Metraipolis › archive › dc_46e8cb950de6

TreePIN$^{2}$: Tree-Prior Initialized Neural Networks — arXiv:2611.00919

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00919
License (as archived)
CC0-1.0
Archived
2026-11-03T10:26:06.127Z
SHA-256 of the archived text
4e98d956f68e330ef8a1e8804b076c78c822652285dd89f79a238c1e739dbb19
Stable URL of this page
https://metraipolis.com/documento/dc_46e8cb950de6

How to cite

TreePIN$^{2}$: Tree-Prior Initialized Neural Networks — arXiv:2611.00919 — arXiv (en), https://arxiv.org/abs/2611.00919 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46e8cb950de6 (Metraipolis archive dc_46e8cb950de6, sha256 4e98d956f68e330ef8a1e8804b076c78c822652285dd89f79a238c1e739dbb19)
BibTeX
@misc{dc46e8cb950de6,
  title = {TreePIN$^2$: Tree-Prior Initialized Neural Networks — arXiv:2611.00919},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00919},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46e8cb950de6; sha256 4e98d956f68e330ef8a1e8804b076c78c822652285dd89f79a238c1e739dbb19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00919. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fitted decision trees provide predictive knowledge for neural network initialization. We present Tree-Prior Initialized Neural Networks (TreePIN$^{2}$), a method that translates split rules, decision paths and leaf predictions into initial network weights and biases for classification and regression. Sigmoid units encode split responses, hidden units combine them along decision paths, and leaf predictions initialize the output layer. We calibrate split softness using local training margins, sample support and impurity reduction, relating the initial responses to the data at each node. All weights and biases remain trainable, allowing gradient-based optimization to refine the transferred decisions and their combinations. Across six classification and six regression tasks with twenty paired seeds, TreePIN$^{2}$ improves mean initial and early validation performance over initialization baselines on most tasks. After fifty epochs, it achieves the best or tied-best mean validation performance among the six compared methods on ten tasks. Paired ablations show how split calibration and leaf-informed output initialization contribute to the starting predictor and its subsequent learning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00919 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:19:50.040Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).