Kumo.ai home page
Search...
⌘K
Ask AI
Community
Contact Support
Start for free
Start for free
Search...
Navigation
GNN
channels
Guide
Examples
Reference
FAQ
Releases
Predictive Query
Overview
Primary Commands
Aggregation Operators
Boolean Operators
Model Plan
Column Processing
Model Architecture
GNN
GNN architecture
aggregation
channels
Graph Transformers
Selecting Link Prediction Model Architectures on Kumo
activation
distance_measure
handle_new_target_entities
module
normalization
num_post_message_passing_layers
num_pre_message_passing_layers
ranking_embedding_loss_coeff
output_embedding_dim
prediction_time_encodings
target_embedding_mode
use_seq_id
Neighbor Sampling
Optimization
Training Job Plan
Training Table Generation
SDK
SDK Reference
On this page
channels: <list[int]> (Optional)
Description
Supported Task Types
Default Values
GNN
channels
channels: <list[int]>
(Optional)
Description
A list of dimension of layers in the graph neural network model for AutoML to explore.
channels
must be an even number between
>= 2
and
<= 1024
.
Supported Task Types
All
Default Values
run_mode
Default Value
FAST
[64, 128, 256]
NORMAL
[64, 128, 256]
BEST
[64, 128, 256]
aggregation
Graph Transformer architecture
Assistant
Responses are generated using AI and may contain mistakes.