Unsupervised multi-source domain adaptation with graph convolution network and multi-alignment in mixed latent space

Chen, Dong; Zhu, Huangqiu; Yang, Suyi; Dai, Yiwen

doi:10.1007/s11760-022-02298-w

Cited by 3 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is crucial to acquire an effective graph structure. Reducing the spatial structural differences between source and target REM grids is a key issue in GNN-based MDA learning tasks [ 39 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction of Radio Environment Map Based on Multi-Source Domain Adaptive of Graph Neural Network for Regression

Wen,

Fang,

Fan

2024

Sensors

View full text Add to dashboard Cite

The graph neural network (GNN) has shown outstanding performance in processing unstructured data. However, the downstream task performance of GNN strongly depends on the accuracy of data graph structural features and, as a type of deep learning (DL) model, the size of the training dataset is equally crucial to its performance. This paper is based on graph neural networks to predict and complete the target radio environment map (REM) through multiple complete REMs and sparse spectrum monitoring data in the target domain. Due to the complexity of radio wave propagation in space, it is difficult to accurately and explicitly construct the spatial graph structure of the spectral data. In response to the two above issues, we propose a multi-source domain adaptive of GNN for regression (GNN-MDAR) model, which includes two key modules: (1) graph structure alignment modules are used to capture and learn graph structure information shared by cross-domain radio propagation and extract reliable graph structure information for downstream reference signal receiving power (RSRP) prediction task; and (2) a spatial distribution matching module is used to reduce the feature distribution mismatch across spatial grids and improve the model’s ability to remain domain invariant. Based on the measured REMs dataset, the comparative results of simulation experiments show that the GNN-MDAR outperforms the other four benchmark methods in accuracy when there is less RSRP label data in the target domain.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We adopt the multi-kernel MMD method. The learning scheme for the parameter matrix

is executed according to the Boosting-based Importance Evaluation Algorithm proposed in [ 39 ].…”

Section: Methodsmentioning

confidence: 99%

Reconstruction of Radio Environment Map Based on Multi-Source Domain Adaptive of Graph Neural Network for Regression

Wen,

Fang,

Fan

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, the effectiveness of contrasting multiple context templates [34], [35], [36] for prompt learning have been empirically verified. Based on the aforementioned issues, this paper proposes a two-stage prompt learning method, which leverages adversarial learning to obtain learnable multisemantic prompt representations in the visual feature space.…”

Section: B Visual-language Learningmentioning

confidence: 99%

Dual Domain Multi-Task Model for Vehicle Re-Identification

Huang

Liang

Xie

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Generalizable vehicle re-identification (ReID) aims to enable the well-trained model in diverse source domains to broadly adapt to unknown target domains without additional fine-tuning or retraining. However, it still faces the challenges of domain shift problem and has difficulty accurately generalizing to unknown target domains. This limitation occurs because the model relies heavily on primary domain-invariant features in the training data and pays less attention to potentially valuable secondary features. To solve this complex and common problem, this paper proposes the two-stage Multi-expert Knowledge Confrontation and Collaboration (MiKeCoCo) method, which incorporates multiple experts with unique perspectives into Contrastive Language-Image Pretraining (CLIP) and fully leverages high-level semantic knowledge for comprehensive feature representation. Specifically, we propose to construct the learnable prompt set of all specific-perspective experts by adversarial learning in the latent space of visual features during the first stage of training. This comprehensive prompt set is integrated with the various high-level semantics related to each vehicle, which are derived from the diverse expert knowledge perspectives learned through CLIP. The learned prompt set with high-level semantics is then utilized to guide representation learning of the multi-level features for final knowledge fusion in the next stage. In this process of knowledge fusion, although multiple experts employ different assessment ways to examine the same vehicle, their common goal is to confirm the vehicle's true identity. By combining their expertise, their collective decision can ensure the accuracy and consistency of the evaluation results. Furthermore, we design different image inputs for two-stage training, which include image component separation and diversity enhancement in order to extract the ID-related prompt representation and to obtain feature representation highlighted by all experts, respectively. Extensive experimental results demonstrate that our method achieves state-of-the-art recognition performance.

show abstract

Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling

Zhao,

Luo,

Zhang

et al. 2024

Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Unsupervised multi-source domain adaptation with graph convolution network and multi-alignment in mixed latent space

Cited by 3 publications

References 15 publications

Reconstruction of Radio Environment Map Based on Multi-Source Domain Adaptive of Graph Neural Network for Regression

Reconstruction of Radio Environment Map Based on Multi-Source Domain Adaptive of Graph Neural Network for Regression

Dual Domain Multi-Task Model for Vehicle Re-Identification

Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling

Contact Info

Product

Resources

About