When Design Rules Break: Benchmark Composition Determines Whether Label Informativeness Predicts GNN Aggregator Choice
cs.LG, cs.SI
Submitted: 2026-06-08
Updated: 2026-08-29
Comments: We found an error in our training pipeline that affected the GIN-Mean results on high-degree graphs and inflated the reported GIN-Sum vs. GIN-Mean gaps. After fixing the pipeline, the main correlation is no longer significant (Spearman \r{ho} ? 0.01). We are withdrawing the paper and will upload an updated version once the ongoing study is complete
Code: https://github.com/nehasharmacs/aggregator-rule-supplement
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks