., traffickers) in the constructed AHIN, we propose a new network embedding model Vendor2Vec to learn the low-dimensional representations for the nodes in AHIN, which leverages complementary attribute information attached in the nodes to guide the meta-path based random walk for path instances sampling. After that, we devise a learning model named vIdentifier to classify if a given pair of traffickers are the same individual. Comprehensive experiments on the data collections from four different darknet markets are conducted to validate the effectiveness of uStyle-uID which integrates our proposed method in drug trafficker identification by comparisons with alternative approaches.
{"title":"Your Style Your Identity: Leveraging Writing and Photography Styles for Drug Trafficker Identification in Darknet Markets over Attributed Heterogeneous Information Network","authors":"Yiming Zhang, Yujie Fan, Wei Song, Shifu Hou, Yanfang Ye, X. Li, Liang Zhao, C. Shi, Jiabin Wang, Qi Xiong","doi":"10.1145/3308558.3313537","DOIUrl":"https://doi.org/10.1145/3308558.3313537","url":null,"abstract":"Due to its anonymity, there has been a dramatic growth of underground drug markets hosted in the darknet (e.g., Dream Market and Valhalla). To combat drug trafficking (a.k.a. illicit drug trading) in the cyberspace, there is an urgent need for automatic analysis of participants in darknet markets. However, one of the key challenges is that drug traffickers (i.e., vendors) may maintain multiple accounts across different markets or within the same market. To address this issue, in this paper, we propose and develop an intelligent system named uStyle-uID leveraging both writing and photography styles for drug trafficker identification at the first attempt. At the core of uStyle-uID is an attributed heterogeneous information network (AHIN) which elegantly integrates both writing and photography styles along with the text and photo contents, as well as other supporting attributes (i.e., trafficker and drug information) and various kinds of relations. Built on the constructed AHIN, to efficiently measure the relatedness over nodes (i.e., traffickers) in the constructed AHIN, we propose a new network embedding model Vendor2Vec to learn the low-dimensional representations for the nodes in AHIN, which leverages complementary attribute information attached in the nodes to guide the meta-path based random walk for path instances sampling. After that, we devise a learning model named vIdentifier to classify if a given pair of traffickers are the same individual. Comprehensive experiments on the data collections from four different darknet markets are conducted to validate the effectiveness of uStyle-uID which integrates our proposed method in drug trafficker identification by comparisons with alternative approaches.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86016260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kang-Min Kim, Yeachan Kim, Jungho Lee, Ji-Min Lee, SangKeun Lee
Neural network models have achieved impressive results in the field of text classification. However, existing approaches often suffer from insufficient training data in a large-scale text classification involving a large number of categories (e.g., several thousands of categories). Several neural network models have utilized multi-task learning to overcome the limited amount of training data. However, these approaches are also limited to small-scale text classification. In this paper, we propose a novel neural network-based multi-task learning framework for large-scale text classification. To this end, we first treat the different scales of text classification (i.e., large and small numbers of categories) as multiple, related tasks. Then, we train the proposed neural network, which learns small- and large-scale text classification tasks simultaneously. In particular, we further enhance this multi-task learning architecture by using a gate mechanism, which controls the flow of features between the small- and large-scale text classification tasks. Experimental results clearly show that our proposed model improves the performance of the large-scale text classification task with the help of the small-scale text classification task. The proposed scheme exhibits significant improvements of as much as 14% and 5% in terms of micro-averaging and macro-averaging F1-score, respectively, over state-of-the-art techniques.
