Neptune ML limits - Amazon Neptune
SageMaker limits
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China.

Neptune ML limits

  • Inference queries are only supported currently using the Gremlin query language.

  • The types of inference currently supported are node classification, node regression, edge classification, edge regression and link prediction (see Neptune ML capabilities).

  • The maximum graph size that Neptune ML can support depends on the amount of memory and storage required during data preparation, model training, and inference.

    • The maximum size of memory of a SageMaker data-processing instance is 768 GB. As a result, the data-processing stage fails if it needs more than 768 GB of memory.

    • The maximum size of memory of a SageMaker training instance is 732 GB. As a result, the training stage fails if it needs more than 732 GB of memory.

  • Neptune ML is currently available only in Regions where Neptune and the other services it depends on (such as Amazon Lambda, Amazon API Gateway and Amazon SageMaker) are all supported.

    There are differences in China (Beijing) and China (Ningxia) having to do with the default use of IAM authentication, as is explained here along with other differences.

  • The inference endpoints launched by Neptune ML currently can only return predictions for nodes that were present in the graph during training. For property graph models, you can update the inference endpoint to provide predictions for new nodes by following the incremental data inference workflow or the retraining workflow with the new data.

    For each supported task, the following nodes can appear in inference queries:

    • For vertex-property prediction (node classification or node regression), all vertices used in the queries must be available in the original graph, but the property to be predicted does not need to exist on all vertices.

    • For edge-property prediction (edge classification or edge regression), all incident vertices on the edges used in the queries must be available in the original graph, but the edge property to be predicted does not need to exist on all edges.

    • For link prediction (source or target vertex prediction), all vertices and edge types used in the queries must be available during training. Predictions for new edge types or vertices cannot be made.

  • The KGE models supported by Neptune ML only work for link prediction tasks, and the representations are specific to vertices and edge types present in the graph during training. This means that all vertices and edge types referred to in an inference query must have been present in the graph during training. Predictions for new edge types or vertices cannot be made without retraining the model.

SageMaker resource limitations

Depending on your activities and resource usage over time, you may encounter error messages saying that you've exceeded your quota (ResourceLimitExceeded). and you need to scale up your SageMaker resources, follow the steps in the Request a service quota increase for SageMaker resources procedure on this page to request a quota increase from Amazon Support.

SageMaker resource names correspond to Neptune ML stages as follows:

  • The SageMaker ProcessingJob is used by Neptune data processing, model training, and model transform jobs.

  • The SageMaker HyperParameterTuningJob is used by Neptune model training jobs.

  • The SageMaker TrainingJob is used by Neptune model training jobs.

  • The SageMaker Endpoint is used by Neptune inference endpoints.