Stacked Ensembles

Introduction

Ensemble machine learning methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms. Many of the popular modern machine learning algorithms are actually ensembles. For example, Random Forest and Gradient Boosting Machine (GBM) are both ensemble learners. Both bagging (e.g. Random Forest) and boosting (e.g. GBM) are methods for ensembling that take a collection of weak learners (e.g. decision tree) and form a single, strong learner.

H2O’s Stacked Ensemble method is supervised ensemble machine learning algorithm that finds the optimal combination of a collection of prediction algorithms using a process called stacking. This method currently supports regression and binary classification, and multiclass support is planned for a future release.

Native support for ensembles of H2O algorithms was added into core H2O in version 3.10.3.1. A separate implementation, the h2oEnsemble R package, is also still available, however for new projects we recommend using the native H2O version, documented below.

Stacking / Super Learning

Stacking, also called Super Learning or Stacked Regression, is a class of algorithms that involves training a second-level “metalearner” to find the optimal combination of the base learners. Unlike bagging and boosting, the goal in stacking is to ensemble strong, diverse sets of learners together.

Although the concept of stacking was originally developed in 1992, the theoretical guarantees for stacking were not proven until the publication of a paper titled, “Super Learner”, in 2007. In this paper, it was shown that the Super Learner ensemble represents an asymptotically optimal system for learning.

There are some ensemble methods that are broadly labeled as stacking, however, the Super Learner ensemble is distinguished by the use of cross-validation to form what is called the “level-one” data, or the data that the metalearning or “combiner” algorithm is trained on. More detail about the Super Learner algorithm is provided below.

Super Learner Algorithm

The steps below describe the individual tasks involved in training and testing a Super Learner ensemble. H2O automates most of the steps below so that you can quickly and easily build ensembles of H2O models.

  1. Set up the ensemble.
    1. Specify a list of L base algorithms (with a specific set of model parameters).
    2. Specify a metalearning algorithm.
  2. Train the ensemble.
    1. Train each of the L base algorithms on the training set.
    2. Perform k-fold cross-validation on each of these learners and collect the cross-validated predicted values from each of the L algorithms.
    3. The N cross-validated predicted values from each of the L algorithms can be combined to form a new N x L matrix. This matrix, along wtih the original response vector, is called the “level-one” data. (N = number of rows in the training set.)
    4. Train the metalearning algorithm on the level-one data. The “ensemble model” consists of the L base learning models and the metalearning model, which can then be used to generate predictions on a test set.
  3. Predict on new data.
    1. To generate ensemble predictions, first generate predictions from the base learners.
    2. Feed those predictions into the metalearner to generate the ensemble prediction.

Defining an H2O Stacked Ensemble Model

  • model_id: Specify a custom name for the model to use as a reference. By default, H2O automatically generates a destination key.
  • training_frame: Specify the dataset used to build the model.
  • validation_frame: Specify the dataset used to evaluate the accuracy of the model.
  • selection_strategy: Specify the strategy for choosing which models to stack. Note that choose_all is currently the only selection strategy implemented.
  • base_models: Specify a list of model IDs that can be stacked together. Models must have been cross-validated using nfolds > 1, they all must use the same cross-validation folds and keep_cross_validation_folds must be set to True.

Regarding the base models: One way to guarantee identical folds across base models is to set fold_assignment = “Modulo” in all the base models. Currently, using base models that were all trained with fold_assignment = “Modulo” is a strict requirement, but this will be relaxed in the next release to allow for identical user-specified folds or random folds that were generated with the same seed.

Also in a future release, there will be an additional metalearner parameter which allows for the user to specify the metalearning algorithm used. Currently, the metalearner is fixed as a default H2O GLM with non-negative weights.

You can follow the progress of H2O’s Stacked Ensemble development here.

Example

  • r
  • python
library(h2o)
h2o.init(nthreads = -1)

# Import a sample binary outcome train/test set into H2O
train <- h2o.importFile("https://s3.amazonaws.com/erin-data/higgs/higgs_train_10k.csv")
test <- h2o.importFile("https://s3.amazonaws.com/erin-data/higgs/higgs_test_5k.csv")

# Identify predictors and response
y <- "response"
x <- setdiff(names(train), y)

# For binary classification, response should be a factor
train[,y] <- as.factor(train[,y])
test[,y] <- as.factor(test[,y])

# Number of CV folds (to generate level-one data for stacking)
nfolds <- 5



# There are a few ways to assemble a list of models to stack toegether:
# 1. Train individual models and put them in a list
# 2. Train a grid of models
# 3. Train several grids of models
# Note: All base models must have the same cross-validation folds and
# the cross-validated predicted values must be kept.



