Metraipolis › archive › dc_839929ce3422

User Embeddings are Superpositions of Interpretable Behavioral Modes — arXiv:2611.08487

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08487
License (as archived)
CC0-1.0
Archived
2026-11-06T14:51:02.375Z
SHA-256 of the archived text
5f9f812d546b46f1170d4e4736c4264e8a9887f38e68b841b8672c87aaf94f55
Stable URL of this page
https://metraipolis.com/documento/dc_839929ce3422

How to cite

User Embeddings are Superpositions of Interpretable Behavioral Modes — arXiv:2611.08487 — arXiv (en), https://arxiv.org/abs/2611.08487 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_839929ce3422 (Metraipolis archive dc_839929ce3422, sha256 5f9f812d546b46f1170d4e4736c4264e8a9887f38e68b841b8672c87aaf94f55)
BibTeX
@misc{dc839929ce3422,
  title = {User Embeddings are Superpositions of Interpretable Behavioral Modes — arXiv:2611.08487},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08487},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_839929ce3422; sha256 5f9f812d546b46f1170d4e4736c4264e8a9887f38e68b841b8672c87aaf94f55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08487. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

User embeddings are central components of modern recommendation, personalization, and behavioral modeling systems. Though these embeddings can compactly encode rich behavioral information, they are inherently dense and opaque, limiting interpretability. To address this gap, we argue that user embeddings can be understood as sparse superpositions of interpretable behavioral modes. This structure is directly predicted by generative models of user behavior for linear embeddings and extends approximately to deep-learning representations by the superposition hypothesis. Superimposed modes can naturally be recovered by sparse dictionary learning methods, such as sparse autoencoders (SAEs), and recovered modes can be automatically named and queried in natural language. We validate mode recovery against known ground truth on synthetic data, where SAEs recover modes better than classical sparse baselines, including on transformer-encoded embeddings. We then apply the method to classical and transformer-based user embeddings from two real-world datasets. We also show how the corresponding natural-language labels enable zero-shot audience retrieval and characterization over embeddings never trained on text. The framework is post-hoc and model-agnostic, requiring no modification to the upstream embedding system.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.08487 — 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 2026-11-06T14:21:42.651Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).