search

neo4j-graph-analytics / ml-models

Machine Learning Procedures and Functions for Neo4j
https://github.com/neo4j-graph-analytics/ml-models/releases/tag/1.0.0
Apache License 2.0
64 stars 23 forks source link

DeepGL OOM #6

Open tomasonjo opened 5 years ago

tomasonjo commented 5 years ago

running on machine with 16gb RAM and using dataset with 8k nodes and 26k rels : https://snap.stanford.edu/data/p2p-Gnutella09.html

import:

LOAD CSV FROM
"file:///p2p-Gnutella09.txt" as row fieldterminator ' '
WITH row SKIP 4
MERGE (h1:Host{id:row[0]})
MERGE (h2:Host{id:row[1]})
MERGE (h1)-[:CONNECTION]->(h2)

Run algo:

CALL embedding.deepgl("Host","CONNECTION", {
iterations: 4,
writePropery:'fourth'
})

Error:

Neo.ClientError.Procedure.ProcedureCallFailed: Failed to invoke procedure embedding.deepgl: Caused by: java.lang.OutOfMemoryError: Physical memory usage is too high: physicalBytes = 7G > maxPhysicalBytes = 7G

Tomposon commented 5 years ago

Where do you get the usage comment of neo4j DeepGL?I cannot find any document for me to run command @tomasonjo

tomasonjo commented 5 years ago

check https://towardsdatascience.com/deepgl-on-neo4j-b27e8c64190f

Tomposon commented 5 years ago

Could you send me a file such as pdf?I can't visit the website given by you @tomasonjo

jameswweis commented 5 years ago

@Tomposon The signature is 

CALL embedding.deepgl("NodeLabel" ,"RelationshipType", {
  nodeFeatures: [string]
  pruningLambda: double,
  diffusions: integer, 
  iterations: integer,
  writeProperty: string
})