重要性反向转移识别跨领域学习的共同原则
Importance inversion transfer identifies shared principles for cross-domain learning
AI总结：
本研究提出X-CDTL框架，通过重要性反向转移机制识别跨领域学习的共同原则，提升异常检测任务在极端噪声下的性能。
摘要：
跨科学领域知识转移的能力依赖于共享的组织原则。然而，现有的迁移学习方法往往无法连接根本不同的系统，尤其是在数据稀缺或随机噪声严重的情况下。本研究正式提出了可解释的跨领域迁移学习（X-CDTL）框架，该框架将网络科学和可解释人工智能统一起来，以识别在生物、语言、分子和社会网络中普遍存在的结构不变量。通过引入重要性反向转移（IIT）机制，该框架优先考虑跨领域的结构锚点，而非具有高度判别性的特殊特征。在异常检测任务中，受这些原则指导的模型在极端噪声下表现出显著的性能提升——在决策稳定性方面比传统基线提高了56%。这些结果提供了跨异质领域的共享组织特征的证据，建立了跨学科知识传播的原理性范式。通过从不透明的潜在表示转向显式的结构法则，本研究将机器学习推进为科学发现的稳健引擎。
英文摘要：
The capacity to transfer knowledge across scientific domains relies on shared organizational principles. However, existing transfer-learning methodologies often fail to bridge radically heterogeneous systems, particularly under severe data scarcity or stochastic noise. This study formalizes Explainable Cross-Domain Transfer Learning (X-CDTL), a framework unifying network science and explainable artificial intelligence to identify structural invariants that generalize across biological, linguistic, molecular, and social networks. By introducing the Importance Inversion Transfer (IIT) mechanism, the framework prioritizes domain-invariant structural anchors over idiosyncratic, highly discriminative features. In anomaly detection tasks, models guided by these principles achieve significant performance gains - exhibiting a 56% relative improvement in decision stability under extreme noise - over traditional baselines. These results provide evidence for a shared organizational signature across heterogeneous domains, establishing a principled paradigm for cross-disciplinary knowledge propagation. By shifting from opaque latent representations to explicit structural laws, this work advances machine learning as a robust engine for scientific discovery.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
