Paper Detail

Streaming Hierarchical Inference with Tabular Foundation Models

Vitor Crista, Afonso Lourenço, Diogo Martinho, Goreti Marreiros

arxiv Score 10.5

Published 2026-09-07 · First seen 2026-09-09

Research Track A · General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{crista2026streaming,
  title = {Streaming Hierarchical Inference with Tabular Foundation Models},
  author = {Vitor Crista and Afonso Lourenço and Diogo Martinho and Goreti Marreiros},
  year = {2026},
  abstract = {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 \textbackslash{}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, },
  url = {https://arxiv.org/abs/2609.07956},
  keywords = {cs.LG},
  eprint = {2609.07956},
  archiveprefix = {arXiv},
}

Metadata

{}