Node-wise Feature Encoding for Neural Performance Prediction

arXiv:2608.27794v1 Announce Type: new Abstract: As neural networks are increasingly deployed on resource constrained edge devices, accurate prediction of latency and energy is critical for efficient neural architecture search. Existing GNN and transformer based predictors achieve strong results but largely ignore node-level computational cost, limiting their ability to model performance critical operations. To address this, we introduce FeatureFormer, a neural performance predictor that incorporates explicit node-wise encodings of FLOPs, parameter counts, and memory proxies within a gated graph attention architecture. We also present NNEQ, a new large-scale energy consumption dataset that enables unified evaluation of latency and energy prediction. Extensive experiments demonstrate that FeatureFormer achieves state-of-the-art performance across both metrics, including challenging out-of-domain settings. Finally, we show that the proposed encoding is broadly applicable and consistently improves existing predictors with negligible overhead.

Related

• Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds
• Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs
• SURGE: SuperBatch Unified Resource-efficient GPU Encoding for Heterogeneous Partitioned Data
• MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs

Source: arXiv cs.LG | 2026-08-31