Verified65% confidenceFactExact time
If only the data of newly added classes is used to fine-tune an expanded classification head, the model is highly prone to catastrophic forgetting, rapidly losing its ability to recognize the original classes.
3
Sources
65%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
BERT新增分类类别：增量微调的三种策略与灾难性遗忘解法
Related Claims
UnverifiedDuring model collapse, the model gradually loses the long-tail portions of the data distribution and ultimately converges to monotonous, repetitive, and diversity-lacking outputs.76% similarUnverified由于历史记录同样受影响，模型名称消失更可能是前端统一显示逻辑层的问题，而非底层数据丢失74% similarUnverified用新数据更新模型时可能破坏原有能力，即灾难性遗忘，工业界通过失败案例库、数据增强与混合回放技术来整合新数据74% similarUnverifiedIf a generative model merely memorizes historical data, it creates a false sense of security without any benefit to backtesting, and ensuring that generated samples are both realistic and diverse is the core challenge.73% similarUnverifiedGradient-based methods often overwrite old knowledge when learning new tasks, causing catastrophic forgetting, whereas population-based evolutionary systems naturally maintain an archive of solution diversity.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/502636API
curl https://kongchang.com/api/v1/knowledge/claims/502636MCP
get_claim(id=502636)