Metraipolis › archive › dc_dfbe22a348e3

Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings — arXiv:2609.31253

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31253
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:04.130Z
SHA-256 of the archived text
b801619e53d25c1befe4c342e234c84ccf4c0c48a279a136fd1eed4bc3d3c3f8
Stable URL of this page
https://metraipolis.com/documento/dc_dfbe22a348e3

How to cite

Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings — arXiv:2609.31253 — arXiv (en), https://arxiv.org/abs/2609.31253 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dfbe22a348e3 (Metraipolis archive dc_dfbe22a348e3, sha256 b801619e53d25c1befe4c342e234c84ccf4c0c48a279a136fd1eed4bc3d3c3f8)
BibTeX
@misc{dcdfbe22a348e3,
  title = {Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings — arXiv:2609.31253},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31253},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dfbe22a348e3; sha256 b801619e53d25c1befe4c342e234c84ccf4c0c48a279a136fd1eed4bc3d3c3f8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31253. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sequential recommenders typically rely on learnable positional embeddings to encode the order of user interactions. In this work, we ask whether this ordinal signal can be replaced by a structural one derived from the item space. We propose to use Laplacian positional embeddings in SASRec: we build an item co-occurrence graph from training interactions, compute eigenvectors of its symmetric normalized Laplacian, and use them as frozen graph-derived positional embeddings. The backbone architecture and training objective remain unchanged. Experiments on four public sequential-recommendation benchmarks show that this simple replacement improves SASRec performance on most ranking metrics and remains competitive with strong positional and temporal encoding baselines. These findings indicate that item-item graph structure can be an effective substitute for standard ordinal positional embeddings in sequential recommendation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.31253 — 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 2026-10-08T02:50:01.738Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).