Unverified50% confidenceConceptExact time
Semi-supervised federated learning (SSFL) trains an initial model using a small amount of labeled seed data on the server side, then uses a teacher model to generate pseudo-labels for large volumes of unlabeled client data, thereby optimizing the model without uploading raw audio.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe typical approach in SSOD is a teacher-student framework, in which the teacher model generates pseudo boxes for unlabeled data, the student model learns on labeled data and high-confidence pseudo labels, and the teacher is updated via EMA75% similarUnverifiedIn offline distillation, training data is generated once by the teacher model and fixed, with the student model learning from a static dataset.70% similarUnverifiedUsing large-scale pre-trained models (such as Whisper and HuBERT) as a foundation for fine-tuning on specific tasks allows small datasets to be reframed as few-shot fine-tuning scenarios.69% similarUnverified少样本学习通过在Prompt中提供2-5个示例帮助模型快速理解输出格式和风格要求69% similarUnverifiedSupervised Fine-Tuning (SFT) trains the model using 'prompt-response' example pairs, teaching the model to respond in a conversational format, thereby making outputs more coherent.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948095API
curl https://kongchang.com/api/v1/knowledge/claims/948095MCP
get_claim(id=948095)