# HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS

arXiv: https://arxiv.org/abs/2607.11746 · HTML: https://mlsanity.com/paper/2607.11746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [BRP-NAS: Prediction-based NAS using GCNs](https://mlsanity.com/paper/2007.08668/) (2020)
- [HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning](https://mlsanity.com/paper/2106.08630/) (2021)
- [Learnable Commutative Monoids for Graph Neural Networks](https://mlsanity.com/paper/2212.08541/) (2022)
- [On Latency Predictors for Neural Architecture Search](https://mlsanity.com/paper/2403.02446/) (2024)
- [Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search](https://mlsanity.com/paper/2306.02459/) (2023)

## Abstract (arXiv)

With deep neural networks (DNNs) increasingly deployed on edge devices, hardware (HW)-aware optimization techniques--such as HW-aware compression and HW-aware neural architecture search (HW-NAS)--have become essential. These methods rely on real feedback from the target hardware to tailor DNN architectures for efficient deployment. While the search can be parallelized, latency measurements via hardware-in-the-loop (HIL) remain a bottleneck due to their sequential nature. Recent approaches use latency predictors to replace costly HIL feedback, but challenges persist: (1) platform-specific predictors often require tens of thousands of samples, and (2) inaccurate predictions can mislead the NAS process. To address this, we introduce HiFi-LLP, a high-fidelity, low-cost latency predictor based on graph attention networks, augmented with a confidence metric. HiFi-LLP outperforms prior platform-specific predictors by up to 9 percentage points (p.p.) in the 10% accuracy bound and achieves a Spearman's rank correlation of up to 0.996 across six devices in the LatBench dataset. We further propose a hybrid NAS framework that routes low-confidence predictions to HIL, achieving up to 8.6× speedup compared to typical NAS while maintaining a competitive Pareto front.