# Streaming Hierarchical Inference with Tabular Foundation Models

arXiv: https://arxiv.org/abs/2609.07956 · HTML: https://mlsanity.com/paper/2609.07956/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025)
- [A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2101.12631/) (2021)
- [HyperFast: Instant Classification for Tabular Data](https://mlsanity.com/paper/2402.14335/) (2024)
- [Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks](https://mlsanity.com/paper/2311.10609/) (2023)
- [Early Stopping Tabular In-Context Learning](https://mlsanity.com/paper/2506.21387/) (2025)
- [DFDT: Dynamic Fast Decision Tree for IoT Data Stream Mining on Edge Devices](https://mlsanity.com/paper/2502.14011/) (2025)
- [In-context Learning of Evolving Data Streams with Tabular Foundational Models](https://mlsanity.com/paper/2502.16840/) (2025)
- [On-device edge learning for IoT data streams: a survey](https://mlsanity.com/paper/2502.17788/) (2025)
- [Bridging Streaming Continual Learning via In-Context Large Tabular Models](https://mlsanity.com/paper/2512.11668/) (2025)
- [Online hierarchical partitioning of the output space in extreme multi-label data stream](https://mlsanity.com/paper/2507.20894/) (2025)
- [The Case for Hierarchical Deep Learning Inference at the Network Edge](https://mlsanity.com/paper/2304.11763/) (2023)
- [Explainable Anomaly Detection for Industrial IoT Data Streams](https://mlsanity.com/paper/2512.08885/) (2025)
- [A Practical Guide to Streaming Continual Learning](https://mlsanity.com/paper/2603.01677/) (2026)
- [Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles](https://mlsanity.com/paper/2605.12803/) (2026)

## Built on by (most cited first, 1 of 1)

- [Collaborative Streaming Anomaly Detection with Interactive Explanations and Ensemble Consensus](https://mlsanity.com/paper/2609.23883/) (2026)

## Abstract (arXiv)

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 textitHINT, 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 textitHINT consistently identifies favorable trade-offs.