AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

LabelKAN - Kolmogorov-Arnold Networks for Inter-Label Learning: Avian Community Learning

Marc Grimson, Joshua Fan, Courtney L. Davis, Dylan van Bramer, Daniel Fink, Carla P. Gomes

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 0 citations (OpenAlex)

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
add LabelKAN headsNN · eBird presence-absenceAUPRC micro: 0.600 -> 0.624Improved
add LabelKAN headsNN · eBird presence-absenceAUPRC macro: 0.408 -> 0.434Improved
add LabelKAN headsDMVP · eBird presence-absenceAUPRC macro: 0.410 -> 0.436Improved
add LabelKAN headsVAE · eBird presence-absenceAUPRC micro: 0.612 -> 0.631Improved
add LabelKAN headsVAE · eBird presence-absenceAUPRC macro: 0.421 -> 0.446Improved
add LabelKAN headsVAE · eBird presence-absenceAUROC macro: 0.916 -> 0.921Improved
add LabelKAN headsSINR · eBird S&T presence-onlymean average precision: 0.494 -> 0.534Improved
use KAN instead of standard neural network as label learner (ablation)VAE · eBird presence-absenceAUPRC macro: 0.414 -> 0.446Improved
use KAN instead of standard neural network as label learner (ablation)VAE · eBird presence-absenceAUROC macro: 0.903 -> 0.921Improved
use KAN instead of standard neural network as label learner (ablation)VAE · per-species errorshare of species worse than base: nearly 25% -> 7.5%Improved

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