Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2204.05104 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914640524476416 |
|---|---|
| author | Yuan, Jin Hou, Feng Du, Yangzhou Shi, Zhongchao Geng, Xin Fan, Jianping Rui, Yong |
| author_facet | Yuan, Jin Hou, Feng Du, Yangzhou Shi, Zhongchao Geng, Xin Fan, Jianping Rui, Yong |
| contents | Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data, and multi-source domain adaptation (MSDA) is very attractive for real world applications. By learning from large-scale unlabeled samples, self-supervised learning has now become a new trend in deep learning. It is worth noting that both self-supervised learning and multi-source domain adaptation share a similar goal: they both aim to leverage unlabeled data to learn more expressive representations. Unfortunately, traditional multi-task self-supervised learning faces two challenges: (1) the pretext task may not strongly relate to the downstream task, thus it could be difficult to learn useful knowledge being shared from the pretext task to the target task; (2) when the same feature extractor is shared between the pretext task and the downstream one and only different prediction heads are used, it is ineffective to enable inter-task information exchange and knowledge sharing. To address these issues, we propose a novel \textbf{S}elf-\textbf{S}upervised \textbf{G}raph Neural Network (SSG), where a graph neural network is used as the bridge to enable more effective inter-task information exchange and knowledge sharing. More expressive representation is learned by adopting a mask token strategy to mask some domain information. Our extensive experiments have demonstrated that our proposed SSG method has achieved state-of-the-art results over four multi-source domain adaptation datasets, which have shown the effectiveness of our proposed SSG method from different aspects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_05104 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation Yuan, Jin Hou, Feng Du, Yangzhou Shi, Zhongchao Geng, Xin Fan, Jianping Rui, Yong Machine Learning Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data, and multi-source domain adaptation (MSDA) is very attractive for real world applications. By learning from large-scale unlabeled samples, self-supervised learning has now become a new trend in deep learning. It is worth noting that both self-supervised learning and multi-source domain adaptation share a similar goal: they both aim to leverage unlabeled data to learn more expressive representations. Unfortunately, traditional multi-task self-supervised learning faces two challenges: (1) the pretext task may not strongly relate to the downstream task, thus it could be difficult to learn useful knowledge being shared from the pretext task to the target task; (2) when the same feature extractor is shared between the pretext task and the downstream one and only different prediction heads are used, it is ineffective to enable inter-task information exchange and knowledge sharing. To address these issues, we propose a novel \textbf{S}elf-\textbf{S}upervised \textbf{G}raph Neural Network (SSG), where a graph neural network is used as the bridge to enable more effective inter-task information exchange and knowledge sharing. More expressive representation is learned by adopting a mask token strategy to mask some domain information. Our extensive experiments have demonstrated that our proposed SSG method has achieved state-of-the-art results over four multi-source domain adaptation datasets, which have shown the effectiveness of our proposed SSG method from different aspects. |
| title | Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2204.05104 |