基于超网络的稀疏任务向量混合用于全切片图像预后中的高效知识迁移
Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis
提出基于任务向量混合与超网络稀疏聚合的模型合并方案，可高效地将多个源域模型的知识迁移到目标域模型，无需联合训练或多模型推理，为医学影像中的跨癌种知识迁移提供了可复用的技术路径。
原文依据 applying task vector mixup to each source-target pair and then sparsely aggregating task vector mixtures to obtain an improved target model, driven by hypernetworks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全切片图像（WSIs）广泛用于估计癌症患者的预后。当前研究通常遵循针对特定癌症的学习范式。然而，病理学中单一癌症类型的可用训练样本通常稀缺。因此，模型往往难以学习到可泛化的知识，从而在具有内在高异质性的肿瘤样本上表现较差。尽管最近已有研究探索多癌症联合学习和知识迁移方法来应对这一问题，但它们要么依赖大规模联合训练，要么需要对多个模型进行大量推理，在计算效率方面带来了新的挑战。为此，本文提出了一种新方案——基于超网络的稀疏任务向量混合（STEPH）。与以往方法不同，它通过模型合并高效地从其他癌症中为目标癌症吸收可泛化知识：i）对每个源-目标对应用任务向量混合，然后 ii）在超网络的驱动下，稀疏聚合任务向量混合结果以获得改进的目标模型。在13个癌症数据集上的大量实验表明，STEPH分别比癌症特异性学习和现有知识迁移基线提升了5.14%和2.01%。此外，它作为一种从其他癌症学习预后知识的解决方案更为高效，无需大规模联合训练或大量多模型推理。
英文原文摘要 1412 字符
Whole-Slide Images (WSIs) are widely used for estimating the prognosis of cancer patients. Current studies generally follow a cancer-specific learning paradigm. However, the available training samples for one cancer type are usually scarce in pathology. Consequently, the model often struggles to learn generalizable knowledge, thus performing worse on the tumor samples with inherent high heterogeneity. Although multi-cancer joint learning and knowledge transfer approaches have been explored recently to address it, they either rely on large-scale joint training or extensive inference across multiple models, posing new challenges in computational efficiency. To this end, this paper proposes a new scheme, Sparse Task Vector Mixup with Hypernetworks (STEPH). Unlike previous ones, it efficiently absorbs generalizable knowledge from other cancers for the target via model merging: i) applying task vector mixup to each source-target pair and then ii) sparsely aggregating task vector mixtures to obtain an improved target model, driven by hypernetworks. Extensive experiments on 13 cancer datasets show that STEPH improves over cancer-specific learning and an existing knowledge transfer baseline by 5.14% and 2.01%, respectively. Moreover, it is a more efficient solution for learning prognostic knowledge from other cancers, without requiring large-scale joint training or extensive multi-model inference.