Research map / Graph learning / Graph self-supervised learning
A Self-Supervised Mixed-Curvature Graph Neural Network
Li Sun, Zhongbao Zhang, Junda Ye, Hao Peng, Jiawei Zhang, Sen Su, Philip S Yu
This paper tried a common change: Add a contrastive loss
Add cross-view contrastive learning to the mixed-curvature model · Node classification · classification accuracy Improved
What 1,317 accepted papers report for this change
- 1,253 improved
- 22 no clear effect
- 16 mixed
- 26 hurt
- Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering ICML 2026 · add contrastive learning · SearchSnippets · ACC: 56.65 -> 80.12Improved
- SleepLM: Natural-Language Intelligence for Human Sleep ICML 2026 · add contrastive objective to captioning (CoCa vs Cap) · sleep event IoU · IoU: 29.2 -> 27.4Hurt
- LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations ICML 2026 · add contrastive loss L_con · FS1000 average · Spearman correlation: 0.759 -> 0.789Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 a mixed-curvature space instead of a single constant-curvature space (ablation) | SelfMGNN · Node classification | classification accuracy | Improved |
| Add cross-view contrastive learning to the mixed-curvature model (ablation) | SelfMGNN · Node classification | classification accuracy | Improved |
| Use multiple hyperbolic and spherical components rather than one of each (ablation) | SelfMGNN · Node classification | classification accuracy | Improved |
| Allow the hyperbolic and spherical components to have distinct learnable curvatures | SelfMGNN · Real-world graph datasets | learned component curvature | Mixed |
Closest papers by meaning
- Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces (AAAI 2023 · similarity 0.90)
- Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning (AAAI 2024 · similarity 0.90)
- Spectro-Riemannian Graph Neural Networks (ICLR 2025 · similarity 0.88)
- Discrete Curvature Graph Information Bottleneck (AAAI 2025 · similarity 0.86)
- Effective Structural Encodings via Local Curvature Profiles (ICLR 2024 · similarity 0.86)
- Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction (NeurIPS 2025 · similarity 0.86)
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.
