ROSE-HEA框架用125条数据预测高熵合金强度,比传统回归少32.4%样本
Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning
做合金或材料实验的朋友可以看看这篇:ROSE-HEA 用 125 条拉伸数据就打平传统回归器要 185 条的成绩,比 EI、UCB 这类贝叶斯优化采样策略更省实验次数。它的思路是先推演实验结果对预测风险的影响再选下一个实验点,做材料信息学或主动学习的都值得对照自己的采集策略想一想。
arXiv 一篇新研究提出 ROSE-HEA(Robust Outcome-aware Sequential Experimentation for High-Entropy Alloys),一个面向高熵合金极限抗拉强度(UTS)预测的样本高效序列实验框架,核心是从成分与加工条件预测 UTS,同时大幅降低所需实验数据量。
其采集策略会预先推演不同 UTS 结果如何更新高斯过程(GP)预测及其支撑度,再在参考域上重新评估最坏情况下的期望预测风险,据此挑选信息量最大的候选实验点。回溯评估基于 501 条 HEA 记录,在 30 组匹配实验中与 EI、UCB 贝叶斯优化、随机 GP 采样和 8 种传统回归器对比:从 25 条初始观测开始、再采集 100 条后,ROSE-HEA 达到最低平均 RMSE 152.84 MPa 和最高平均 R² 0.7443,RMSE 比 EI 和 UCB 分别低 6.16% 和 6.37%。
更直观的对比是:ROSE-HEA 用 125 条观测就超过了最强传统回归器需要 185 条才能达到的平均预测性能,训练样本减少 32.4%,且所选观测能提升六类回归器的预测并覆盖更广的设计空间。这对拉伸试验成本高、实验门槛高的合金研发场景意味着,在受限实验预算下也能更快逼近可用预测精度。
Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning
Accurate prediction of high-entropy alloy (HEA) strength can guide composition and processing decisions; however, obtaining tensile-test data for HEAs can be costly and experimentally demanding. This study proposes Robust Outcome-aware Sequential Experimentation for High-Entropy Alloys (ROSE-HEA), a sample-efficient framework for predicting ultimate tensile strength (UTS) from alloy composition and processing conditions. Its acquisition policy anticipates how possible UTS outcomes update predictions and the support for complementary Gaussian process (GP) descriptions. It then reassesses the worst-case expected predictive risk remaining across a reference domain to select informative candidates. A retrospective evaluation on 501 HEA records compares ROSE-HEA with expected-improvement (EI) and upper-confidence-bound (UCB) Bayesian optimization (BO), random GP sampling, and eight conventional regressors across 30 matched runs with shared initial observations and test conditions. Starting from 25 initial observations and acquiring 100 additional responses, ROSE-HEA achieves the lowest mean root-mean-square error (RMSE), at 152.84 MPa, and the highest mean R^2, at 0.7443. Mean RMSE is reduced by 6.16% and 6.37% relative to EI and UCB, respectively. The selected observations improve prediction across six regressor families and provide broader design-space coverage. ROSE-HEA also surpasses the strongest conventional regressor's mean predictive performance using 125 rather than 185 observations, corresponding to 32.4% fewer training observations. These findings demonstrate the potential of outcome-aware robust sequential learning to improve UTS prediction in HEAs under constrained training budgets.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括:ROSE-HEA、高熵合金、贝叶斯优化、材料预测,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Ahmed Shoyeb Raihan, Md Habibor Rahman, Ashish Nimbarte, Imtiaz Ahmed),经 AITOP 多维评分管线结构化提炼。