Biqing Zeng

In the era of heterogeneous computing environments, including diverse hardware platforms and programming paradigms, accurate performance prediction of software applications is essential for efficient resource allocation, cost optimization, and informed deployment decisions. However, traditional methods often require platform-specific measurements, which are resource-intensive and limited by data scarcity in low-performance or novel code contexts. This exploratory study addresses these challenges by leveraging transfer learning with regression models to enable cross-platform (from Intel x86 to ARM M1) and cross-code performance predictions. Using the Renaissance benchmark suite (renaissance-gpl-0.15.0.jar), we systematically evaluate eight traditional machine learning models and a deep neural network across scenarios of data transfer and fine-tuning. Key findings demonstrate that transfer learning significantly improves prediction accuracy, with tree-based models like Extra Trees achieving high R² scores (0.92) and outperforming DNNs in robustness, particularly under noisy or data-scarce conditions. The study provides empirical insights into model effectiveness, highlights the superiority of transfer settings, and offers practical guidance for software engineers to reduce measurement overheads and enhance optimization processes.

会话推荐的目标是仅根据用户在匿名会话中有限的交互行为，来预测用户的下一次点击行为。最近几年，许多基于图神经网络的会话推荐方法取得了可喜的结果。然而，这些方法仍然存在不足之处。一方面，基于图神经网络的方法只考虑物品之间的转换模式，忽略了会话中的序列模式。另一方面，现有的大多数方法都只关注当前会话内部的信息，忽略了来自邻居会话的外部协作信息，即上下文模式。为了解决上述问题，本文提出了一种新颖的基于上下文增强的多级注意力会话推荐模型（CEMA），通过多级注意力机制分别在物品级和会话级这两个粒度上学习物品特征和建模用户偏好，以增强模型的个性化推荐能力。CEMA 模型利用多层GraphSAGE 来学习物品之间复杂的转换模式，以捕获用户的局部偏好。特别地，在CEMA 模型中设计了一种物品级注意力机制，通过门控注意力单元来计算会话中不同物品的重要性，以识别用户真正感兴趣的物品，避免噪声物品的干扰。这有助于准确地捕获会话的序列模式，以建模用户的全局偏好。此外，所提出的方法还设计了一种会话级注意力机制，通过简单的软注意力高效地计算不同会话之间的相似度，以聚焦于那些与当前会话最相似的邻居会话，并从中提取上下文模式，以帮助预测用户的下一次点击。本文在三个公开的基准数据集上进行了一系列实验，实验结果表明CEMA 的推荐性能超过了现有最好的方法，充分验证了CEMA 的有效性和优越性。