AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

A Skip-Connected Evolving Recurrent Neural Network for Data Stream Classification under Label Latency Scenario

Monidipa Das, Mahardhika Pratama, Jie Zhang, Yew Soon Ong

AAAI 2020 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 18 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 SkipE-RNN instead of fixed-structure vanilla RNN tanhSkipE-RNN · Electricity, Hyperplane, Sea, P-MNISTclassification rate: 65.12 -> 77.75 (Electricity)Improved
increase label delay from 0 to 50 or 500SkipE-RNN · Electricity, Hyperplane, Sea, P-MNISTclassification rate: 77.75 -> 75.01 (delta 50, Electricity)Hurt
SkipE-RNN vs SCARGC under infinite label delaySkipE-RNN · MG 2C 2Daccuracy: 61.91 -> 87.31Improved
SkipE-RNN vs SCARGC under infinite label delaySkipE-RNN · GEARS 2C 2Daccuracy: 95.60 -> 95.61No clear effect
SkipE-RNN vs SCARGC under infinite label delaySkipE-RNN · UG 2C 5Daccuracy: 79.98 -> 91.92Improved
SkipE-RNN vs SCARGCSkipE-RNN · Run-time, infinite delayrun-time (s): 16.10 -> 72.27 (GEARS)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