Unverified50% confidenceDecision RuleExact time
In transfer learning practice, the smaller the amount of data for the new task, the more layers should be frozen to prevent overfitting; the learning rate should be much smaller than when training from scratch; if the new data differs greatly in distribution from the pretraining data, more layers often need to be fine-tuned.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverified当目标数据域与源数据域差异悬殊时，预训练权重可能产生负迁移（Negative Transfer），反而干扰目标域的学习78% similarVerifiedDuring cross-domain fine-tuning, an excessively large learning rate will destroy pre-trained weights, while an excessively small one will result in almost no learning, requiring a careful trade-off.76% similarUnverified冻结基准可能因数据泄露被纳入模型训练数据而随时间失去区分力，这是一个权衡76% similarUnverifiedFederated learning faces challenges: model updates may leak statistical features of training data through gradient inversion attacks, and large distribution differences across vehicle data can cause non-IID problems that lead to convergence difficulties or performance degradation.75% similarUnverifiedIf the dataset is small while the model has too many parameters, the model may memorize the training data prematurely and degenerate; this can be mitigated by adding more data, applying dropout regularization, or reducing model size.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018469API
curl https://kongchang.com/api/v1/knowledge/claims/1018469MCP
get_claim(id=1018469)