DNG-Encoder represents NN weights as dynamic graphs to preserve sequential inference and powers INR2JLS, which raises INR classification accuracy by ~10% on CIFAR-100-INR.
Permutation equivariant neural functionals.Advances in Neural Information Processing Systems, 36, 2024a
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
-
Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space
DNG-Encoder represents NN weights as dynamic graphs to preserve sequential inference and powers INR2JLS, which raises INR classification accuracy by ~10% on CIFAR-100-INR.