AI Paper Atlas

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

The Semantic Architect: How FEAML Bridges Structured Data and LLMs for Multi-Label Tasks

Wanfu Gao, Zebin He, Jun Gao

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
use FEAML features instead of no feature generation (Base)downstream classifier · adultAccuracy: 0.6183 -> 0.6312Improved
use FEAML instead of CAAFEFEAML vs CAAFE · communitiesAccuracy: 0.5301 -> 0.5478Improved
use FEAML instead of CAAFEFEAML vs CAAFE · myocardialAccuracy: 0.1395 -> 0.1355Hurt
use FEAML instead of FeatLLMFEAML vs FeatLLM · myocardialHamming Loss: 0.1275 -> 0.1277No clear effect
use FEAML instead of FeatLLMFEAML vs FeatLLM · bankF1-score (micro): 0.6534 -> 0.6724Improved
use FEAML instead of Base with Random ForestFEAML · adult (RF downstream)Accuracy: 0.6062 -> 0.6602Improved
use FEAML instead of Base with MLKNNFEAML · adult (MLKNN downstream)Accuracy: 0.5469 -> 0.6693Improved
use FEAML instead of AFAT with RFFEAML vs AFAT · adult (RF downstream)Accuracy: 0.5945 -> 0.6602Improved
add structured metadata prompts (ablation)FEAML · adult, bank, communities, credit-gHamming LossImproved
add label co-occurrence prompts (ablation)FEAML · adult, bank, communities, credit-gHamming LossImproved

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