Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Motivating Example and Background
Background of Authority Flow-Based Ranking
Related Work
Ranking and Recommendation
Learning the W of Futurerank
Data Sets and Methods
Evaluating Futurerank Performance
Generate Training Data y as Follows
Conclusions and Future Work
References
All Topics
Mathematics
Combinatorics

Learning to Rank in Entity Relationship Graphs

Profile image of Louiqa RaschidLouiqa Raschid

2019, Informs Journal on Computing

https://doi.org/10.1287/IJOC.2018.0837
visibility

…

description

19 pages

link

1 file

Abstract

Many real-world data sets are modeled as entity relationship graphs or heterogeneous information networks. In these graphs, nodes represent entities and edges mimic relationships. ObjectRank extends the well-known PageRank authority flow-based ranking method to entity relationship graphs using an authority flow weight vector (W). The vector W assigns a different authority flow-based importance (weight) to each edge type based on domain knowledge or personalization. In this paper, our contribution is a framework for Learning to Rank in entity relationship graphs to learn W, in the context of authority flow. We show that the problem is similar to learning a recursive scoring function. We present a two-phase iterative solution and multiple variants of learning. In pointwise learning, we learn W, and hence the scoring function, from the scores of a sample of nodes. In pairwise learning, we learn W from given preferences for pairs of nodes. To demonstrate our contribution in a real setting, we apply our framework to learn the rank, with high accuracy, for a real-world challenge of predicting future citations in a bibliographic archive-that is, the FutureRank score. Our extensive experiments show that with a small amount of training data, and a limited number of iterations, our Learning to Rank approach learns W with high accuracy. Learning works well with pairwise training data in large graphs.

Related papers

Effective latent space graph-based re-ranking model with global consistency
Fazl Q Parray

2009

Recently the re-ranking algorithms have been quite popular for web search and data mining. However, one of the issues is that those algorithms treat the content and link information individually. Inspired by graph-based machine learning algorithms, we propose a novel and general framework to model the re-ranking algorithm, by regularizing the smoothness of ranking scores over the graph, along with a regularizer on the initial ranking scores (which are obtained by the base ranker). The intuition behind the model is the global consistency over the graph: similar entities are likely to have the same ranking scores with respect to a query. Our approach simultaneously incorporates the content with other explicit or implicit link information in a latent space graph. Then an effective unified re-ranking algorithm is performed on the graph with respect to the query. To illustrate our methodology, we apply the framework to literature retrieval and expert finding applications on DBLP bibliography data. We compare the proposed method with the initial language model method and another PageRankstyle re-ranking method. Also, we evaluate the proposed method with varying graphs and settings. Experimental results show that the improvement in our proposed method is consistent and promising.

View PDFchevron_right
Generic Damping Functions for Propagating Importance in Link-Based Ranking
Ricardo Baeza-Yates

Internet Mathematics, 2006

This paper introduces a family of link-based ranking algorithms that propagate page importance through links. The algorithms include a damping function which decreases with distance, thus a direct link implies greater endorsement that a link via a longer path. PageRank is the most widely known ranking function of this family.

View PDFchevron_right
Challenges in personalized authority flow based ranking of social media
Louiqa Raschid

Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10, 2010

As the social interaction of Internet users increases, so does the need to effectively rank social media. We study the challenges of personalized ranking of blog posts. Web search techniques are inadequate since social media lack many of the characteristics of the Web such as rich document content and an extensive hyperlink graph. Further, user behavior in social media has moved beyond keyword based search and must support users who follow a particular blog or theme. In this research, we extend a social media dataset to exploit the associations between authors, blog posts, and categories (topics) of the posts. We then apply personalized authority flow based ranking algorithms based on the random surfer model. We evaluate our personalization approaches through an extensive study on a range of virtual users whose preferences are defined based on intuitive criteria. Our evaluation shows that the accuracy of our personalized recommendations ranges from good to very good for a majority of users, and outperforms reasonable baseline approaches.