# 1. Generate a 2-model ensemble (GBM + RF)

# Train & Cross-validate a GBM
my_gbm <- h2o.gbm(x = x,
                  y = y,
                  training_frame = train,
                  distribution = "bernoulli",
                  ntrees = 10,
                  max_depth = 3,
                  min_rows = 2,
                  learn_rate = 0.2,
                  nfolds = nfolds,
                  fold_assignment = "Modulo",
                  keep_cross_validation_predictions = TRUE,
                  seed = 1)

# Train & Cross-validate a RF
my_rf <- h2o.randomForest(x = x,
                          y = y,
                          training_frame = train,
                          ntrees = 50,
                          nfolds = nfolds,
                          fold_assignment = "Modulo",
                          keep_cross_validation_predictions = TRUE,
                          seed = 1)

# Train a stacked ensemble using the GBM and RF above
ensemble <- h2o.stackedEnsemble(x = x,
                                y = y,
                                training_frame = train,
                                model_id = "my_ensemble_binomial",
                                base_models = list(my_gbm@model_id, my_rf@model_id))

# Eval ensemble performance on a test set
perf <- h2o.performance(ensemble, newdata = test)

# Compare to base learner performance on the test set
perf_gbm_test <- h2o.performance(my_gbm, newdata = test)
perf_rf_test <- h2o.performance(my_rf, newdata = test)
baselearner_best_auc_test <- max(h2o.auc(perf_gbm_test), h2o.auc(perf_rf_test))
ensemble_auc_test <- h2o.auc(perf)
print(sprintf("Best Base-learner Test AUC:  %s", baselearner_best_auc_test))
print(sprintf("Ensemble Test AUC:  %s", ensemble_auc_test))

# Generate predictions on a test set (if neccessary)
pred <- h2o.predict(ensemble, newdata = test)



# 2. Generate a random grid of models and stack them together

# GBM Hyperparamters
learn_rate_opt <- c(0.01, 0.03)
max_depth_opt <- c(3, 4, 5, 6, 9)
sample_rate_opt <- c(0.7, 0.8, 0.9, 1.0)
col_sample_rate_opt <- c(0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8)
hyper_params <- list(learn_rate = learn_rate_opt,
                     max_depth = max_depth_opt,
                     sample_rate = sample_rate_opt,
                     col_sample_rate = col_sample_rate_opt)

search_criteria <- list(strategy = "RandomDiscrete",
                        max_models = 3,
                        seed = 1)

gbm_grid <- h2o.grid(algorithm = "gbm",
                     grid_id = "gbm_grid_binomial",
                     x = x,
                     y = y,
                     training_frame = train,
                     ntrees = 10,
                     seed = 1,
                     nfolds = nfolds,
                     fold_assignment = "Modulo",
                     keep_cross_validation_predictions = TRUE,
                     hyper_params = hyper_params,
                     search_criteria = search_criteria)

# Train a stacked ensemble using the GBM grid
ensemble <- h2o.stackedEnsemble(x = x,
                                y = y,
                                training_frame = train,
                                model_id = "ensemble_gbm_grid_binomial",
                                base_models = gbm_grid@model_ids)

# Eval ensemble performance on a test set
perf <- h2o.performance(ensemble, newdata = test)

# Compare to base learner performance on the test set
.getauc <- function(mm) h2o.auc(h2o.performance(h2o.getModel(mm), newdata = test))
baselearner_aucs <- sapply(gbm_grid@model_ids, .getauc)
baselearner_best_auc_test <- max(baselearner_aucs)
ensemble_auc_test <- h2o.auc(perf)
print(sprintf("Best Base-learner Test AUC:  %s", baselearner_best_auc_test))
print(sprintf("Ensemble Test AUC:  %s", ensemble_auc_test))

# Generate predictions on a test set (if neccessary)
pred <- h2o.predict(ensemble, newdata = test)

FAQ

  • How do I save ensemble models?
Currently, there is no support for saving ensembles, but this will be addressed in the next release. Binary save/load as as well as MOJO support is planned for Stacked Ensemble models. (More accurately, you can currently save an ensemble as a binary model, but there may be issues when loading it back in.)
  • Will an stacked ensemble always perform better than a single model?
Hopefully, but it’s not always the case. That’s why it always a good idea to check the performance of your stacked ensemble and compare it against the performance of the individual base learners.
  • How do I improve the performance of an ensemble?
If you find that your ensemble is not performing better than the best base learner, then you can try a few different things. First, look to see if there are base learners that are performing much worse than the other base learners (for example, a GLM). If so, remove them from the ensemble and try again. Second, you can try adding more models to the ensemble, especially models that add diversity to your set of base models. Once custom metalearner support is added, you can try out different metalearners as well.
  • How does the algorithm handle missing values during training?
This is handled by the base algorithms of the ensemble. See the documentation for those algorithms to find out more information.
  • How does the algorithm handle missing values during testing?
This is handled by the base algorithms of the ensemble. See the documentation for those algorithms to find out more information.
  • What happens if the response has missing values?
No errors will occur, but nothing will be learned from rows containing missing values in the response column.
  • What happens when you try to predict on a categorical level not seen during training?
This is handled by the base algorithms of the ensemble. See the documentation for those algorithms to find out more information.
  • How does the algorithm handle highly imbalanced data in a response column?
In the base learners, specify balance_classes, class_sampling_factors and max_after_balance_size to control over/under-sampling.

Additional Information