{"ID":6537392,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11746","arxiv_id":"2607.11746","title":"HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS","abstract":"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$\\times$ speedup compared to typical NAS while maintaining a competitive Pareto front.","short_abstract":"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 efficien...","url_abs":"https://arxiv.org/abs/2607.11746","url_pdf":"https://arxiv.org/pdf/2607.11746v1","authors":"[\"Shambhavi Balamuthu Sampath\",\"Behzad Shomali\",\"Nael Fasfous\",\"Moritz Thoma\",\"Judeson Anthony Fernando\",\"Lukas Frickenstein\",\"Pierpaolo Mori\",\"Manoj Rohit Vemparala\",\"Alexander Frickenstein\",\"Walter Stechele\"]","published":"2026-07-13T16:05:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AR\"]","methods":"[]","has_code":false}