View PDFchevron_right
Node ranking in labeled directed graphs
Srinivas Kashyap

Proceedings of the Thirteenth ACM conference on Information and knowledge management - CIKM '04, 2004

Our work is motivated by the problem of ranking hyperlinked documents for a given query. Given an arbitrary directed graph with edge and node labels, we present a new flow-based model and an efficient method to dynamically rank the nodes of this graph with respect to any of the original labels. Ranking documents for a given query in a hyperlinked document set and ranking of authors/articles for a given topic in a citation database are some typical applications of our method. We outline the structural conditions that the graph must satisfy for our ranking to be different from the traditional PageRank. We have built a system using two indices that is capable of dynamically ranking documents for any given query. We validate our system and method using experiments on a few datasets: a crawl of the IBM Intranet (12 million pages), a crawl of the www (30 million pages) and the DBLP citation dataset. We compare our method to existing schemes for topic-biased ranking that require a classifier and the traditional PageRank. In these experiments, we demonstrate that our method is well suited for fine-grained ranking and that our method performs better than the existing schemes. We also demonstrate that our system can obtain an improved ranking with very little impact on query time.

View PDFchevron_right
PageRank for bibliographic networks
francois rousselot

Scientometrics, 2008

In this paper, we present several modifications of the classical PageRank formula adapted for bibliographic networks. Our versions of PageRank take into account not only the citation but also the co-authorship graph. We verify the viability of our algorithms by applying them to the data from the DBLP digital library and by comparing the resulting ranks of the winners of the ACM E. F. Codd Innovations Award. Rankings based on both the citation and co-authorship information turn out to be "better" than the standard PageRank ranking.

View PDFchevron_right
Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs
Mohammad Al Hasan

arXiv (Cornell University), 2016

Link prediction, or predicting the likelihood of a link in a knowledge graph based on its existing state is a key research task. It differs from a traditional link prediction task in that the links in a knowledge graph are categorized into different predicates and the link prediction performance of different predicates in a knowledge graph generally varies widely. In this work, we propose a latent feature embedding based link prediction model which considers the prediction task for each predicate disjointly. To learn the model parameters it utilizes a Bayesian personalized ranking based optimization technique. Experimental results on large-scale knowledge bases such as YAGO2 show that our link prediction approach achieves substantially higher performance than several state-of-art approaches. We also show that for a given predicate the topological properties of the knowledge graph induced by the given predicate edges are key indicators of the link prediction performance of that predicate in the knowledge graph.

View PDFchevron_right
Time-aware PageRank for bibliographic networks
Dalibor Fiala

Journal of Informetrics, 2012

View PDFchevron_right
A novel approach to Rank Authors in an Academic Network
Journal of Computer Science IJCSIS

Ranking the authors in an academic network is a significant research domain to find the top authors in various domains. We find various links based ranking algorithms and index based approaches to measure the productivity and impact of an author in a social network of authors. The research problem to rank the experts has vast applications such as advisor finding, domain expert identification. In this paper, we propose a novel approach to rank the scholars in the academic network of DBLP, a well-known computer science bibliography website. A huge data set is prepared covering the publications of more than 70 years. We propose AuthorRank and Weighted AuthorRank algorithms based on the state of the art ranking algorithms of PageRank and weighted PageRank algorithms respectively. For weighted algorithms, existing methods lack to provide diverse weights. We introduce the novel weights of h-index, g-index and R-index and elaborate their impact to identify the top authors in the scholarly network. The results confirm that the proposed algorithms find the top authors in an effective manner.

View PDFchevron_right
Trans4E: Link prediction on scholarly knowledge graphs
Nadezhda Vassilyeva

Neurocomputing, 2021

The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with N≫M. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., 'neural networks', 'machine learning', 'artificial intelligence'), and affiliation types (e.g., 'education', 'company', 'government'), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.

View PDFchevron_right
FutureRank: Ranking scientific articles by predicting their future PageRank
Lise Getoor

2009

Abstract The dynamic nature of citation networks makes the task of ranking scientific articles hard. Citation networks are continually evolving because articles obtain new citations every day. For ranking scientific articles, we can define the popularity or prestige of a paper based on the number of past citations at the user query time; however, we argue that what is most useful is the expected future references.

