Unverified50% confidenceFactExact time
In the class-incremental graph learning scenario of graph neural networks, as new classes arrive one after another the model exhibits catastrophic forgetting, and predictions are often dominated by the most recently learned classes, producing recency bias.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
Unverified灾难性遗忘是指模型在学习新知识时可能覆盖已有知识的现象74% similarUnverifiedA memory state that accurately reproduces all predictions of the current model may have already lost the ability to continue learning from the next observation.73% similarUnverifiedMachine learning models may overfit specific training samples and inadvertently reproduce details of the original data when generating content, a phenomenon known as training data memorization.73% similarUnverified大模型中的参数在数学上是神经网络每条连接边上的权重数值和偏置值，训练前随机初始化，通过反向传播算法和梯度下降不断调整73% similarUnverified模型对 schema 的遵循能力受训练数据分布影响，训练语料中高频出现的字段组合会导致模型产生幻觉字段72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033023API
curl https://kongchang.com/api/v1/knowledge/claims/1033023MCP
get_claim(id=1033023)