Research map / Graph learning / GNN architectures
Expressive Sign Equivariant Networks for Spectral Geometric Learning
Derek Lim, Joshua Robinson, Stefanie Jegelka, Haggai Maron
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 sign equivariant model instead of SignNet | edge representation model · Erdos-Renyi link prediction | test AUC: .498 -> .751 | Improved |
| use sign equivariant model instead of SignNet | edge representation model · Barabasi-Albert link prediction | test AUC: .707 -> .773 | Improved |
| update eigenvector representations with sign equivariant network instead of MLP(V_i * V_j) decoder (ablation) | edge model · Erdos-Renyi link prediction | test AUC: .614 -> .751 | Improved |
| use sign equivariant model instead of SignNet | edge model · Erdos-Renyi link prediction | runtime per epoch (s): .120 -> .063 | Improved |
| use sign equivariant model instead of frame averaging | n-body model · n-body d=3 | MSE: .00575 -> .00646 | Hurt |
| increase dimension d with sign equivariant model versus frame averaging | n-body model · n-body varying d | runtime | Improved |
| add sign equivariant model to GPS instead of no positional encoding | GPS · CLUSTER | test accuracy (%): 77.423 -> 78.201 | Improved |
| add sign equivariant model to GPS instead of SignNet | GPS · CLUSTER | test accuracy (%): 77.442 -> 78.201 | Improved |
| add sign equivariant model instead of PEG | GPS · CLUSTER | test accuracy (%): 77.945 -> 78.201 | Improved |
| add LapPE to GPS | GPS · CLUSTER | test accuracy (%): 77.423 -> 77.250 | No clear effect |
Closest papers by meaning
- Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? (NeurIPS 2024 · similarity 0.89)
- On the Expressive Power of Spectral Invariant Graph Neural Networks (ICML 2024 · similarity 0.88)
- On the Generalization of Equivariant Graph Neural Networks (ICML 2024 · similarity 0.88)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.87)
- Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum (NeurIPS 2025 · similarity 0.87)
- Universally Invariant Learning in Equivariant GNNs (NeurIPS 2025 · similarity 0.87)
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.
