Unverified50% confidenceFactExact time
The paper finds that the commonly used Mean Pairwise Distance is not the best choice, and that Graph Entropy performs better overall.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedComputing Graph Entropy typically involves constructing a k-nearest-neighbor graph and computing eigenvalues or random-walk entropy; its complexity is higher than simple distance averaging, but it is feasible on medium-sized datasets.73% similarUnverifiedThere is a weak but consistent negative correlation between split entropy and node accuracy: the higher the entropy, the more likely the node judgment is to err.69% similarUnverifiedThe paper introduces an entropy-regularized loss to prevent the routing distribution from becoming overly concentrated, encouraging a more diverse routing distribution.65% similarUnverified标准交叉熵损失在目标占图像面积较小时会导致严重的类别不平衡问题，模型倾向于全部预测为背景65% similarUnverifiedIn high-dimensional spaces, distances between data points tend to become uniform, causing distance-based algorithms to perform significantly worse; this is called the curse of dimensionality64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074757API
curl https://kongchang.com/api/v1/knowledge/claims/1074757MCP
get_claim(id=1074757)