面向神经性能预测的节点级特征编码
Node-wise Feature Encoding for Neural Performance Prediction
- University of South Carolina（南卡罗来纳大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有神经性能预测器忽略节点级计算成本的问题，提出FeatureFormer模型并构建NNEQ数据集，实现了延迟与能耗预测的最优性能，且可提升现有预测器的效果。
AI中文摘要：
随着神经网络越来越多地部署在资源受限的边缘设备上，准确预测延迟和能耗对于高效的神经架构搜索至关重要。现有的基于GNN和Transformer的预测器虽取得了良好效果，但在很大程度上忽略了节点级计算成本，限制了其对性能关键操作的建模能力。为解决这一问题，我们提出FeatureFormer，一种神经性能预测器，它在门控图注意力架构中纳入了针对FLOPs、参数数量和内存代理的显式节点级编码。我们还提出了NNEQ，一个新的大规模能耗数据集，可用于延迟和能耗预测的统一评估。大量实验表明，FeatureFormer在两个指标上均达到了最先进的性能，包括具有挑战性的域外设置。最后，我们证明所提出的编码具有广泛适用性，可在几乎无开销的情况下持续提升现有预测器的性能。
英文摘要：
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.
