GrapNet defines a graph-as-architecture neural substrate with node-owned child references and allocation vectors that supports structural edits and shows accuracy gains over MLPs in continual learning on Split Fashion-MNIST and CIFAR-10.
arXiv preprint arXiv:2305.02299 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
Growth during training inserts new units into a specialized trajectory, making them forward-active but backward-starved with weaker gradients than existing units.
citing papers explorer
-
GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate
GrapNet defines a graph-as-architecture neural substrate with node-owned child references and allocation vectors that supports structural edits and shows accuracy gains over MLPs in continual learning on Split Fashion-MNIST and CIFAR-10.
-
HORST: Composing Optimizer Geometries for Sparse Transformer Training
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
-
On the Stability of Growth in Structural Plasticity
Growth during training inserts new units into a specialized trajectory, making them forward-active but backward-starved with weaker gradients than existing units.