View PDFchevron_right

References (65)

  1. Adomavicius G, Tuzhilin A (2015) Context-aware recommender systems. Ricci F, Rokach L, Shapira B, eds. Recommender Systems Handbook, 2nd ed. (Springer, Boston), 191-226.
  2. Bahmani B, Chakrabarti K, Xin D (2011) Fast Personalized PageRank on MapReduce (ACM, New York).
  3. Bahmani B, Chowdhury A, Goel A (2010) Fast incremental and personalized PageRank. Proc. VLDB Endow. 4(3):173-184.
  4. Balmin A, Hristidis V, Papakonstantinou Y (2004) Objectrank: Authority-based keyword search in databases. Proc. 2004 VLDB Conf. (Morgan Kaufmann, St. Louis), 564-575.
  5. Baltrunas L, Ludwig B, Ricci F (2011) Matrix factorization techniques for context aware recommendation. Proc. 5th ACM Conf. Rec- ommender Systems (RecSys'11) (ACM, New York), 301-304.
  6. Burges C, et al. (2005) Learning to rank using gradient descent, Proc. 22nd Internat. Conf. Machine Learn. (ICML'05), J. Machine Learn. Res. 89-96.
  7. Burton K, Java A, Soboroff I (2009) The icwsm 2009 spinn3r dataset. Proc. Conf. Weblogs Social Media (ICWSM'09) (Association for the Advancement of Artificial Intelligence, Palo Alto, CA).
  8. Cao Z, Liu T (2007) Learning to rank: From pairwise approach to listwise approach. Proc. 24th Internat. Conf. Machine Learn., J. Machine Learn. Res., 129-136.
  9. Chakrabarti S (2007) Dynamic personalized pagerank in entity- relation graphs. Proc. 16th Internat. Conf. World Wide Web (WWW'07) (ACM, New York), 571-580.
  10. Chakrabarti S, Agarwal A (2006) Learning parameters in entity relationship graphs from ranking preferences. Eur. Conf. Ma- chine Learn. Principles Practice Knowledge Discovery Databases (Springer, Berlin), 91-102.
  11. Cooley R, Mobasher B, Srivastava J (1999) Data preparation for mining world wide web browsing patterns. Knowledge Inform. Systems 1(1):5-32.
  12. Cortes C, Mohri M, Rastogi A (2007) Magnitude-preserving ranking algorithms. Proc. 24th Internat. Conf. Machine Learn. (ICML'07) (ACM, New York), 169-176,
  13. Croft B, Metzler D, Strohman T (2009) Search Engines: Information Retrieval in Practice, 1st ed. (Addison-Wesley Publishing Com- pany, Boston).
  14. Deng W, Ma J (2017) Leveraging heterogeneous information network for community recommendation. Proc. Internat. Conf. Inform. Systems (Association of Information Systems, Atlanta)
  15. Fakas G, Cai Z, Mamoulis N (2014) Versatile size-ℓ object summaries for relational keyword search. IEEE Trans. Knowledge Data Engrg. 26(4):1026-1038.
  16. Fakas G, Cai Z, Mamoulis N (2015) Diverse and proportional size-l object summaries for keyword search. Proc. 2015 ACM SIGMOD Internat. Conf. Management Data (ACM, New York), 363-375.
  17. Fakas G, Cai Z, Mamoulis N (2016) Diverse and proportional size-l object summaries using pairwise relevance. VLDB J. 25(6):791-816.
  18. Fogaras D, Rácz B, Csalogány K, Sarl ós T (2005) Towards scaling fully personalized pagerank: Algorithms, lower bounds, and exper- iments. Internet Math. 2(3):333-358.
  19. Gao J, Qi H, Xia X, yun Nie J (2005) Linear discriminant model for information retrieval. Proc. 28th Internat. ACM SIGIR Conf. (ACM, New York), 290-297.
  20. Geerts F, Mannila H, Terzi E (2004) Relational link-based ranking. Proc. 2004 VLDB Conf. (Morgan Kaufmann, St. Louis), 552-563.
  21. Getoor L, Taskar B (2007) Introduction to statistical relational learning. Adaptive Computation and Machine Learning (MIT Press, Cambridge, MA).
  22. Haveliwala T (2002) Topic-sensitive pagerank. Proc. 11th Internat. Conf. World Wide Web (WWW'02) (ACM, New York).
  23. Hristidis V, Hwang H, Papakonstantinou Y (2008) Authority-based keyword search in databases. ACM Trans. Database System 33(1): 1-40.
