Class: NodeEmbeddingsParams

Node embeddings parameters.

URI: https://w3id.org/neat-ml/:NodeEmbeddingsParams

Slots

Name	Range	Cardinality	Description	Info
method_name	NodeEmbedMethodEnum	0..1	Name of the node embedding method.	.
walk_length	integer	0..1	Maximal length of the walks.	.
batch_size	integer	0..1	Number of nodes to include in a single batch.	.
window_size	integer	0..1	Size of the context and target nodes for node2vec.	.
return_weight	float	0..1	Weight on the probability of returning to the same node the walk just came from Having this higher tends the walks to be more like a Breadth-First Search. Having this very high (> 2) makes search very local. Equal to the inverse of p in the Node2Vec paper.	.
explore_weight	float	0..1	Weight on the probability of visiting a neighbor node to the one we're coming from in the random walk Having this higher tends the walks to be more like a Depth-First Search. Having this very high makes search more outward. Having this very low makes search very local. Equal to the inverse of q in the Node2Vec paper.	.
iterations	integer	0..1	Number of iterations.	.

Usages

used by	used in	type	used
EmbeddingsConfig	node_embeddings_params	range	NodeEmbeddingsParams

Identifier and Mapping Information

LinkML Specification

Direct

name: NodeEmbeddingsParams
description: Node embeddings parameters.
from_schema: https://w3id.org/neat-ml
attributes:
  method_name:
    name: method_name
    description: Name of the node embedding method.
    from_schema: https://w3id.org/neat-ml
    range: node_embed_method_enum
  walk_length:
    name: walk_length
    description: Maximal length of the walks.
    from_schema: https://w3id.org/neat-ml
    range: integer
  batch_size:
    name: batch_size
    description: Number of nodes to include in a single batch.
    from_schema: https://w3id.org/neat-ml
    range: integer
  window_size:
    name: window_size
    description: Size of the context and target nodes for node2vec.
    from_schema: https://w3id.org/neat-ml
    range: integer
  return_weight:
    name: return_weight
    description: Weight on the probability of returning to the same node the walk
      just came from Having this higher tends the walks to be more like a Breadth-First
      Search. Having this very high  (> 2) makes search very local. Equal to the inverse
      of p in the Node2Vec paper.
    from_schema: https://w3id.org/neat-ml
    range: float
  explore_weight:
    name: explore_weight
    description: Weight on the probability of visiting a neighbor node to the one
      we're coming from in the random walk Having this higher tends the walks to be
      more like a Depth-First Search. Having this very high makes search more outward.
      Having this very low makes search very local. Equal to the inverse of q in the
      Node2Vec paper.
    from_schema: https://w3id.org/neat-ml
    range: float
  iterations:
    name: iterations
    description: Number of iterations.
    from_schema: https://w3id.org/neat-ml
    range: integer

Induced

name: NodeEmbeddingsParams
description: Node embeddings parameters.
from_schema: https://w3id.org/neat-ml
attributes:
  method_name:
    name: method_name
    description: Name of the node embedding method.
    from_schema: https://w3id.org/neat-ml
    alias: method_name
    owner: NodeEmbeddingsParams
    range: node_embed_method_enum
  walk_length:
    name: walk_length
    description: Maximal length of the walks.
    from_schema: https://w3id.org/neat-ml
    alias: walk_length
    owner: NodeEmbeddingsParams
    range: integer
  batch_size:
    name: batch_size
    description: Number of nodes to include in a single batch.
    from_schema: https://w3id.org/neat-ml
    alias: batch_size
    owner: NodeEmbeddingsParams
    range: integer
  window_size:
    name: window_size
    description: Size of the context and target nodes for node2vec.
    from_schema: https://w3id.org/neat-ml
    alias: window_size
    owner: NodeEmbeddingsParams
    range: integer
  return_weight:
    name: return_weight
    description: Weight on the probability of returning to the same node the walk
      just came from Having this higher tends the walks to be more like a Breadth-First
      Search. Having this very high  (> 2) makes search very local. Equal to the inverse
      of p in the Node2Vec paper.
    from_schema: https://w3id.org/neat-ml
    alias: return_weight
    owner: NodeEmbeddingsParams
    range: float
  explore_weight:
    name: explore_weight
    description: Weight on the probability of visiting a neighbor node to the one
      we're coming from in the random walk Having this higher tends the walks to be
      more like a Depth-First Search. Having this very high makes search more outward.
      Having this very low makes search very local. Equal to the inverse of q in the
      Node2Vec paper.
    from_schema: https://w3id.org/neat-ml
    alias: explore_weight
    owner: NodeEmbeddingsParams
    range: float
  iterations:
    name: iterations
    description: Number of iterations.
    from_schema: https://w3id.org/neat-ml
    alias: iterations
    owner: NodeEmbeddingsParams
    range: integer