A typed tensor language formalizes federated computations via virtual global tensor semantics and proves shared-state factorization for one-round and iterative programs, plus a differentiable fragment for gradient descent.
FBFL : a field-based coordination approach for data heterogeneity in federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Typed Tensor Language for Federated Learning
A typed tensor language formalizes federated computations via virtual global tensor semantics and proves shared-state factorization for one-round and iterative programs, plus a differentiable fragment for gradient descent.