Python in Science Conference (SciPy)
Published July 10, 2025 | Version v1
Presentation Open

GBNet: XGBoost and LightGBM PyTorch Modules

Authors/Creators

  • 1. AlixPartners

Contributors

  • 1. SLB
  • 2. Lawrence Berkeley National Laboratory
  • 3. Aptos
  • 4. Curvenote
  • 5. Arm
  • 6. Deloitte
  • 7. University of Alabama in Huntsville

Description

GBNet is a Python package that integrates XGBoost and LightGBM with PyTorch. By leveraging PyTorch auto-differentiation, GBNet enables novel architectures for GBMs that were previously exclusive to pure Neural Networks. The result is a greatly expanded set of applications for GBMs and an improved ability to interpret expressive architectures due to the use of GBMs.

Files

GBNet.pdf

Files (1.6 MB)

Name Size Download all
md5:ec76cae696dfb1d755c09b4c12fdad30
1.6 MB Preview Download