{"title":"From Small-scale to Large-scale Text Classification","authors":"Kang-Min Kim, Yeachan Kim, Jungho Lee, Ji-Min Lee, SangKeun Lee","doi":"10.1145/3308558.3313563","DOIUrl":"https://doi.org/10.1145/3308558.3313563","url":null,"abstract":"Neural network models have achieved impressive results in the field of text classification. However, existing approaches often suffer from insufficient training data in a large-scale text classification involving a large number of categories (e.g., several thousands of categories). Several neural network models have utilized multi-task learning to overcome the limited amount of training data. However, these approaches are also limited to small-scale text classification. In this paper, we propose a novel neural network-based multi-task learning framework for large-scale text classification. To this end, we first treat the different scales of text classification (i.e., large and small numbers of categories) as multiple, related tasks. Then, we train the proposed neural network, which learns small- and large-scale text classification tasks simultaneously. In particular, we further enhance this multi-task learning architecture by using a gate mechanism, which controls the flow of features between the small- and large-scale text classification tasks. Experimental results clearly show that our proposed model improves the performance of the large-scale text classification task with the help of the small-scale text classification task. The proposed scheme exhibits significant improvements of as much as 14% and 5% in terms of micro-averaging and macro-averaging F1-score, respectively, over state-of-the-art techniques.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88749187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elie Bursztein, Einat Clarke, Michelle DeLaune, David M. Elifff, Nick Hsu, Lindsey Olson, John Shehan, Madhukar Thakur, Kurt Thomas, Travis Bright
Over the last decade, the illegal distribution of child sexual abuse imagery (CSAI) has transformed alongside the rise of online sharing platforms. In this paper, we present the first longitudinal measurement study of CSAI distribution online and the threat it poses to society's ability to combat child sexual abuse. Our results illustrate that CSAI has grown exponentially-to nearly 1 million detected events per month-exceeding the capabilities of independent clearinghouses and law enforcement to take action. In order to scale CSAI protections moving forward, we discuss techniques for automating detection and response by using recent advancements in machine learning.
{"title":"Rethinking the Detection of Child Sexual Abuse Imagery on the Internet","authors":"Elie Bursztein, Einat Clarke, Michelle DeLaune, David M. Elifff, Nick Hsu, Lindsey Olson, John Shehan, Madhukar Thakur, Kurt Thomas, Travis Bright","doi":"10.1145/3308558.3313482","DOIUrl":"https://doi.org/10.1145/3308558.3313482","url":null,"abstract":"Over the last decade, the illegal distribution of child sexual abuse imagery (CSAI) has transformed alongside the rise of online sharing platforms. In this paper, we present the first longitudinal measurement study of CSAI distribution online and the threat it poses to society's ability to combat child sexual abuse. Our results illustrate that CSAI has grown exponentially-to nearly 1 million detected events per month-exceeding the capabilities of independent clearinghouses and law enforcement to take action. In order to scale CSAI protections moving forward, we discuss techniques for automating detection and response by using recent advancements in machine learning.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81404019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The growth of the Web in recent years has resulted in the development of various online platforms that provide healthcare information services. These platforms contain an enormous amount of information, which could be beneficial for a large number of people. However, navigating through such knowledgebases to answer specific queries of healthcare consumers is a challenging task. A majority of such queries might be non-factoid in nature, and hence, traditional keyword-based retrieval models do not work well for such cases. Furthermore, in many scenarios, it might be desirable to get a short answer that sufficiently answers the query, instead of a long document with only a small amount of useful information. In this paper, we propose a neural network model for ranking documents for question answering in the healthcare domain. The proposed model uses a deep attention mechanism at word, sentence, and document levels, for efficient retrieval for both factoid and non-factoid queries, on documents of varied lengths. Specifically, the word-level cross-attention allows the model to identify words that might be most relevant for a query, and the hierarchical attention at sentence and document levels allows it to do effective retrieval on both long and short documents. We also construct a new large-scale healthcare question-answering dataset, which we use to evaluate our model. Experimental evaluation results against several state-of-the-art baselines show that our model outperforms the existing retrieval techniques.
