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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use SkipE-RNN instead of fixed-structure vanilla RNN tanh | SkipE-RNN · Electricity, Hyperplane, Sea, P-MNIST | classification rate: 65.12 -> 77.75 (Electricity) | Improved |
| increase label delay from 0 to 50 or 500 | SkipE-RNN · Electricity, Hyperplane, Sea, P-MNIST | classification rate: 77.75 -> 75.01 (delta 50, Electricity) | Hurt |
| SkipE-RNN vs SCARGC under infinite label delay | SkipE-RNN · MG 2C 2D | accuracy: 61.91 -> 87.31 | Improved |
| SkipE-RNN vs SCARGC under infinite label delay | SkipE-RNN · GEARS 2C 2D | accuracy: 95.60 -> 95.61 | No clear effect |
| SkipE-RNN vs SCARGC under infinite label delay | SkipE-RNN · UG 2C 5D | accuracy: 79.98 -> 91.92 | Improved |
| SkipE-RNN vs SCARGC | SkipE-RNN · Run-time, infinite delay | run-time (s): 16.10 -> 72.27 (GEARS) | Hurt |
Closest papers by meaning
- SkipW: Resource Adaptable RNN with Strict Upper Computational Limit (ICLR 2021 · similarity 0.86)
- Latency-Aware Adaptive Learning for Nonstationary Data Streams: Coordinating Concept Drift and Delayed Supervision (TPAMI 2026 · similarity 0.86)
- Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks (ICLR 2018 · similarity 0.86)
- RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients? (ICLR 2020 · similarity 0.85)
- Semi-Supervised Streaming Learning with Emerging New Labels (AAAI 2020 · similarity 0.85)
- Online Boosting Adaptive Learning under Concept Drift for Multistream Classification (AAAI 2024 · similarity 0.83)
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.
