B. Abrahao, Flavio Chierichetti, Robert D. Kleinberg, A. Panconesi
The network inference problem consists of reconstructing the edge set of a network given traces representing the chronology of infection times as epidemics spread through the network. This problem is a paradigmatic representative of prediction tasks in machine learning that require deducing a latent structure from observed patterns of activity in a network, which often require an unrealistically large number of resources (e.g., amount of available data, or computational time). A fundamental question is to understand which properties we can predict with a reasonable degree of accuracy with the available resources, and which we cannot. We define the trace complexity as the number of distinct traces required to achieve high fidelity in reconstructing the topology of the unobserved network or, more generally, some of its properties. We give algorithms that are competitive with, while being simpler and more efficient than, existing network inference approaches. Moreover, we prove that our algorithms are nearly optimal, by proving an information-theoretic lower bound on the number of traces that an optimal inference algorithm requires for performing this task in the general case. Given these strong lower bounds, we turn our attention to special cases, such as trees and bounded-degree graphs, and to property recovery tasks, such as reconstructing the degree distribution without inferring the network. We show that these problems require a much smaller (and more realistic) number of traces, making them potentially solvable in practice.
{"title":"Trace complexity of network inference","authors":"B. Abrahao, Flavio Chierichetti, Robert D. Kleinberg, A. Panconesi","doi":"10.1145/2487575.2487664","DOIUrl":"https://doi.org/10.1145/2487575.2487664","url":null,"abstract":"The network inference problem consists of reconstructing the edge set of a network given traces representing the chronology of infection times as epidemics spread through the network. This problem is a paradigmatic representative of prediction tasks in machine learning that require deducing a latent structure from observed patterns of activity in a network, which often require an unrealistically large number of resources (e.g., amount of available data, or computational time). A fundamental question is to understand which properties we can predict with a reasonable degree of accuracy with the available resources, and which we cannot. We define the trace complexity as the number of distinct traces required to achieve high fidelity in reconstructing the topology of the unobserved network or, more generally, some of its properties. We give algorithms that are competitive with, while being simpler and more efficient than, existing network inference approaches. Moreover, we prove that our algorithms are nearly optimal, by proving an information-theoretic lower bound on the number of traces that an optimal inference algorithm requires for performing this task in the general case. Given these strong lower bounds, we turn our attention to special cases, such as trees and bounded-degree graphs, and to property recovery tasks, such as reconstructing the degree distribution without inferring the network. We show that these problems require a much smaller (and more realistic) number of traces, making them potentially solvable in practice.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78188387","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}
Matching entities from different information sources is a very important problem in data analysis and data integration. It is, however, challenging due to the number and diversity of information sources involved, and the significant editorial efforts required to collect sufficient training data. In this paper, we present an approach that leverages user clicks during Web search to automatically generate training data for entity matching. The key insight of our approach is that Web pages clicked for a given query are likely to be about the same entity. We use random walk with restart to reduce data sparseness, rely on co-clustering to group queries and Web pages, and exploit page similarity to improve matching precision. Experimental results show that: (i) With 360K pages from 6 major travel websites, we obtain 84K matchings (of 179K pages) that refer to the same entities, with an average precision of 0.826; (ii) The quality of matching obtained from a classifier trained on the resulted seed data is promising: the performance matches that of editorial data at small size and improves with size.
{"title":"Exploiting user clicks for automatic seed set generation for entity matching","authors":"Xiao Bai, F. Junqueira, Srinivasan H. Sengamedu","doi":"10.1145/2487575.2487662","DOIUrl":"https://doi.org/10.1145/2487575.2487662","url":null,"abstract":"Matching entities from different information sources is a very important problem in data analysis and data integration. It is, however, challenging due to the number and diversity of information sources involved, and the significant editorial efforts required to collect sufficient training data. In this paper, we present an approach that leverages user clicks during Web search to automatically generate training data for entity matching. The key insight of our approach is that Web pages clicked for a given query are likely to be about the same entity. We use random walk with restart to reduce data sparseness, rely on co-clustering to group queries and Web pages, and exploit page similarity to improve matching precision. Experimental results show that: (i) With 360K pages from 6 major travel websites, we obtain 84K matchings (of 179K pages) that refer to the same entities, with an average precision of 0.826; (ii) The quality of matching obtained from a classifier trained on the resulted seed data is promising: the performance matches that of editorial data at small size and improves with size.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90063965","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}
Karthik Raman, Adith Swaminathan, J. Gehrke, T. Joachims
Big Data Pipelines decompose complex analyses of large data sets into a series of simpler tasks, with independently tuned components for each task. This modular setup allows re-use of components across several different pipelines. However, the interaction of independently tuned pipeline components yields poor end-to-end performance as errors introduced by one component cascade through the whole pipeline, affecting overall accuracy. We propose a novel model for reasoning across components of Big Data Pipelines in a probabilistically well-founded manner. Our key idea is to view the interaction of components as dependencies on an underlying graphical model. Different message passing schemes on this graphical model provide various inference algorithms to trade-off end-to-end performance and computational cost. We instantiate our framework with an efficient beam search algorithm, and demonstrate its efficiency on two Big Data Pipelines: parsing and relation extraction.
{"title":"Beyond myopic inference in big data pipelines","authors":"Karthik Raman, Adith Swaminathan, J. Gehrke, T. Joachims","doi":"10.1145/2487575.2487588","DOIUrl":"https://doi.org/10.1145/2487575.2487588","url":null,"abstract":"Big Data Pipelines decompose complex analyses of large data sets into a series of simpler tasks, with independently tuned components for each task. This modular setup allows re-use of components across several different pipelines. However, the interaction of independently tuned pipeline components yields poor end-to-end performance as errors introduced by one component cascade through the whole pipeline, affecting overall accuracy. We propose a novel model for reasoning across components of Big Data Pipelines in a probabilistically well-founded manner. Our key idea is to view the interaction of components as dependencies on an underlying graphical model. Different message passing schemes on this graphical model provide various inference algorithms to trade-off end-to-end performance and computational cost. We instantiate our framework with an efficient beam search algorithm, and demonstrate its efficiency on two Big Data Pipelines: parsing and relation extraction.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72961949","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}
Yanping Chen, Bing Hu, Eamonn J. Keogh, Gustavo E. A. P. A. Batista
Classification of time series data is an important problem with applications in virtually every scientific endeavor. The large research community working on time series classification has typically used the UCR Archive to test their algorithms. In this work we argue that the availability of this resource has isolated much of the research community from the following reality, labeled time series data is often very difficult to obtain. The obvious solution to this problem is the application of semi-supervised learning; however, as we shall show, direct applications of off-the-shelf semi-supervised learning algorithms do not typically work well for time series. In this work we explain why semi-supervised learning algorithms typically fail for time series problems, and we introduce a simple but very effective fix. We demonstrate our ideas on diverse real word problems.
{"title":"DTW-D: time series semi-supervised learning from a single example","authors":"Yanping Chen, Bing Hu, Eamonn J. Keogh, Gustavo E. A. P. A. Batista","doi":"10.1145/2487575.2487633","DOIUrl":"https://doi.org/10.1145/2487575.2487633","url":null,"abstract":"Classification of time series data is an important problem with applications in virtually every scientific endeavor. The large research community working on time series classification has typically used the UCR Archive to test their algorithms. In this work we argue that the availability of this resource has isolated much of the research community from the following reality, labeled time series data is often very difficult to obtain. The obvious solution to this problem is the application of semi-supervised learning; however, as we shall show, direct applications of off-the-shelf semi-supervised learning algorithms do not typically work well for time series. In this work we explain why semi-supervised learning algorithms typically fail for time series problems, and we introduce a simple but very effective fix. We demonstrate our ideas on diverse real word problems.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75851634","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}
In many applications such as image and video processing, the data matrix often possesses simultaneously a low-rank structure capturing the global information and a sparse component capturing the local information. How to accurately extract the low-rank and sparse components is a major challenge. Robust Principal Component Analysis (RPCA) is a general framework to extract such structures. It is well studied that under certain assumptions, convex optimization using the trace norm and l1-norm can be an effective computation surrogate of the difficult RPCA problem. However, such convex formulation is based on a strong assumption which may not hold in real-world applications, and the approximation error in these convex relaxations often cannot be neglected. In this paper, we present a novel non-convex formulation for the RPCA problem using the capped trace norm and the capped l1-norm. In addition, we present two algorithms to solve the non-convex optimization: one is based on the Difference of Convex functions (DC) framework and the other attempts to solve the sub-problems via a greedy approach. Our empirical evaluations on synthetic and real-world data show that both of the proposed algorithms achieve higher accuracy than existing convex formulations. Furthermore, between the two proposed algorithms, the greedy algorithm is more efficient than the DC programming, while they achieve comparable accuracy.