{"title":"A Hierarchical Attention Retrieval Model for Healthcare Question Answering","authors":"Ming Zhu, Aman Ahuja, Wei Wei, C. Reddy","doi":"10.1145/3308558.3313699","DOIUrl":"https://doi.org/10.1145/3308558.3313699","url":null,"abstract":"The growth of the Web in recent years has resulted in the development of various online platforms that provide healthcare information services. These platforms contain an enormous amount of information, which could be beneficial for a large number of people. However, navigating through such knowledgebases to answer specific queries of healthcare consumers is a challenging task. A majority of such queries might be non-factoid in nature, and hence, traditional keyword-based retrieval models do not work well for such cases. Furthermore, in many scenarios, it might be desirable to get a short answer that sufficiently answers the query, instead of a long document with only a small amount of useful information. In this paper, we propose a neural network model for ranking documents for question answering in the healthcare domain. The proposed model uses a deep attention mechanism at word, sentence, and document levels, for efficient retrieval for both factoid and non-factoid queries, on documents of varied lengths. Specifically, the word-level cross-attention allows the model to identify words that might be most relevant for a query, and the hierarchical attention at sentence and document levels allows it to do effective retrieval on both long and short documents. We also construct a new large-scale healthcare question-answering dataset, which we use to evaluate our model. Experimental evaluation results against several state-of-the-art baselines show that our model outperforms the existing retrieval techniques.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87715922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oleksii Starov, Pierre Laperdrix, A. Kapravelos, Nick Nikiforakis
In this paper, we investigate to what extent the page modifications that make browser extensions fingerprintable are necessary for their operation. We characterize page modifications that are completely unnecessary for the extension's functionality as extension bloat. By analyzing 58,034 extensions from the Google Chrome store, we discovered that 5.7% of them were unnecessarily identifiable because of extension bloat. To protect users against unnecessary extension fingerprinting due to bloat, we describe the design and implementation of an in-browser mechanism that provides coarse-grained access control for extensions on all websites. The proposed mechanism and its built-in policies, does not only protect users from fingerprinting, but also offers additional protection against malicious extensions exfiltrating user data from sensitive websites.
{"title":"Unnecessarily Identifiable: Quantifying the fingerprintability of browser extensions due to bloat","authors":"Oleksii Starov, Pierre Laperdrix, A. Kapravelos, Nick Nikiforakis","doi":"10.1145/3308558.3313458","DOIUrl":"https://doi.org/10.1145/3308558.3313458","url":null,"abstract":"In this paper, we investigate to what extent the page modifications that make browser extensions fingerprintable are necessary for their operation. We characterize page modifications that are completely unnecessary for the extension's functionality as extension bloat. By analyzing 58,034 extensions from the Google Chrome store, we discovered that 5.7% of them were unnecessarily identifiable because of extension bloat. To protect users against unnecessary extension fingerprinting due to bloat, we describe the design and implementation of an in-browser mechanism that provides coarse-grained access control for extensions on all websites. The proposed mechanism and its built-in policies, does not only protect users from fingerprinting, but also offers additional protection against malicious extensions exfiltrating user data from sensitive websites.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84294147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gabriel Cadamuro, Ramya Korlakai Vinayak, J. Blumenstock, S. Kakade, Jacob N. Shapiro
Societal-scale data is playing an increasingly prominent role in social science research; examples from research on geopolitical events include questions on how emergency events impact the diffusion of information or how new policies change patterns of social interaction. Such research often draws critical inferences from observing how an exogenous event changes meaningful metrics like network degree or network entropy. However, as we show in this work, standard estimation methodologies make systematically incorrect inferences when the event also changes the sparsity of the data. To address this issue, we provide a general framework for inferring changes in social metrics when dealing with non-stationary sparsity. We propose a plug-in correction that can be applied to any estimator, including several recently proposed procedures. Using both simulated and real data, we demonstrate that the correction significantly improves the accuracy of the estimated change under a variety of plausible data generating processes. In particular, using a large dataset of calls from Afghanistan, we show that whereas traditional methods substantially overestimate the impact of a violent event on social diversity, the plug-in correction reveals the true response to be much more modest.
{"title":"The Illusion of Change: Correcting for Biases in Change Inference for Sparse, Societal-Scale Data","authors":"Gabriel Cadamuro, Ramya Korlakai Vinayak, J. Blumenstock, S. Kakade, Jacob N. Shapiro","doi":"10.1145/3308558.3313722","DOIUrl":"https://doi.org/10.1145/3308558.3313722","url":null,"abstract":"Societal-scale data is playing an increasingly prominent role in social science research; examples from research on geopolitical events include questions on how emergency events impact the diffusion of information or how new policies change patterns of social interaction. Such research often draws critical inferences from observing how an exogenous event changes meaningful metrics like network degree or network entropy. However, as we show in this work, standard estimation methodologies make systematically incorrect inferences when the event also changes the sparsity of the data. To address this issue, we provide a general framework for inferring changes in social metrics when dealing with non-stationary sparsity. We propose a plug-in correction that can be applied to any estimator, including several recently proposed procedures. Using both simulated and real data, we demonstrate that the correction significantly improves the accuracy of the estimated change under a variety of plausible data generating processes. In particular, using a large dataset of calls from Afghanistan, we show that whereas traditional methods substantially overestimate the impact of a violent event on social diversity, the plug-in correction reveals the true response to be much more modest.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85620995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social recommendations have been a very intriguing domain for researchers in the past decade. The main premise is that the social network of a user can be leveraged to enhance the rating-based recommendation process. This has been achieved in various ways, and under different assumptions about the network characteristics, structure, and availability of other information (such as trust, content, etc.) In this work, we create neighborhoods of influence leveraging only the social graph structure. These are in turn introduced in the recommendation process both as a pre-processing step and as a social regularization factor of the matrix factorization algorithm. Our experimental evaluation using real-life datasets demonstrates the effectiveness of the proposed technique.
