WANDER帮用户在高性能计算中找到可解释的配置优化方案。
WANDER: An Explainable Decision-Support Framework for HPC
- 用反事实分析生成符合目标和约束的配置建议
- 综合不确定度、因果关系一致性和历史分布相似性排序推荐
- 适合需要可解释调优的科研与工程人员
高性能计算（HPC）系统包含大量相互关联的配置参数，影响运行时间、资源使用、功耗和结果变异性。现有预测工具虽能建模这些指标，但缺乏结构化探索、解释和引导重配置的能力。我们提出 WANDER，一个决策支持框架，通过与用户目标和约束对齐的反事实分析合成替代配置。引入复合权衡评分，基于预测不确定性、因果模型下特征-目标关系的一致性，以及特征分布与历史数据的相似性进行排序。据我们所知，WANDER 是首个在统一查询接口下整合预测、探索与解释的 HPC 调优系统。在多个数据集上，WANDER 生成了可解释、可信且人类可读的配置备选方案，有效引导用户达成性能目标。
原文摘要 · Abstract (English)
High-performance computing (HPC) systems expose many interdependent configuration knobs that impact runtime, resource usage, power, and variability. Existing predictive tools model these outcomes, but do not support structured exploration, explanation, or guided reconfiguration. We present WANDER, a decision-support framework that synthesizes alternate configurations using counterfactual analysis aligned with user goals and constraints. We introduce a composite trade-off score that ranks suggestions based on prediction uncertainty, consistency between feature-target relationships using causal models, and similarity between feature distributions against historical data. To our knowledge, WANDER is the first such system to unify prediction, exploration, and explanation for HPC tuning under a common query interface. Across multiple datasets WANDER generates interpretable and trustworthy, human-readable alternatives that guide users to achieve their performance objectives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。