Struc2Vec Walk

Overview

The Struc2Vec Walk is a biased random walk and serves as a key component of the Struc2Vec framework. Unlike traditional random walks, it operates on a constructed multi-layer weighted graph instead of the original graph. For more details, please refer to the Struc2Vec algorithm.

Example Graph

Run the following statements on an empty graph to define its structure and insert data:

GQLUQL
INSERT (A:default {_id: "A"}),
       (B:default {_id: "B"}),
       (C:default {_id: "C"}),
       (D:default {_id: "D"}),
       (E:default {_id: "E"}),
       (F:default {_id: "F"}),
       (G:default {_id: "G"}),
       (H:default {_id: "H"}),
       (I:default {_id: "I"}),
       (J:default {_id: "J"}),
       (A)-[:default]->(B),
       (A)-[:default]->(C),
       (D)-[:default]->(C),
       (D)-[:default]->(F),
       (E)-[:default]->(C),
       (E)-[:default]->(F),
       (F)-[:default]->(G),
       (G)-[:default]->(J),
       (H)-[:default]->(G),
       (H)-[:default]->(I);

Creating HDC Graph

To load the entire graph to the HDC server hdc-server-1 as my_hdc_graph:

GQLUQL
CREATE HDC GRAPH my_hdc_graph ON "hdc-server-1" OPTIONS {
  nodes: {"*": ["*"]},
  edges: {"*": ["*"]},
  direction: "undirected",
  load_id: true,
  update: "static"
}

Parameters

Algorithm name: random_walk_struc2vec

File Writeback

UQL
algo(random_walk_struc2vec).params({
  projection: "my_hdc_graph",
  return_id_uuid: "id",
  walk_length: 5,
  walk_num: 1,
  k: 4,
  stay_probability: 0.8
}).write({
  file:{
    filename: 'walks'
}})

Result:

File: walks
_ids
J,G,F,E,C,
D,F,E,F,E,
F,G,F,
H,I,H,F,
B,A,B,A,B,
A,C,E,D,
E,F,G,H,G,
C,D,F,G,
I,H,G,F,E,
G,D,F,

Full Return

UQL
exec{
  algo(random_walk_struc2vec).params({
    return_id_uuid: "id",
    ids: ['J'],
    walk_length: 6,
    walk_num: 3,
    k: 4,
    stay_probability: 0.8
  }) as walks
  return walks
} on my_hdc_graph

Result:

Stream Return

UQL
exec{
  algo(random_walk_struc2vec).params({
    return_id_uuid: "id",
    ids: ['J'],
    walk_length: 6,
    walk_num: 3,
    k: 5,
    stay_probability: 0.7
  }).stream() as walks
  return walks
} on my_hdc_graph

Result: