Machine learningDeep learning / NLP / CV
自监督 GRU
自监督 GRU 使用从无标签数据本身派生的自动构建的监督信号（例如，下一步预测或掩码标记恢复）来训练门控循环单元（Gated Recurrent Unit, GRU）网络。然后，学习到的序列表示在小型有标签数据集上进行微调，从而在标注稀缺的情况下实现高质量的序列建模。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014. link ↗
- Liu, X., Zhang, F., Hou, Z., Mian, L., Wang, Z., Zhang, J., & Tang, J. (2023). Self-Supervised Learning: Generative or Contrastive. IEEE Transactions on Knowledge and Data Engineering, 35(1), 857–876. DOI: 10.1109/TKDE.2021.3090866 ↗
如何引用本页
ScholarGate. (2026, June 3). Self-supervised Gated Recurrent Unit. ScholarGate. https://scholargate.app/zh/deep-learning/self-supervised-gru
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- 门控循环单元 (GRU)深度学习↔ compare
- 长短期记忆网络（LSTM）深度学习↔ compare
- 自监督Transformer深度学习↔ compare
- 半监督门控循环单元 (Semi-supervised GRU)深度学习↔ compare