PaperScope
LIVE · 2026-09-09 05:40 UTC

Streaming Hierarchical Inference with Tabular Foundation Models

Vitor Crista, Afonso Lourenço, Diogo Martinho, Goreti Marreiros

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.07956 v1
Category
Submitted
2026-09-07

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.

Comment: Streaming Continual Learning ECML PKDD Workshop 2026

arXiv abs page · PDF · same-day batch