AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Kronecker Generative Networks: A General Neural Architecture for Parameter-Efficient Learning Across Classification Tasks

Yang Yang, Zhengmin Kong, Yuan Liu, Tao Huang, Wei Xiang

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use full Kronecker-generated topology instead of a feed-forward chain (ablation)Helix5-C100 · CIFAR-100accuracy (%): 77.88% -> 79.55%Improved
add KGN-induced nodes over stem and final fusion node only (ablation)Helix5-C100 · CIFAR-100accuracy (%): 64.48% -> 79.55%Improved
use full KGN topology instead of chain with same atomic nodes (ablation)KGN-PAMAP2 · PAMAP2accuracy (%): 89.9% -> 95.6%Improved
add KGN module (ablation)KGN-PAMAP2 · PAMAP2accuracy (%): 84.8% -> 95.6%Improved
compare KGN-HAR to larger HS-ResNetKGN-HAR · UCI-HARaccuracy (%): 97.38% (HS-ResNet) vs 97.10% (KGN-HAR)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy