Unsupervised Ranking using Graph Structures and Node Attributes

Hsu, Chin-Chi; Lai, Yi-An; Chen, Wen‐Hao; Feng, Ming-Han; Lin, Shou-De

doi:10.1145/3018661.3018668

Cited by 28 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a nutshell, an embedding algorithm learns a latent vector representation that maps each vertex v in the graph G to a single d dimensional vector. This area has found strong applications, as the embedding representation of nodes leads to improved results in data mining and machine learning tasks, such as node classification [37], user profiling [39], ranking [26], and link prediction [2,25]. In virtually all cases, the crucial assumption of the embedding methods developed so far is that a single embedding vector has to be learned for each node in the graph.…”

Section: Introductionmentioning

confidence: 99%

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Epasto

Perozzi

2019

The World Wide Web Conference

104

109

View full text Add to dashboard Cite

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph. But can nodes really be best described by a single vector representation? In this work, we propose a method for learning multiple representations of the nodes in a graph (e.g., the users of a social network). Based on a principled decomposition of the ego-network, each representation encodes the role of the node in a different local community in which the nodes participate. These representations allow for improved reconstruction of the nuanced relationships that occur in the graph -a phenomenon that we illustrate through state-of-the-art results on link prediction tasks on a variety of graphs, reducing the error by up to 90%. In addition, we show that these embeddings allow for effective visual analysis of the learned community structure.

show abstract

Section: Introductionmentioning

confidence: 99%

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Epasto

Perozzi

2019

The World Wide Web Conference

104

109

View full text Add to dashboard Cite

show abstract

“…The earliest structure-based solutions to rank nodes were based on centrality-based metrics [17], such as degree centrality [18], closeness centrality [17] and betweenness centrality [19] derived in the research field of social networks [20]. PageRank [6] and HITS [21] were subsequently proposed.…”

Section: Related Workmentioning

confidence: 99%

FSCRank: A Failure-Sensitive Structure-Based Component Ranking Approach for Cloud Applications

Zuo

Zhang

et al. 2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Cloud computing has attracted a growing number of enterprises to move their business to the cloud because of the associated operational and cost benefits. Improving availability is one of the major concerns of cloud application owners because modern applications generally comprise a large number of components and failures are common at scale. Fault tolerance enables an application to continue operating properly when failure occurs, but fault tolerance strategy is typically employed for the most important components because of financial concerns. Therefore, identifying important components has become a critical research issue. To address this problem, we propose a failure-sensitive structure-based component ranking approach (FSCRank), which integrates component failure impact and application structure information into component importance evaluation. An iterative ranking algorithm is developed according to the structural characteristics of cloud applications. The experimental results show that FSCRank outperforms the other two structure-based ranking algorithms for cloud applications. In addition, factors that affect application availability optimization are analyzed and summarized. The experimental results suggest that the availability of cloud applications can be greatly improved by implementing fault tolerance strategy for the important components identified by FSCRank.

show abstract

“…This method was compared with various search engines and concluded that the design of the method is based on increasing the reliability of the results retrieved by the MSE. Also, in [19][20][21][22][23][24][25][26] algorithms based on various mechanisms such as anthology and non-regulatory algorithms, and etc. are presented for ranking web pages.…”

Section: A Related Workmentioning

confidence: 99%

A Multi-Criteria Ranking Algorithm Based on the VIKOR Method for Meta-Search Engines

Jamshidi

Haji

Kamankesh

et al. 2019

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Ranking of web pages is one of the most important parts of search engines and is, in fact, a process that through it the quality of a page is estimated by the search engine. In this study, a ranking algorithm based on VIKOR multi-criteria decisionmaking method for Meta-Search Engines (MSEs) was proposed. In this research, the considered MSE first will receive the suggested pages associated with the search term from eight search engines including, Teoma, Google, Yahoo!, AlltheWeb, AltaVista, Wisenut, ODP, MSN. The results, at most 10 first pages are selected from each search engine and creates the initial dataset contains 80 web pages. The proposed parser is then executed on these pages and the eight criteria including the rank of web page in the related search engine, access time, number of repetitions of search terms, positions of search term at the webpage, numbers of media at the webpage, the number of imports in the webpage, the number of incoming links, and the number of outgoing links are extracted from these web pages. Finally, by using the VIKOR method and these extracted criteria, web pages will rank and 10 top results will be provided for the user. To implement the proposed method, JAVA and MATLAB languages are used. In the experiments, the proposed method is implemented for a query and its ranking results have been compared in terms of accuracy with three famous search engine including Google, Yahoo, and MSN. The results of comparisons show that the proposed method offers higher accuracy.

show abstract

Unsupervised Ranking using Graph Structures and Node Attributes

Cited by 28 publications

References 18 publications

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts

FSCRank: A Failure-Sensitive Structure-Based Component Ranking Approach for Cloud Applications

A Multi-Criteria Ranking Algorithm Based on the VIKOR Method for Meta-Search Engines

Contact Info

Product

Resources

About