  24. Hristidis V, Wu Y, Raschid L (2014) Efficient ranking on entity graphswith personalized relationships. IEEE Trans. Knowledge Data Engrg. 26(4):850-863.
  25. Hwang H, Balmin A, Reinwald B, Nijkamp E (2009) Binrank: Scaling dynamic authority-based search using materialized subgraphs. Proc. Internat. Conf. Data Engrg. (IEEE, Piscataway, NJ) 66-77.
  26. Jeh G, Widom J (2003) Scaling personalized web search. Proc. 12th Internat. Conf. World Wide Web (WWW'03) (ACM, New York), 271-279.
  27. Ji M, Han J, Danilevsky M (2011) Ranking-based classification of heterogeneous information networks. Proc. 17th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York), 1298-1306.
  28. Kashyap A, Hristidis V (2012) Logrank: Summarizing social activity logs. WebDB (ACM, New York), 1-6.
  29. KDD Cup 2003 (2016) Datasets. http://www.cs.cornell.edu/ projects/kddcup/datasets.html.
  30. Kleinberg JM (1999) Authoritative sources in a hyperlinked envi- ronment. J. ACM 46(5):604-632.
  31. Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30-37.
  32. Kritikopoulos A, Sideri M (2003) The compass filter: Search engine result personalization using web communities. Mobasher B, Anand SS, eds. Intelligent Techniques for Web Personalization: IJCAI 2003 Workshop, ITWP 2003, Acapulco, Mexico, August 11, 2003, Revised Selected Papers, Lecture Notes in Computer Science, vol. 3169 (Springer, Berlin), 229-240.
  33. Lao N, Cohen WW (2010) Relational retrieval using a combination of path-constrained random walks. Machine Learn. 81(1):53-67.
  34. Li P, Burges C, Wu Q (2007) Mcrank: Learning to rank using multiple classification and gradient boosting. Platt JC, Koller D, Singer Y, Raschid, Sayyadi, and Hristidis: Learning to Rank in Entity Relationship Graphs INFORMS Journal on Computing, Articles in Advance, pp. 1-18, © 2019 INFORMS Roweis ST, eds. Advances in Neural Information Processing Systems, vol. 20 (Morgan Kauffman, San Francisco).
  35. Liu Y, Fu Y (2007) Automatic search engine performance evaluation with click-through data analysis. Proc. 16th Internat. Conf. World Wide Web (WWW'07) (ACM, New York).
  36. Manning C, Raghavan P, Schutze H (2008) Introduction to Information Retrieval (Cambridge University Press, New York).
  37. Mobasher B, Cooley R, Srivastava J (2000) Automatic personalization based on web usage mining. Commun. ACM 43(8):142-151.
  38. Nallapati R (2004) Discriminative models for information retrieval. Proc. 27th Annual Internat. Conf. Res. Development Inform. Retrieval (SIGIR'04) (ACM, New York), 64-71.
  39. Nie Z, Zhang Y, Wen JR, Ma WY (2005) Object-level ranking: Bringing order to web objects. Proc. 14th Internat. Conf. World Wide Web (WWW'05) (ACM, New York), 567-574.
  40. Page L, Brin S, Motwani R, Winograd T (1998) The pagerank citation ranking: Bringing order to the web. Stanford Technical Report, Stanford University, Palo Alto, CA.
  41. Prawesh S, Padmanabhan B (2012) Probabilistic news recommender systems with feedback. Proc. 6th ACM Conf. Recommender Sys- tems (RecSys'12) (ACM, New York), 257-260.
  42. Resnick P, Iacovou N, Suchak M, Bergstrom P, Riedl J (1994) Grouplens: An open architecture for collaborative filtering of netnews. Proc. 1994 ACM Conf. Comput. Supported Cooperative Work (CSCW'94) (ACM, New York), 175-186.
  43. Salton G, Wong A, Yang C (1975) A vector space model for automatic indexing. Commun. ACM 18(11):613-620.
  44. Sayyadi H, Getoor L (2009) Future rank: Ranking scientific articles by predicting their future pagerank. 2009 SIAM Internat. Conf. Data Mining (SDM'09) (SIAM, Philadelphia).
  45. Schloss Dagstuhl -Leibniz Center for Informatics and University of Trier (2017) DBLP Computer Science Bibliography. https:// dblp.uni-trier.de/.
