[SPARK-50120] SALSA graph ranking algoritm upstreaming

• Type: Brainstorming
• Status: Open
• Priority: Minor
• Resolution: Unresolved
• Affects Version/s: 3.1.2
• Component/s: GraphX
• Assignee: Unassigned
• Reporter: Câju Mihai-Drosi
• Created: 25/Oct/24 14:12
• Updated: 25/Oct/24 14:12

Description

Greetings,

A while back in 2021 as part of an MRes project I wrote several variations of the SALSA graph ranking algorithm for Apache Spark. I would like to know if there is any interest in upstreaming one of these versions in Apache Spark. I wrote some code to benchmark the performance and scalability of these variations. The code is available here:
https://github.com/CajuM/DA/blob/salsa2/src/main/scala/PageRankBench/App.scala

The benchmark is available here:
https://www.overleaf.com/read/yvhtkfqpcsbn#93e386