[Crib-list] GrAPL'21 Call for Participation (please distribute)

Tue May 4 08:44:17 EDT 2021

  CALL FOR PARTICIPATION

*******************************************************************************

  IPDPS GrAPL 2021: Workshop on Graphs, Architectures, Programming, and
Learning
  https://hpc.pnl.gov/grapl/ [1]

  May 17th 2021
  8AM – 12:15PM PDT

  IMPORTANT: This year, GrAPL will hold two LIVE 2-hour Q&A sessions with
the authors of the accepted papers and invited talks according to the
current schedule below. Register at the IPDPS website
(http://www.ipdps.org [2]) to get instructions on how to access the
papers included in this program. In addition, links to 3-minute
lightning talks by the workshop speakers will be found at the GrAPL
website (https://hpc.pnl.gov/grapl/ [1]) during the week of May 10th.

TO ATTEND THE ZOOM SESSIONS, WE ASK PARTICIPANTS TO REGISTER IN ADVANCE
AT THE FOLLOWING LINK: https://tinyurl.com/GrAPL-2021-Registration [3]

The organizing committee will then provide the link to the zoom session.

******************************************************************************

  Program for May 17th:

  0800 – 0955 (PDT): Session 1

  Welcome message.

  HPC, GRAPHBLAS, TOOLS

  Keynote - Sparse Adjacency Matrices at the Core of Graph Databases:
GraphBLAS the Engine Behind RedisGraph Property Graph Database
  _Roi Lipman (Redis Labs)_

  LAGraph: Linear Algebra, Network Analysis Libraries, and the Study of
Graph Algorithms
  _Gábor Szárnyas (CWI Amsterdam), David A. Bader (New Jersey Institute
of Technology), Timothy A. Davis (Texas A&M), James Kitchen (Anaconda),
Timothy G. Mattson (Intel), Scott McMillan (SEI, Carnegie Mellon), Erik
Welch (Anaconda)_

  Introduction to GraphBLAS 2.0
  _Benjamin A. Brock (UC Berkeley), Aydın Buluç (LBNL, UC Berkeley),
Timothy G. Mattson (Intel), Scott McMillan (SEI, Carnegie Mellon), José
E. Moreira (IBM)_

  Mathematics of Digital Hyperspace
  _Jeremy Kepner (MIT Lincoln Laboratory), Timothy Davis (Texas A&M
University), Vijay Gadepally (MIT Lincoln Laboratory), Hayden Jananthan
(MIT Lincoln Laboratory, Vanderbilt), Lauren Milechin (MIT)_

  SPbLA: The Library of GPGPU-Powered Sparse Boolean Linear Algebra
Operations
  _Egor Orachev (St. Petersburg St. Univ., JetBrains Research), Maria
Karpenko (ITMO Univ.), Artem Khoroshev (BIOCAD), Semyon Grigorev (St.
Petersburg St. Univ, JetBrains Research)_

  PIGO: A Parallel Graph Input/Output Library
  _Kasimir Gabert (Georgia Tech), Ümit V. Çatalyürek (Georgia Tech)_

  1015 – 12155 (PDT): Session 2

  GRAPH MACHINE LEARNING, MODELS, AND APPLICATIONS
  _ _
  Keynote – Label Propagation and Graph Neural Networks
  _Austin Benson (Cornell University)_

  Hybrid Power-Law Models of Network Traffic
  Pat Devlin (Yale), Jeremy Kepner (MIT), Ashley Luo (MIT), Erin Meger
(Univ. du Québec à Montréal)

  Characterizing Job-Task Dependency in Cloud Workloads Using Graph
Learning
  _Zhaochen Gu (Univ. N. Texas), Sihai Tang (Univ. N. Texas), Beilei
Jiang (Univ. N. Texas), Song Huang (Allstate), Qiang Guan (Kent State),
Song Fu (Univ. N. Texas)_
  _ _
  Co-design of Advanced Architectures for Graph Analytics using Machine
Learning
  _Kuldeep Kurte (ORNL), Neena Imam (ORNL), Ramakrishnan Kannan (ORNL),
S. M. Shamimul Hasan (ORNL), Srikanth Yoginath (ORNL)_

