Metraipolis › archive › dc_7e889ac7ca21

No Attention, No Problem: Rethinking Session-based Recommendation with Pure Convolution — arXiv:2609.34802

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34802
License (as archived)
CC0-1.0
Archived
2026-10-07T23:49:52.434Z
SHA-256 of the archived text
76f9a209141e18d3f4a22be9a0537179bb62c4b59fa554f46d7356d3fca2aa0e
Stable URL of this page
https://metraipolis.com/documento/dc_7e889ac7ca21

How to cite

No Attention, No Problem: Rethinking Session-based Recommendation with Pure Convolution — arXiv:2609.34802 — arXiv (en), https://arxiv.org/abs/2609.34802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e889ac7ca21 (Metraipolis archive dc_7e889ac7ca21, sha256 76f9a209141e18d3f4a22be9a0537179bb62c4b59fa554f46d7356d3fca2aa0e)
BibTeX
@misc{dc7e889ac7ca21,
  title = {No Attention, No Problem: Rethinking Session-based Recommendation with Pure Convolution — arXiv:2609.34802},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34802},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e889ac7ca21; sha256 76f9a209141e18d3f4a22be9a0537179bb62c4b59fa554f46d7356d3fca2aa0e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Session-based recommendation (SBR) predicts the next choice in a session by analyzing recent interactions. Transformer-based models are widely used because of their ability to capture long-range dependencies through self-attention mechanisms. In contrast, traditional convolutional models, although more efficient, are often limited by their weak global modeling capabilities and are losing ground in SBR tasks. In this work, we propose a Next-generation Pure Convolutional Framework (NextConvRec) for SBR tasks, aiming to balance efficiency and performance. NextConvRec uses a Structural and Positional Convolutional Encoder (SPCE) for preprocessing, combining learnable convolutional positional biases with session-level structural signals extracted through GCN layers. Its backbone convolutional module effectively expands the effective receptive field through depthwise convolutions and pointwise convolutions, enabling robust long-range preference modeling without attention mechanisms. Extensive experiments on 4 benchmark datasets show that NextConvRec outperforms several state-of-the-art baselines by around 1.73% on average, and reduces the average inference time per session by 16.7%. The convolutional architectures remain a promising direction for efficient and accurate session-based recommendations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.34802 — 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 2026-10-07T23:26:57.208Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).