{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multi-layered-gradient-boosting-decision","title":"Multi-Layered Gradient Boosting Decision Trees","arxiv_id":"1806.00007","date":"2018-05-31","proceeding":"NeurIPS 2018 12","authors":["Ji Feng","Yang Yu","Zhi-Hua Zhou"],"abstract":"Multi-layered representation is believed to be the key ingredient of deep\nneural networks especially in cognitive tasks like computer vision. While\nnon-differentiable models such as gradient boosting decision trees (GBDTs) are\nthe dominant methods for modeling discrete or tabular data, they are hard to\nincorporate with such representation learning ability. In this work, we propose\nthe multi-layered GBDT forest (mGBDTs), with an explicit emphasis on exploring\nthe ability to learn hierarchical representations by stacking several layers of\nregression GBDTs as its building block. The model can be jointly trained by a\nvariant of target propagation across layers, without the need to derive\nback-propagation nor differentiability. Experiments and visualizations\nconfirmed the effectiveness of the model in terms of performance and\nrepresentation learning ability.","url_abs":"http://arxiv.org/abs/1806.00007v1","url_pdf":"http://arxiv.org/pdf/1806.00007v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multi-layered-gradient-boosting-decision","repo_url":"https://github.com/kingfengji/mGBDT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.00007","atlas_url":"https://app.syntology.ai/?focus=1806.00007","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}