AI Paper Atlas

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

A Sequential Set Generation Method for Predicting Set-Valued Outputs

Tian Gao, Jie Chen, Vijil Chenthamarakshan, Michael Witbrock

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 3 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 a CNN lambda-optimizer instead of the sigmoid-network multi-label methodSSG · YEASTmF1: 0.430 -> 0.658Improved
use a CNN lambda-optimizer instead of the sigmoid-network multi-label methodSSG · SCENEmF1: 0.455 -> 0.605Improved
use an RNN lambda-optimizer instead of the sigmoid-network multi-label methodSSG · YEASTmF1: 0.430 -> 0.402Hurt
use an RNN lambda-optimizer instead of the sigmoid-network multi-label methodSSG · SCENEmF1: 0.455 -> 0.378Hurt
use a CNN lambda-optimizer instead of fixed position-specific penalties (ablation)SSG-S · Task 1mF1: 0.19 -> 0.70Improved
use a CNN lambda-optimizer instead of an RNN lambda-optimizer (ablation)SSG · Task 1mF1: 0.42 -> 0.70Improved
use an RNN lambda-optimizer instead of fixed position-specific penalties (ablation)SSG-S · Task 1mF1: 0.19 -> 0.42Improved
use a CNN lambda-optimizer instead of fixed position-specific penalties (ablation)SSG-S · Task 2mED: 8.10 -> 2.00Improved
use an RNN lambda-optimizer instead of fixed position-specific penalties (ablation)SSG-S · Task 2mED: 8.10 -> 3.75Improved
use a CNN lambda-optimizer instead of an RNN lambda-optimizer (ablation)SSG · Task 2mED: 3.75 -> 2.00Improved
use a CNN lambda-optimizer instead of the sigmoid-network multi-label methodSSG · Task 1mF1: 0.64 -> 0.70Improved

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