判别式
可解释性
嵌入
计算机科学
人工智能
图嵌入
模式识别(心理学)
稳健性(进化)
图形
域适应
理论计算机科学
机器学习
分类器(UML)
生物化学
化学
基因
作者
Wenxu Wang,Zhenbo Li,Weiran Li
标识
DOI:10.1016/j.neunet.2023.11.048
摘要
Heterogeneous domain adaptation (HDA) methods leverage prior knowledge from the source domain to train models for the target domain and address the differences in their feature spaces. However, incorrect alignment of categories and distribution structure disruption may be caused by unlabeled target samples during the domain alignment process for most existing methods, resulting in negative transfer. Additionally, the previous works rarely focus on the robustness and interpretability of the model. To address these issues, we propose a novel Graph embedding-based Heterogeneous domain-Invariant feature learning and Distributional order preserving framework (GHID). Specifically, a bidirectional robust cross-domain alignment graph embedding structure is proposed to globally align two domains, which learns the domain-invariant and discriminative features simultaneously. In addition, the interpretability of the proposed graph structures is demonstrated through two theoretical analyses, which can elucidate the correlation between important samples from a global perspective in heterogeneous domain alignment scenarios. Then, a heterogeneous discriminative distributional order preserving graph embedding structure is designed to preserve the original distribution relationship of each domain to prevent negative transfer. Moreover, the dynamic centroid strategy is incorporated into the graph structures to improve the robustness of the model. Comprehensive experimental results on four benchmarks demonstrate that the proposed method outperforms other state-of-the-art approaches in effectiveness.
科研通智能强力驱动
Strongly Powered by AbleSci AI