DeInfoReg trains deep networks with per-module local losses so gradients flow only within each module, improving accuracy and enabling pipeline parallelism, with speedups of up to 1.47x over single-GPU backpropagation.
Realizing synchronized parameter updating, dynamic layer accumulation, and forward shortcuts in supervised contrastive parallel learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DeInfoReg: A Decoupled Learning Framework for Better Training Throughput
DeInfoReg trains deep networks with per-module local losses so gradients flow only within each module, improving accuracy and enabling pipeline parallelism, with speedups of up to 1.47x over single-GPU backpropagation.