Research map / Time series / Long-term forecasting
Directional Label Rectification in Adaptive Graph
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| select features and instances simultaneously with an adaptive graph (DRAG) instead of separate sequential steps | DRAG vs category 1-3 baselines · Data A and Data B, instance stability | F1-score of event class | Helped |
| use DRAG instead of comparison methods | failure analysis · real world Data A and Data B | F1-score: at least 15% | Helped |
| use DRAG instead of comparison methods with few selected features | DRAG · synthetic data, feature stability | F1-score | Helped |
| increase number of selected instances q | comparison methods · synthetic data, instance stability | F1-score | Hurt |
| increase number of selected instances q | DRAG · synthetic data, instance stability | F1-score | No clear effect |
| vary size of Xa from 30 to 90 | DRAG · synthetic data | F1 against ground truth | No clear effect |
| vary size of Xa from 30 to 90 | comparison methods · synthetic data | F1 against ground truth | Hurt |
| use smaller affinity matrix between Xa and Xb instead of full graph (DRAG vs Coselect) | DRAG · Data B, varying size of Xb | running time | Helped |
| learn an adaptive graph in each iteration instead of a fixed affinity graph | DRAG · real world data | F1-score | Helped |
Closest papers by meaning
- Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning (NeurIPS 2026 · similarity 0.83)
- Graph Anomaly Detection via Prototype-Aware Label Propagation (Student Abstract) (AAAI 2024 · similarity 0.82)
- Multi-Scale Dynamic Graph Learning for Time Series Anomaly Detection (Student Abstract) (AAAI 2024 · similarity 0.82)
- Motif-aware Graph Neural Networks for Networked Time Series Imputation (AAAI 2025 · similarity 0.82)
- Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection (AAAI 2025 · similarity 0.82)
- Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification (NeurIPS 2026 · similarity 0.81)
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.