{"title":"Robust principal component analysis via capped norms","authors":"Qian Sun, Shuo Xiang, Jieping Ye","doi":"10.1145/2487575.2487604","DOIUrl":"https://doi.org/10.1145/2487575.2487604","url":null,"abstract":"In many applications such as image and video processing, the data matrix often possesses simultaneously a low-rank structure capturing the global information and a sparse component capturing the local information. How to accurately extract the low-rank and sparse components is a major challenge. Robust Principal Component Analysis (RPCA) is a general framework to extract such structures. It is well studied that under certain assumptions, convex optimization using the trace norm and l1-norm can be an effective computation surrogate of the difficult RPCA problem. However, such convex formulation is based on a strong assumption which may not hold in real-world applications, and the approximation error in these convex relaxations often cannot be neglected. In this paper, we present a novel non-convex formulation for the RPCA problem using the capped trace norm and the capped l1-norm. In addition, we present two algorithms to solve the non-convex optimization: one is based on the Difference of Convex functions (DC) framework and the other attempts to solve the sub-problems via a greedy approach. Our empirical evaluations on synthetic and real-world data show that both of the proposed algorithms achieve higher accuracy than existing convex formulations. Furthermore, between the two proposed algorithms, the greedy algorithm is more efficient than the DC programming, while they achieve comparable accuracy.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78954851","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}
Analyzing functional interactions between small compounds and proteins is indispensable in genomic drug discovery. Since rich information on various compound-protein inter- actions is available in recent molecular databases, strong demands for making best use of such databases require to in- vent powerful methods to help us find new functional compound-protein pairs on a large scale. We present the succinct interval-splitting tree algorithm (SITA) that efficiently per- forms similarity search in databases for compound-protein pairs with respect to both binary fingerprints and real-valued properties. SITA achieves both time and space efficiency by developing the data structure called interval-splitting trees, which enables to efficiently prune the useless portions of search space, and by incorporating the ideas behind wavelet tree, a succinct data structure to compactly represent trees. We experimentally test SITA on the ability to retrieve similar compound-protein pairs/substrate-product pairs for a query from large databases with over 200 million compound- protein pairs/substrate-product pairs and show that SITA performs better than other possible approaches.
{"title":"Succinct interval-splitting tree for scalable similarity search of compound-protein pairs with property constraints","authors":"Yasuo Tabei, Akihiro Kishimoto, Masaaki Kotera, Yoshihiro Yamanishi","doi":"10.1145/2487575.2487637","DOIUrl":"https://doi.org/10.1145/2487575.2487637","url":null,"abstract":"Analyzing functional interactions between small compounds and proteins is indispensable in genomic drug discovery. Since rich information on various compound-protein inter- actions is available in recent molecular databases, strong demands for making best use of such databases require to in- vent powerful methods to help us find new functional compound-protein pairs on a large scale. We present the succinct interval-splitting tree algorithm (SITA) that efficiently per- forms similarity search in databases for compound-protein pairs with respect to both binary fingerprints and real-valued properties. SITA achieves both time and space efficiency by developing the data structure called interval-splitting trees, which enables to efficiently prune the useless portions of search space, and by incorporating the ideas behind wavelet tree, a succinct data structure to compactly represent trees. We experimentally test SITA on the ability to retrieve similar compound-protein pairs/substrate-product pairs for a query from large databases with over 200 million compound- protein pairs/substrate-product pairs and show that SITA performs better than other possible approaches.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79023550","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}
Online social networks have become important channels for users to share content with their connections and diffuse information. Although much work has been done to identify socially influential users, the problem of finding "reputable" sharers, who share good content, has received relatively little attention. Availability of such reputation scores can be useful or various applications like recommending people to follow, procuring high quality content in a scalable way, creating a content reputation economy to incentivize high quality sharing, and many more. To estimate sharer reputation, it is intuitive to leverage data that records how recipients respond (through clicking, liking, etc.) to content items shared by a sharer. However, such data is usually biased --- it has a selection bias since the shared items can only be seen and responded to by users connected to the sharer in most social networks, and it has a response bias since the response is usually influenced by the relationship between the sharer and the recipient (which may not indicate whether the shared content is good). To correct for such biases, we propose to utilize an additional data source that provides unbiased goodness estimates for a small set of shared items, and calibrate biased social data through a novel multi-level hierarchical model that describes how the unbiased data and biased data are jointly generated according to sharer reputation scores. The unbiased data also provides the ground truth for quantitative evaluation of different methods. Experiments based on such ground-truth data show that our proposed model significantly outperforms existing methods that estimate social influence using biased social data.
{"title":"Estimating sharer reputation via social data calibration","authors":"Jaewon Yang, Bee-Chung Chen, D. Agarwal","doi":"10.1145/2487575.2487685","DOIUrl":"https://doi.org/10.1145/2487575.2487685","url":null,"abstract":"Online social networks have become important channels for users to share content with their connections and diffuse information. Although much work has been done to identify socially influential users, the problem of finding \"reputable\" sharers, who share good content, has received relatively little attention. Availability of such reputation scores can be useful or various applications like recommending people to follow, procuring high quality content in a scalable way, creating a content reputation economy to incentivize high quality sharing, and many more. To estimate sharer reputation, it is intuitive to leverage data that records how recipients respond (through clicking, liking, etc.) to content items shared by a sharer. However, such data is usually biased --- it has a selection bias since the shared items can only be seen and responded to by users connected to the sharer in most social networks, and it has a response bias since the response is usually influenced by the relationship between the sharer and the recipient (which may not indicate whether the shared content is good). To correct for such biases, we propose to utilize an additional data source that provides unbiased goodness estimates for a small set of shared items, and calibrate biased social data through a novel multi-level hierarchical model that describes how the unbiased data and biased data are jointly generated according to sharer reputation scores. The unbiased data also provides the ground truth for quantitative evaluation of different methods. Experiments based on such ground-truth data show that our proposed model significantly outperforms existing methods that estimate social influence using biased social data.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81119909","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}
Charalampos E. Tsourakakis, F. Bonchi, A. Gionis, Francesco Gullo, M. A. Tsiarli
Finding dense subgraphs is an important graph-mining task with many applications. Given that the direct optimization of edge density is not meaningful, as even a single edge achieves maximum density, research has focused on optimizing alternative density functions. A very popular among such functions is the average degree, whose maximization leads to the well-known densest-subgraph notion. Surprisingly enough, however, densest subgraphs are typically large graphs, with small edge density and large diameter. In this paper, we define a novel density function, which gives subgraphs of much higher quality than densest subgraphs: the graphs found by our method are compact, dense, and with smaller diameter. We show that the proposed function can be derived from a general framework, which includes other important density functions as subcases and for which we show interesting general theoretical properties. To optimize the proposed function we provide an additive approximation algorithm and a local-search heuristic. Both algorithms are very efficient and scale well to large graphs. We evaluate our algorithms on real and synthetic datasets, and we also devise several application studies as variants of our original problem. When compared with the method that finds the subgraph of the largest average degree, our algorithms return denser subgraphs with smaller diameter. Finally, we discuss new interesting research directions that our problem leaves open.
{"title":"Denser than the densest subgraph: extracting optimal quasi-cliques with quality guarantees","authors":"Charalampos E. Tsourakakis, F. Bonchi, A. Gionis, Francesco Gullo, M. A. Tsiarli","doi":"10.1145/2487575.2487645","DOIUrl":"https://doi.org/10.1145/2487575.2487645","url":null,"abstract":"Finding dense subgraphs is an important graph-mining task with many applications. Given that the direct optimization of edge density is not meaningful, as even a single edge achieves maximum density, research has focused on optimizing alternative density functions. A very popular among such functions is the average degree, whose maximization leads to the well-known densest-subgraph notion. Surprisingly enough, however, densest subgraphs are typically large graphs, with small edge density and large diameter. In this paper, we define a novel density function, which gives subgraphs of much higher quality than densest subgraphs: the graphs found by our method are compact, dense, and with smaller diameter. We show that the proposed function can be derived from a general framework, which includes other important density functions as subcases and for which we show interesting general theoretical properties. To optimize the proposed function we provide an additive approximation algorithm and a local-search heuristic. Both algorithms are very efficient and scale well to large graphs. We evaluate our algorithms on real and synthetic datasets, and we also devise several application studies as variants of our original problem. When compared with the method that finds the subgraph of the largest average degree, our algorithms return denser subgraphs with smaller diameter. Finally, we discuss new interesting research directions that our problem leaves open.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75348551","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}
Many businesses now have almost real time data available about their operations. This data can be helpful in contemporaneous prediction ("nowcasting") of various economic indicators. We illustrate how one can use Google search data to nowcast economic metrics of interest, and discuss some of the ramifications for research and policy. Our approach combines three Bayesian techniques: Kalman filtering, spike-and-slab regression, and model averaging. We use Kalman filtering to whiten the time series in question by removing the trend and seasonal behavior. Spike-and-slab regression is a Bayesian method for variable selection that works even in cases where the number of predictors is far larger than the number of observations. Finally, we use Markov Chain Monte Carlo methods to sample from the posterior distribution for our model; the final forecast is an average over thousands of draws from the posterior. An advantage of the Bayesian approach is that it allows us to specify informative priors that affect the number and type of predictors in a flexible way.
