skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: PathMining: A Path-based User Profiling Algorithm for Heterogeneous Graph-based Recommender Systems

 [1];  [2];  [3]
  1. (Matt) [ORNL
  2. University of Tennessee, Knoxville (UTK)
  3. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: The 28th International FLAIRS Conference, Hollywood City, FL, USA, 20150518, 20150520
Country of Publication:
United States

Citation Formats

Lee, Sangkeun, Lee, Sanghyeb, and Park, Byung H. PathMining: A Path-based User Profiling Algorithm for Heterogeneous Graph-based Recommender Systems. United States: N. p., 2015. Web.
Lee, Sangkeun, Lee, Sanghyeb, & Park, Byung H. PathMining: A Path-based User Profiling Algorithm for Heterogeneous Graph-based Recommender Systems. United States.
Lee, Sangkeun, Lee, Sanghyeb, and Park, Byung H. 2015. "PathMining: A Path-based User Profiling Algorithm for Heterogeneous Graph-based Recommender Systems". United States. doi:.
title = {PathMining: A Path-based User Profiling Algorithm for Heterogeneous Graph-based Recommender Systems},
author = {Lee, Sangkeun and Lee, Sanghyeb and Park, Byung H},
abstractNote = {},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2015,
month = 1

Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • Heterogeneous graph-based recommendation frameworks have flexibility in that they can incorporate various recommendation algorithms and various kinds of information to produce better results. In this demonstration, we present a heterogeneous graph-based recommendation simulator which enables participants to experience the flexibility of a heterogeneous graph-based recommendation method. With our system, participants can simulate various recommendation semantics by expressing the semantics via meaningful paths like User Movie User Movie. The simulator then returns the recommendation results on the fly based on the user-customized semantics using a fast Monte Carlo algorithm.
  • A 2-D and 3-D path planning algorithm for robot navigation and manipulation is developed in this paper. This method is of particular interest for robotic systems which require both 2-D navigation to reach the work site and 3-D path planning for on-site manipulation and inspection. This study extends the approach of 2-D path planning to 3-D with minimum effort. The quadtree and octree structures are used for 2-D and 3-D workspace representation, respectively. Quadtrees and octrees are generated from brightness image of the workspace obtained using a camera mounted on a robot. Path generation is based on the A* algorithm.more » The spatial length and the clearance space available for the robot are used as constraints in the path generation. The results of this approach are illustrated through an experimental system setup on a robotic workstation. 12 refs., 11 figs.« less
  • Recent work on real-world graph analytics has sought to leverage the massive amount of parallelism offered by GPU devices, but challenges remain due to the inherent irregularity of graph algorithms and limitations in GPU-resident memory for storing large graphs. We present GraphReduce, a highly efficient and scalable GPU-based framework that operates on graphs that exceed the device’s internal memory capacity. GraphReduce adopts a combination of both edge- and vertex-centric implementations of the Gather-Apply-Scatter programming model and operates on multiple asynchronous GPU streams to fully exploit the high degrees of parallelism in GPUs with efficient graph data movement between the hostmore » and the device.« less
  • The spectral bisection algorithm bisects a graph into equally-sized parts in such a way that only a near minimal number of edges is cut. It requires the calculation of the Fiedler vector of the graph, i.e. the eigenvector that corresponds to the second smallest eigenvalue of the Laplacian matrix. Traditionally, a Lanczos algorithm is used for this purpose. Barnard and Simon have proposed calculating the Fiedler vector with a multilevel algorithm. This requires the construction of a series of consecutively smaller contractions of the graph. In this paper, we present a powerful graph contraction algorithm. We will show that themore » Fiedler vector of a contracted graph is a very good approximation of the Fiedler vector of the original graph and that the resulting multilevel algorithm calculates the Fiedler vector in less time than a Lanczos algorithm.« less
  • A description is given of the COMEX (compact knowledge based expert system) expert system language for application-domain users who want to develop a knowledge-based expert system by themselves. The COMEX system was written in FORTRAN and works on a microcomputer. COMEX is being used in several application domains such as medicine, education, and industry. 7 references.