Metraipolis › archive › dc_d2f97a64e72a
Streaming Hierarchical Inference with Tabular Foundation Models — arXiv:2609.07956
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07956
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:58:00.790Z
- SHA-256 of the archived text
56c02aa2777fa07119fa2f3071b8087509d1bca13abf7927e19ffc66ff031dab- Stable URL of this page
https://metraipolis.com/documento/dc_d2f97a64e72a
How to cite
Streaming Hierarchical Inference with Tabular Foundation Models — arXiv:2609.07956 — arXiv (en), https://arxiv.org/abs/2609.07956 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2f97a64e72a (Metraipolis archive dc_d2f97a64e72a, sha256 56c02aa2777fa07119fa2f3071b8087509d1bca13abf7927e19ffc66ff031dab)
BibTeX
@misc{dcd2f97a64e72a,
title = {Streaming Hierarchical Inference with Tabular Foundation Models — arXiv:2609.07956},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07956},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2f97a64e72a; sha256 56c02aa2777fa07119fa2f3071b8087509d1bca13abf7927e19ffc66ff031dab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07956. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tabular Foundation Models (TFMs) have recently demonstrated strong predictive performance through in-context learning, but their deployment in high-throughput data streams remains challenging due to communication overhead and latency. We propose \textit{HINT}, a hierarchical inference framework that combines edge-based retrieval with cloud-based TFM inference. A graph-based approximate nearest neighbor memory maintained over a sliding window provides local predictions and uncertainty estimates, allowing confident samples to be processed locally while uncertain instances are selectively offloaded, together with their retrieved context, to a cloud-hosted TFM. The framework exposes an offloading threshold and a neighborhood retrieval policy that can be varied to balance predictive performance and communication cost. Experiments show \textit{HINT} consistently identifies favorable trade-offs.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.07956 — 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 2026-10-16T13:39:43.003Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).