{"title":"With a Little Help from My Friends (and Their Friends): Influence Neighborhoods for Social Recommendations","authors":"Avni Gulati, M. Eirinaki","doi":"10.1145/3308558.3313745","DOIUrl":"https://doi.org/10.1145/3308558.3313745","url":null,"abstract":"Social recommendations have been a very intriguing domain for researchers in the past decade. The main premise is that the social network of a user can be leveraged to enhance the rating-based recommendation process. This has been achieved in various ways, and under different assumptions about the network characteristics, structure, and availability of other information (such as trust, content, etc.) In this work, we create neighborhoods of influence leveraging only the social graph structure. These are in turn introduced in the recommendation process both as a pre-processing step and as a social regularization factor of the matrix factorization algorithm. Our experimental evaluation using real-life datasets demonstrates the effectiveness of the proposed technique.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"48 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85731331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Qiu, Yuxiao Dong, Hao Ma, Jun Yu Li, Chi Wang, Kuansan Wang, Jie Tang
We study the problem of large-scale network embedding, which aims to learn latent representations for network mining applications. Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2) the explicit factorization of such matrix generates more powerful embeddings than existing methods. However, directly constructing and factorizing this matrix-which is dense-is prohibitively expensive in terms of both time and space, making it not scalable for large networks. In this work, we present the algorithm of large-scale network embedding as sparse matrix factorization (NetSMF). NetSMF leverages theories from spectral sparsification to efficiently sparsify the aforementioned dense matrix, enabling significantly improved efficiency in embedding learning. The sparsified matrix is spectrally close to the original dense one with a theoretically bounded approximation error, which helps maintain the representation power of the learned embeddings. We conduct experiments on networks of various scales and types. Results show that among both popular benchmarks and factorization based methods, NetSMF is the only method that achieves both high efficiency and effectiveness. We show that NetSMF requires only 24 hours to generate effective embeddings for a large-scale academic collaboration network with tens of millions of nodes, while it would cost DeepWalk months and is computationally infeasible for the dense matrix factorization solution. The source code of NetSMF is publicly available1.
{"title":"NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization","authors":"J. Qiu, Yuxiao Dong, Hao Ma, Jun Yu Li, Chi Wang, Kuansan Wang, Jie Tang","doi":"10.1145/3308558.3313446","DOIUrl":"https://doi.org/10.1145/3308558.3313446","url":null,"abstract":"We study the problem of large-scale network embedding, which aims to learn latent representations for network mining applications. Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2) the explicit factorization of such matrix generates more powerful embeddings than existing methods. However, directly constructing and factorizing this matrix-which is dense-is prohibitively expensive in terms of both time and space, making it not scalable for large networks. In this work, we present the algorithm of large-scale network embedding as sparse matrix factorization (NetSMF). NetSMF leverages theories from spectral sparsification to efficiently sparsify the aforementioned dense matrix, enabling significantly improved efficiency in embedding learning. The sparsified matrix is spectrally close to the original dense one with a theoretically bounded approximation error, which helps maintain the representation power of the learned embeddings. We conduct experiments on networks of various scales and types. Results show that among both popular benchmarks and factorization based methods, NetSMF is the only method that achieves both high efficiency and effectiveness. We show that NetSMF requires only 24 hours to generate effective embeddings for a large-scale academic collaboration network with tens of millions of nodes, while it would cost DeepWalk months and is computationally infeasible for the dense matrix factorization solution. The source code of NetSMF is publicly available1.","PeriodicalId":23013,"journal":{"name":"The World Wide Web Conference","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86204512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：