방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 자기 지도 연합 학습× | 자기 지도 학습× | |
|---|---|---|
| 분야 | 머신러닝 | 머신러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2021–2022 | 2018–2020 |
| 창시자≠ | McMahan et al. (federated); Zhuang et al. and others (federated SSL combination) | LeCun, Y. and community (formalized ~2018–2020) |
| 유형≠ | Federated self-supervised pretraining paradigm | Representation learning paradigm |
| 원전≠ | Zhuang, W., Wen, Y., & Zhang, S. (2021). Divergence-aware Federated Self-Supervised Learning. In International Conference on Learning Representations (ICLR 2022). link ↗ | 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/ link ↗ |
| 별칭 | FedSSL, Federated Self-supervised Learning, Federated Contrastive Learning, Self-supervised Federated Pretraining | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| 관련≠ | 5 | 3 |
| 요약≠ | Self-supervised Federated Learning combines federated training — where data never leaves local devices — with self-supervised pretext tasks such as contrastive learning or masked prediction. Clients learn general-purpose representations from their own unlabeled data and share only model updates, not raw data, with a central server that aggregates them into a global encoder. | 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. |
| ScholarGate데이터셋 ↗ |
|
|