LightGBM on Apache Spark
LightGBM is an open-source, distributed, high-performance gradient boosting (GBDT, GBRT, GBM, or MART) framework. This framework specializes in creating high-quality and GPU enabled decision tree algorithms for ranking, classification, and many other machine learning tasks. LightGBM is part of Microsoft's DMTK project.
Advantages of LightGBM
- Composability: LightGBM models can be incorporated into existing SparkML Pipelines, and used for batch, streaming, and serving workloads.
- Performance: LightGBM on Spark is 10-30% faster than SparkML on the Higgs dataset, and achieves a 15% increase in AUC. Parallel experiments have verified that LightGBM can achieve a linear speed-up by using multiple machines for training in specific settings.
- Functionality: LightGBM offers a wide array of tunable parameters, that one can use to customize their decision tree system. LightGBM on Spark also supports new types of problems such as quantile regression.
- Cross platform LightGBM on Spark is available on Spark, PySpark, and SparklyR
In PySpark, you can run the
from synapse.ml.lightgbm import LightGBMClassifier
model = LightGBMClassifier(learningRate=0.3,
Similarly, you can run the
LightGBMRegressor by setting the
from synapse.ml.lightgbm import LightGBMRegressor
model = LightGBMRegressor(application='quantile',
For an end to end application, check out the LightGBM notebook example.
LightGBM on Spark uses the Simple Wrapper and Interface Generator (SWIG) to add Java support for LightGBM. These Java Binding use the Java Native Interface call into the distributed C++ API.
We initialize LightGBM by calling
with the Spark executors within a MapPartitions call. We then pass each
workers partitions into LightGBM to create the in-memory distributed
dataset for LightGBM. We can then train LightGBM to produce a model
that can then be used for inference.
LightGBMRegressor use the SparkML API,
inherit from the same base classes, integrate with SparkML pipelines,
and can be tuned with SparkML's cross
Models built can be saved as SparkML pipeline with native LightGBM model
saveNativeModel(). Additionally, they're fully compatible with PMML and
can be converted to PMML format through the
Barrier Execution Mode
By default LightGBM uses regular spark paradigm for launching tasks and communicates with the driver to coordinate task execution.
The driver thread aggregates all task host:port information and then communicates the full list back to the workers in order for NetworkInit to be called.
This procedure requires the driver to know how many tasks there are, and a mismatch between the expected number of tasks and the actual number will cause the initialization to deadlock.
To avoid this issue, use the
UseBarrierExecutionMode flag, to use Apache Spark's
barrier() stage to ensure all tasks execute at the same time.
Barrier execution mode simplifies the logic to aggregate
host:port information across all tasks.
To use it in scala, you can call setUseBarrierExecutionMode(true), for example:
val lgbm = new LightGBMClassifier()