  46. Sen P, Namata GM, Bilgic M, Getoor L, Gallagher B, Eliassi-Rad T (2008) Collective classification in network data. AI Magazine 29(3):93-106.
  47. Shi C, Li Y, Zhang J, Sun Y, Yu P (2017) A survey of heterogeneous information network analysis. IEEE Trans. Knowledge Data Engrg. 29(1):17-37.
  48. Spiliopoulou M, Faulstich LC (1999) WUM: A tool for web utilization analysis. The World Wide Web and Databases International Work- shop WebDB'98, Valencia, Spain, March 27-28, 1998. Selected Pa- pers, Lecture Notes in Computer Science, vol. 1590 (Springer, Berlin), 184-203.
  49. Sugiyama K, Hatano K, Yoshikawa M (2004) Adaptive web search based on user profile constructed without any effort from users. Proc. 13th Conf. World Wide Web (WWW '04) (ACM, New York), 675-684.
  50. Sun Y, Han J (2012a) Mining heterogeneous information networks: A structural analysis approach. SigKDD Explorations 14(2):20.
  51. Sun Y, Han J (2012b) Mining Heterogeneous Information Networks: Principles and Methodologies (Morgan & Claypool, San Rafael, CA), 1-159.
  52. Sun Y, Norick B, Yan JHX, Yu P, Yu X (2012) Integrating meta-path selection with user-guided object clustering in heteroge- neous information networks. Proc. 18th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York), 1348-1356.
  53. Sun Y, Yu Y, Han J (2009) Ranking-based clustering of heteroge- neous information networks with star network schema. Proc. 15th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York), 797-806.
  54. Symeonidis P (2016) Matrix and tensor decomposition in recom- mender systems. Proc. 10th ACM Conf. Recommender Systems (RecSys '16) (ACM, New York), 429-430.
  55. Taskar B, fai Wong M, Abbeel P, Koller D (2003) Link prediction in relational data. Thrun S, Saul LK, Sch ölkopf B, eds. Advances in Neural Information Processing Systems, vol. 16 (Morgan Kauffman, San Francisco).
  56. Teevan J, Dumais ST, Horvitz E (2005) Personalizing search via automated analysis of interests and activities. Proc. 28th Annual Internat. ACM SIGIR Conf. Res. Dev. Inform. Retrieval (SIGIR'05) (ACM, New York).
  57. Varadarajan R, Hristidis V, Raschid L (2008) Explaining and refor- mulating authority flow queries. IEEE 24th Internat. Conf. Data Engrg. (IEEE, Piscataway, NJ) 883-892.
  58. Xia F, Liu T, Wang J, Zhang W, Li H (2008) Listwise approach to learning to rank: Theory and algorithm. Internat. Conf. Machine Learn., J. Machine Learn. Res., 1192-1199.
  59. Yedidia J (2011) Message-passing algorithms for inference and op- timization. J. Statist. Phys. 145(4):860-890.
  60. Yu X, Ren X, Sun Y, Gu Q, Sturt B, Khandelwal U, Norick B, Han J (2014) Personalized entity recommendation: A heterogeneous information network approach. Proc. 7th ACM Conf. Web Search Data Mining (ACM, New York).
  61. Zeng X, Li Y, Leung S, Lin Z, Liu X (2016) Investment behavior prediction in heterogeneous information network. Neuro- computing 217:125-132.
  62. Zhao H, Yao Q, Li J, Song Y, Lee DL (2017) Meta-graph based rec- ommendation fusion over heterogeneous information networks. Proc. ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York).
  63. Zheng Z, Zha H, Zhang T, Chapelle O, Chen K, Sun G (2008) A general boosting method and its application to learning rank- ing functions for web search. Platt JC, Koller D, Singer Y, Roweis ST, eds. Advances in Neural Information Processing Systems, vol. 20 (Morgan Kauffman, San Francisco), 1697-1704.
  64. Zhou D, Orshanskiy SA, Zha H, Giles CL (2007) Co-ranking authors and documents in a heterogeneous network. 7th IEEE Internat. Conf. Data Mining (ICDM 2007) (IEEE, Piscataway, NJ).
  65. Raschid, Sayyadi, and Hristidis: Learning to Rank in Entity Relationship Graphs

