Class meeting for 10-405 Graph Architectures for ML
From Cohen Courses
Jump to navigationJump to search
This is one of the class meetings on the schedule for the course Machine Learning with Large Datasets 10-405 in Spring 2018.
Slides
- Slides in powerpoint, in pdf
Quiz
Readings
- Philip Stutz, Abraham Bernstein and William W. Cohen (2010): Signal/Collect: Graph Processing Large Graphs In Seconds in ISWC-2010.
Things to Remember and/or Think About
- Differences and commonalities between the graph-processing methods discussed: Pregel, Signal-Collect, GraphX, and GraphChi.
- How graph-processing approaches could be used for ML problems that will be studied in class, like SSL, PIC, and LDA.
- How operations on graphs can be implemented in dataflow languages.
