Research map / Label-efficient and robust learning / Noisy labels
Overlap-Robust Decision Boundary Learning for Within-Network Classification
Sharad Nandanwar, M. N. Murty
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 |
|---|---|---|---|
| add homophily regularizer to ridge in structural-loss ReSLMin (ablation) | ReSLMin · PubMed | Micro F1 (%): 80.23±0.10 -> 80.83±0.04 | Improved |
| add homophily regularizer to ridge (ablation) | ReSLMin · CoRA | Micro F1 (%): 76.43±0.07 -> 77.49±0.07 | Improved |
| add homophily regularizer to ridge (ablation) | ReSLMin · Wikipedia | Micro F1 (%): 71.67±0.12 -> 73.65±0.11 | Improved |
| add homophily regularizer to ridge (ablation) | ReSLMin · Amazon | Micro F1 (%): 66.77±0.06 -> 66.75±0.03 | No clear effect |
| use homophily regularizer alone instead of combination (ablation) | ReSLMin · Amazon | Micro F1 (%): 66.75±0.03 -> 67.03±0.04 | Improved |
| replace Laplacian regularizer by Ridge+Homophily (ablation) | ReSLMin · Wikipedia | Micro F1 (%): 69.19±0.08 -> 73.65±0.11 | Improved |
| replace Laplacian regularizer by Ridge+Homophily (ablation) | ReSLMin · Amazon | Micro F1 (%): 66.56±0.04 -> 66.75±0.03 | No clear effect |
| ReSLMin Ridge+Homophily vs SNBC | ReSLMin · CoRA | Micro F1 (%): 67.39±2.24 -> 77.49±0.07 | Improved |
| ReSLMin Ridge+Homophily vs DeepWalk | ReSLMin · Amazon | Micro F1 (%): 31.98±0.03 -> 66.75±0.03 | Improved |
| ReSLMin Ridge+Homophily vs SDEC | ReSLMin · PubMed | Micro F1 (%): 56.89±0.01 -> 80.83±0.04 | Improved |
| ReSLMin Ridge+Homophily vs SCRN | ReSLMin · Wikipedia | Micro F1 (%): 71.98±1.22 -> 73.65±0.11 | Mixed |
| increase LFR mixing coefficient beyond 0.25 (class overlap), ReSLMin vs SNBC | ReSLMin · LFR synthetic 10000 nodes | accuracy | Improved |
Closest papers by meaning
- From Link Prediction to Linear Community Detection: A Finite-Sample Guarantee for Graph Pretraining (NeurIPS 2026 · similarity 0.87)
- Posterior Label Smoothing for Node Classification (AAAI 2026 · similarity 0.86)
- Diffusion Probabilistic Models for Structured Node Classification (NeurIPS 2023 · similarity 0.86)
- Neural Structured Prediction for Inductive Node Classification (ICLR 2022 · similarity 0.86)
- Disentangled Partial Label Learning (AAAI 2024 · similarity 0.85)
- Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning (ICML 2024 · similarity 0.85)
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.