Related papers

Efficient Ranking on Entity Graphs with Personalized Relationships
LansA Informatics Pvt Ltd

Authority flow techniques like PageRank and ObjectRank can provide personalized ranking of typed entity-relationship graphs.

View PDFchevron_right
A Multi-Entity Page Rank Algorithm
Kavi Mahesh

2017

We propose a generic multi-entity page rank algorithm for ranking a set of related entities of more than one type. The algorithm takes into account not only the mutual endorsements among entities of the same type but also the influences of other types of entities on the ranks of all entities involved. A key idea of our algorithm is the separation of prime and non-prime entities to structure the iterative evolution of the ranks and matrices involved. We illustrate the working of the proposed algorithm in the domain of concurrently ranking research papers, their authors and the affiliated universities.

View PDFchevron_right
Co-ranking Authors and Documents in a Heterogeneous Network
Computer Science Engineering SJCET

Seventh IEEE International Conference on Data Mining (ICDM 2007), 2007

The problem of evaluating scientific publications and their authors is important, and as such has attracted increasing attention. Recent graph-theoretic ranking approaches have demonstrated remarkable successes, but most of their applications are limited to homogeneous networks such as the network of citations between publications. This paper proposes a novel method for co-ranking authors and their publications using several networks: the social network connecting the authors, the citation network connecting the publications, as well as the authorship network that ties the previous two together. The new coranking framework is based on coupling two random walks, that separately rank authors and documents following the PageRank paradigm. As a result, improved rankings of documents and their authors depend on each other in a mutually reinforcing way, thus taking advantage of the additional information implicit in the heterogeneous network of authors and documents. The proposed ranking approach has been tested using data collected from CiteSeer, and demonstrates a great improvement in author ranking quality compared with ranking by the number of publications, the number of citations and the PageRank calculated in the authors' social network. This paper proposes a framework for co-ranking entities of different kinds in a heterogeneous network connect

View PDFchevron_right
An authority-flow based ranking approach to discover potential novel associations between Linked Data
Maria-Esther Vidal

Semantic Web, 2014

Under the umbrella of the Semantic Web, Linking Open Data projects have made available a large number of semantically intra-and interconnected links. As an example, in the biomedical domain, data about disorders, disease related genes and proteins, clinical trials, and drugs or interventions are accessible on the Linked Open Data cloud. In addition, domain ontologies have been used to annotate scientific data. For instance, publications in PubMed have been annotated using controlled vocabulary (CV) terms from ontologies such as the Medical Subject Header (MeSH) or the Unified Medical Language System (UMLS). These annotations have been successfully mined to discover associations between drugs and diseases using techniques that have been labeled as Literature-Based Discovery (LBD). Given the large scale of the linked datasets in the Linked Open Data cloud, there is a need to develop scalable techniques that can provide answers in close to real time, to explain a phenomena, to identify anomalies, or to explore a discovery. This paper describes an authority flow based ranking technique that is inspired by LBD methods. The ranking is tailored to a layered graph. The input terms are in the first layer and the ranking will efficiently identify and assign high scores to terms in a third (or subsequent) layer, corresponding to potential novel discoveries. The terms, links and scores are modeled as a Bayesian network. Two sampling techniques are proposed to only traverse the terms that may have high scores. The first technique implements a Direct Sampling reasoning algorithm to approximate the ranking scores of nodes in the Bayesian network; it visits only the nodes with the highest probability. The second technique samples paths in the Bayesian network with the highest conditional probability. An experimental study reveals that the proposed ranking techniques are able to reproduce state-of-the-art discoveries. In addition, the sampling-based approaches are able to reduce execution times and reach high levels of accuracy.

View PDFchevron_right
Link Prediction in a Modified Heterogeneous Bibliographic Network
Henry Adorna

2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2012

Researchers have discovered, in recent years, the advantages of modeling complex systems using heterogeneous information networks. These networks are comprised of heterogeneous sets of nodes and edges that better represent the different entities and relationships often found in the real world. Although heterogeneous networks provide a richer semantic view of the data, the added complexity makes it difficult to directly apply existing techniques that work well on homogeneous networks.

View PDFchevron_right

Related topics

  • Computer Science
  • Combinatorics
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved