Metraipolis › archive › dc_40aa91c45d2d

PCGNet: Unifying Shared and Specific Information for Fashion Matching Recommendations — arXiv:2609.13339

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13339
License (as archived): CC0-1.0
Archived: 2026-10-16T01:34:54.694Z
SHA-256 of the archived text: 66b703fd80a2c8bb1d4eff944ae9089e8d8395669b83fb734910c527f9a356e7
Stable URL of this page: https://metraipolis.com/documento/dc_40aa91c45d2d

How to cite

PCGNet: Unifying Shared and Specific Information for Fashion Matching Recommendations — arXiv:2609.13339 — arXiv (en), https://arxiv.org/abs/2609.13339 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40aa91c45d2d (Metraipolis archive dc_40aa91c45d2d, sha256 66b703fd80a2c8bb1d4eff944ae9089e8d8395669b83fb734910c527f9a356e7)

BibTeX

@misc{dc40aa91c45d2d,
  title = {PCGNet: Unifying Shared and Specific Information for Fashion Matching Recommendations — arXiv:2609.13339},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13339},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40aa91c45d2d; sha256 66b703fd80a2c8bb1d4eff944ae9089e8d8395669b83fb734910c527f9a356e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13339. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In fashion domain, recommending complementary clothing items that match selected pieces is a crucial cross-selling technique that improves customer satisfaction. Nevertheless, fashion matching presents significant challenges, as recommendations must not only align with individual user fashion preferences but also ensure compatibility between garments. These challenges are twofold. First, existing models often assume an overly simplified decoupled relationship between product compatibility and personalized user preferences, overlooking the natural complexity between the two. Second, existing data-driven approaches are not optimized for real-world fashion data, which is typically sparse and characterized by noisy interactions. To address these challenges, we propose Personalized Compatibility Graph Network, a multi-objective graph learning framework that organically unifies the modeling of product compatibility and personal preferences. PCGNet uses contrastive mutual information maximization to extract and align shared and view-specific patterns, thereby capturing the complex interplay between compatibility and personal preferences. Moreover, we introduce a correlation-aware neighbor sampling and a learnable global graph augmentation, which enhance the model by incorporating self-supervised signals mined directly from the graph, ensuring more stable and informative representations. Finally, PCGNet generates recommendation scores through the joint optimization of BPR ranking loss and multi-view mutual information losses. Experimental validation on two benchmark datasets demonstrates that PCGNet significantly outperforming state-of-the-art methods across all four evaluation metrics.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-15 in math.IT).
Categorie arXiv: Information Retrieval (cs.IR) ; Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2609.13339 — 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 2026-10-16T01:21:38.635Z dalla pagina https://arxiv.org/catchup/math.IT/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).