mlsanityData to 14 Oct 2026

MetaDSE: A Few-shot Meta-learning Framework for Cross-workload CPU Design Space Exploration

arXiv 2504.13568 ↗First posted 18 Apr 2025cs.AR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-workload design space exploration (DSE) is crucial in CPU architecture design. Existing DSE methods typically employ the transfer learning technique to leverage knowledge from source workloads, aiming to minimize the requirement of target workload simulation. However, these methods struggle with overfitting, data ambiguity, and workload dissimilarity. To address these challenges, we reframe the cross-workload CPU DSE task as a few-shot meta-learning problem and further introduce MetaDSE. By leveraging model agnostic meta-learning, MetaDSE swiftly adapts to new target workloads, greatly enhancing the efficiency of cross-workload CPU DSE. Additionally, MetaDSE introduces a novel knowledge transfer method called the workload-adaptive architectural mask algorithm, which uncovers the inherent properties of the architecture. Experiments on SPEC CPU 2017 demonstrate that MetaDSE significantly reduces prediction error by 44.3% compared to the state-of-the-art. MetaDSE is open-sourced and available at this hrefhttps://anonymous.4open.science/r/MetaDSE-02F8anonymous GitHub.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 31 references that are in the map. First posted on arXiv 18 Apr 2025.

Builds on

7 of 31 references.

References · 7

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  4. 2023A Closer Look at Few-shot Classification Againcited by 46
  5. 2021Learning Pareto-Frontier Resource Management Policies for Heterogeneous SoCs: An Information-Theoretic Approachcited by 3
  6. 2024Multi-objective Optimization in CPU Design Space Exploration: Attention is All You Needcited by 1
  7. 2024Explainable Fuzzy Neural Network with Multi-Fidelity Reinforcement Learning for Micro-Architecture Design Space Explorationcited by 1

Built on by

Not cited yet.