{"title":"Predicting the present with search engine data","authors":"H. Varian","doi":"10.1145/2487575.2492150","DOIUrl":"https://doi.org/10.1145/2487575.2492150","url":null,"abstract":"Many businesses now have almost real time data available about their operations. This data can be helpful in contemporaneous prediction (\"nowcasting\") of various economic indicators. We illustrate how one can use Google search data to nowcast economic metrics of interest, and discuss some of the ramifications for research and policy. Our approach combines three Bayesian techniques: Kalman filtering, spike-and-slab regression, and model averaging. We use Kalman filtering to whiten the time series in question by removing the trend and seasonal behavior. Spike-and-slab regression is a Bayesian method for variable selection that works even in cases where the number of predictors is far larger than the number of observations. Finally, we use Markov Chain Monte Carlo methods to sample from the posterior distribution for our model; the final forecast is an average over thousands of draws from the posterior. An advantage of the Bayesian approach is that it allows us to specify informative priors that affect the number and type of predictors in a flexible way.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86570633","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}
D. Erdös, Vatche Isahagian, Azer Bestavros, Evimaria Terzi
Arguably, the most effective technique to ensure wide adoption of a concept (or product) is by repeatedly exposing individuals to messages that reinforce the concept (or promote the product). Recognizing the role of repeated exposure to a message, in this paper we propose a novel framework for the effective placement of content: Given the navigational patterns of users in a network, e.g., web graph, hyperlinked corpus, or road network, and given a model of the relationship between content-adoption and frequency of exposition, we define the repetition-aware content-placement (RACP) problem as that of identifying the set of B nodes on which content should be placed so that the expected number of users adopting that content is maximized. The key contribution of our work is the introduction of memory into the navigation process, by making user conversion dependent on the number of her exposures to that content. This dependency is captured using a conversion model that is general enough to capture arbitrary dependencies. Our solution to this general problem builds upon the notion of absorbing random walks, which we extend appropriately in order to address the technicalities of our definitions. Although we show the RACP problem to be NP-hard, we propose a general and efficient algorithmic solution. Our experimental results demonstrate the efficacy and the efficiency of our methods in multiple real-world datasets obtained from different application domains.
{"title":"Repetition-aware content placement in navigational networks","authors":"D. Erdös, Vatche Isahagian, Azer Bestavros, Evimaria Terzi","doi":"10.1145/2487575.2487622","DOIUrl":"https://doi.org/10.1145/2487575.2487622","url":null,"abstract":"Arguably, the most effective technique to ensure wide adoption of a concept (or product) is by repeatedly exposing individuals to messages that reinforce the concept (or promote the product). Recognizing the role of repeated exposure to a message, in this paper we propose a novel framework for the effective placement of content: Given the navigational patterns of users in a network, e.g., web graph, hyperlinked corpus, or road network, and given a model of the relationship between content-adoption and frequency of exposition, we define the repetition-aware content-placement (RACP) problem as that of identifying the set of B nodes on which content should be placed so that the expected number of users adopting that content is maximized. The key contribution of our work is the introduction of memory into the navigation process, by making user conversion dependent on the number of her exposures to that content. This dependency is captured using a conversion model that is general enough to capture arbitrary dependencies. Our solution to this general problem builds upon the notion of absorbing random walks, which we extend appropriately in order to address the technicalities of our definitions. Although we show the RACP problem to be NP-hard, we propose a general and efficient algorithmic solution. Our experimental results demonstrate the efficacy and the efficiency of our methods in multiple real-world datasets obtained from different application domains.","PeriodicalId":20472,"journal":{"name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84266584","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：