Metraipolis › archive › dc_ef34dc6bca4e

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: 2026-11-03T11:05:35.045Z
SHA-256 of the archived text: bb45639523d15869d23476895037b0d26d113371bf5d47cb9be5036fa3e06744
Stable URL of this page: https://metraipolis.com/documento/dc_ef34dc6bca4e

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_ef34dc6bca4e (Metraipolis archive dc_ef34dc6bca4e, sha256 bb45639523d15869d23476895037b0d26d113371bf5d47cb9be5036fa3e06744)

BibTeX

@misc{dcef34dc6bca4e,
  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_ef34dc6bca4e; sha256 bb45639523d15869d23476895037b0d26d113371bf5d47cb9be5036fa3e06744},
  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 2026-11-03T10:59:45.977Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).