Unverified50% confidenceFactExact time
Heterogeneity in federated learning refers to the degree to which each client's local data distribution deviates from the global distribution, commonly quantified with Dirichlet distribution parameters, label distribution divergence (such as KL divergence), or feature distances between clients.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedDistribution shift refers to the systematic difference between the statistical distribution of data seen during model training and the distribution of data in the actual deployment environment.70% similarUnverifiedKL divergence is an asymmetric metric measuring the difference between two probability distributions, and in reinforcement learning it is used to constrain the degree of deviation between the new and old policies (such as PPO's trust region).68% similarUnverifiedWhen using kernel methods or local polynomial estimation for CATE, the local structure of the covariate distribution (such as spikes, discontinuities or irregular clustering) is directly reflected in the convergence behavior of the estimator.67% similarUnverifiedA generative distribution embedding (GDE) is a method for representing probability distributions with a parameterized generative model, learning a mapping from low-dimensional latent variables to the state space, while using an encoder to map observation histories to a distribution over latent variables.64% similarUnverifiedA classification head is typically a simple fully connected layer with Softmax activation that maps a high-dimensional feature vector to a probability distribution over each category.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113990API
curl https://kongchang.com/api/v1/knowledge/claims/1113990MCP
get_claim(id=1113990)