Exclusive feature bundling
Exclusive feature bundling is a tree-learning optimization that groups sparse, mutually exclusive features to reduce the effective feature dimensionality.
Ensemble Methods for Machine Learning
Feature bundling is a tree-learning optimization that groups compatible features to reduce the effective number of features processed.
- How it is used
- Speeds LightGBM training when high-dimensional data makes tree-split search and histogram construction expensive.
- How deep it goes
- Defines feature bundling’s purpose and contrast with GOSS but stops short of detailing the bundling algorithm or implementation.
- Examples
- Uses LightGBM, available for Python and R, as the concrete tooling context for applying EFB.
- What you can do after
- Evaluate how LightGBM reduces feature-processing costs through EFB when scaling gradient-boosting training.
Read how Ensemble Methods for Machine Learning explains exclusive feature bundling →
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
Exclusive feature bundling is a feature-dimensionality-reduction technique that groups sparse, mutually exclusive features while preserving their nonzero information.
- How it is used
- Reduces sparse feature dimensionality to accelerate LightGBM computations while retaining nonzero information.
- How deep it goes
- Explains sparse encoding, two-feature bundling, and greedy approximation, but does not detail the complete algorithm.
- Examples
- Uses two sparse features, A and B, to demonstrate separated value ranges after bundling.
- What you can do after
- Apply it via LightGBM to reduce sparse feature columns without discarding nonzero signals.
Related concepts
- LightGBMused by · LightGBM is an open-source gradient-boosting framework for efficiently training tree-based machine-learning models.
- one-hot encodingcontrasts with · One-hot encoding represents each category as a binary vector or set of indicators with exactly one active component identifying that category.
- dimensionality reductionimplements · Dimensionality reduction is the transformation of data into a representation with fewer dimensions while retaining selected information, structure, or relationships.
- greedy algorithmimplemented by · A greedy algorithm builds a solution incrementally by choosing the locally best available option at each step, without generally accounting for all future consequences or revising prior choices.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.