So sánh phương pháp

	LightGBM tự giám sát	Học tăng cường tự giám sát
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2017–2020	2018–2020
Người khởi xướng	Ke, G. et al. (LightGBM); self-supervised paradigm adapted from broader SSL literature	LeCun, Y. and community (formalized ~2018–2020)
Loại	Hybrid (self-supervised pretraining + gradient boosting)	Representation learning paradigm
Công trình gốc	Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Advances in Neural Information Processing Systems, 30.	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/
Tên gọi khác	SSL-LightGBM, self-supervised gradient boosting, pretraining LightGBM, pseudo-label LightGBM	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Liên quan	6	3
Tóm tắt	Self-supervised LightGBM combines the self-supervised learning paradigm with the LightGBM gradient boosting framework to exploit large volumes of unlabeled tabular data. A self-supervised pretext task — such as masked feature prediction or contrastive corruption — generates rich feature representations or pseudo-labels that are then used to train or fine-tune a LightGBM model, substantially improving performance in label-scarce regimes.	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.