  Sparse Binary Matrix-Vector Multiplication on Neuromorphic Computers
  _Catherine D. Schuman (ORNL), Bill Kay (ORNL), Prassana Date (ORNL),
Ramakrishnan Kannan (ORNL), Piyush Sao (ORNL), Thomas E. Potok (ORNL)_

******************************************************************************

  GrAPL is the result of the combination of two IPDPS workshops:
  GABB: Graph Algorithms Building Blocks
  GraML: Workshop on The Intersection of Graph Algorithms and Machine
Learning

  SUMMARY
  -------

  Data analytics is one of the fastest growing segments of computer
science. Many real-world analytic workloads are a mix of graph and
machine learning methods. Graphs play an important role in the synthesis
and analysis of relationships and organizational structures, furthering
the ability of machine-learning methods to identify signature features.
Given the difference in the parallel execution models of graph
algorithms and machine learning methods, current tools, runtime systems,
and architectures do not deliver consistently good performance across
data analysis workflows. In this workshop we are interested in graphs,
how their synthesis (representation) and analysis is supported in
hardware and software, and the ways graph algorithms interact with
machine learning to learn models and structured representations. The
workshop’s scope is broad and encompasses the wide range of methods
used in large-scale data analytics workflows.

  This workshop seeks papers on the theory, model-based analysis,
simulation, and analysis of operational data for graph analytics and
related machine learning applications. In particular, we are interested,
but not limited to the following topics:

  • Provide tractability and performance analysis in terms of
complexity, time-to-solution, problem size, and quality of solution for
systems that deal with mixed data analytics workflows;

  • Discuss the problem domains and problems addressable with graph
methods, machine learning methods, or both;

  • Discuss programming models and associated frameworks such as
Pregel, Galois, Boost, GraphBLAS, GraphChi, etc., for building large
multi-attributed graphs;

  • Discuss how frameworks for building graph algorithms interact with
those for building machine learning algorithms;

  • Discuss hardware platforms specialized for addressing large,
dynamic, multi-attributed graphs and associated machine learning;

  Besides regular papers, short papers (up to four pages) describing
work-in-progress or incomplete but sound, innovative ideas related to
the workshop theme are also encouraged.

  ORGANIZATION
  ------------

  General co-Chairs:

  Scott McMillan (CMU SEI), smcmillan at sei.cmu.edu
  Manoj Kumar (IBM), manoj1 at us.ibm.com

  Program Chairs:

  Nesreen K Ahmed, Intel Labs, nesreen.k.ahmed at intel.com

  GrAPL's Little Helpers:

  Tim Mattson (Intel Labs)
  Antonino Tumeo (PNNL)

  Program Committee:

  Paul Bogdan, University of Southern California , US
  Anu Bourgeois, Georgia State University , US
  Aydin Buluç, Lawrence Berkeley National Laboratory; University of
California, Berkeley, US
  Timothy Davis, Texas A&M University, US
  John Gilbert, University of California, Santa Barbara, US
  Sergio Gomez, Universitat Rovira i Virgili , ES
  Stratis Ioannidis, Northeastern University, US
  Kamesh Madduri, Pennsylvania State University, US
  Hesham Mostafa, Intel Labs, US
  Yuechao Pan, Google, US
  Robert Rallo, Pacific Northwest National Laboratory, US
  Indranil Roy, Natural Intelligence Systems, Inc. , US
  Ponnuswamy Sadayappan, University of Utah; Pacific Northwest National
Laboratory, US
  Shaden Smith, Microsoft Corporation, US
  Yizhou Sun, University of California, Los Angeles, US
  Ramachandran Vaidyanathan, Louisiana State University, US
  Alexander van der Grinten, Humboldt-University of Berlin, DE
  Flavio Vella, Free University of Bozen, IT

  Steering Committee:

  David A. Bader (New Jersey Institute of Technology)
  Aydın Buluç (LBNL)
  John Feo (PNNL)
  John Gilbert (UC Santa Barbara)
  Tim Mattson (Intel)
  Ananth Kalyanaraman (Washington State University)
  Jeremy Kepner (MIT Lincoln Laboratory)
  Antonino Tumeo (PNNL)

Links:
------
[1] https://hpc.pnl.gov/grapl/
[2] http://www.ipdps.org/
[3] https://tinyurl.com/GrAPL-2021-Registration