Metraipolis › archive › dc_3a949f5cea64
GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation — arXiv:2608.16073
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16073
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:44:18.630Z
- SHA-256 of the archived text
2766eb165697977ac3bdb3a37300608ec4a0a024bd8422b8f7af93d8fb323f45- Stable URL of this page
https://metraipolis.com/documento/dc_3a949f5cea64
How to cite
GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation — arXiv:2608.16073 — arXiv (en), https://arxiv.org/abs/2608.16073 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a949f5cea64 (Metraipolis archive dc_3a949f5cea64, sha256 2766eb165697977ac3bdb3a37300608ec4a0a024bd8422b8f7af93d8fb323f45)
BibTeX
@misc{dc3a949f5cea64,
title = {GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation — arXiv:2608.16073},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16073},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a949f5cea64; sha256 2766eb165697977ac3bdb3a37300608ec4a0a024bd8422b8f7af93d8fb323f45},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16073. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sequential recommenders often struggle with sparse and noisy histories, limiting generalization to unseen interactions. Knowledge distillation mitigates this by transferring dense supervision from a teacher to a student. However, most distillation methods run teacher and student independently, then match student outputs or representations to the teacher. Such supervision entangles student-component effects, blurring whether weak generalization stems from unreliable embeddings, overfitted encoding, or co-adaptation to sparse histories. In this paper, we propose Graft-Oriented Distillation (GOD), a component-level distillation framework for improved generalization through grafting. Grafting denotes replacing selected frozen-teacher components with trainable student counterparts to build hybrid source models. GOD uses these hybrid models to evaluate student embeddings with the teacher encoder and the student encoder with teacher embeddings, providing component-level feedback. At inference, GOD uses only the student, incurring no additional cost. Across three real-world datasets, GOD outperforms state-of-the-art baselines by up to 13.92%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Information Retrieval (cs.IR) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.16073 — 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 2026-10-18T19:02:44.293Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).