MapReduce 2014 - Algorithms for MapReduce and Beyond 2014

The workshop aims to explore algorithms and computational models for systems that need large scale parallelization and systems designed to support efficient parallelization and fault tolerance. These include specialized programming and data-management systems based on MapReduce and extensions, graph processing systems, data flow systems, and log processing systems.
The workshop will take place in Athens, Greece, in conjunction with EDBT/ICDT 2014, on March 28, 2014.
Topics of Interest
Cost Models for MapReduce and Extensions: Formal definition of models that evaluate the efficiency of algorithms in large scale parallel processing systems taking into account the requirements of such systems in different applications.
Scheduling of Tasks and Load-Balancing Techniques: Methods to tackle data skewness. Study of cases where automatic MapReduce data distribution does not provide sufficient data balancing. Design of algorithms that avoid skewness. Extensions of MapReduce that automatically tackle data skewness.
Tackling Iteration and Recursion : Techniques that deal with the inherent inadequacy of MapReduce when implementing iteration or recursion. Transformation of iterative algorithms to efficient MapReduce algorithms. Approaches that allow for efficient recursive computation in MapReduce without losing the blocking property. Extensions of MapReduce that support iteration.
Systems Similar to MapReduce: Use of MapReduce properties and techniques to solve problems in similar settings like graph processing, data flow, and log processing systems. Extensions of MapReduce with more fundamental functions other than Map and Reduce and more complex data flow connections between function inputs and outputs.