HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration

arXiv:2609.32426 · cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/inu0104/HoTS

Terminology

• Calibration — 102× in this paper · explained in 7 episodes
• Accuracy — 30× in this paper · explained in 1 episode
• Temperature Scaling — 23× in this paper
• Benchmark — 21× in this paper · explained in 2 episodes
• Actor — 10× in this paper · explained in 3 episodes
• Contextual Stochastic Block Model — 6× in this paper
• Adam — 5× in this paper · explained in 2 episodes
• Clustering — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• GNNs — 4× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Expected Calibration Error — 2× in this paper
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fisher Information — 1× in this paper · explained in 3 episodes
• Graph Neural Networks (GNNs) — 1× in this paper · explained in 7 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semi-supervised Learning — 1× in this paper · explained in 4 episodes
• Vector Scaling — 1× in this paper

Sources

• Optimal Inference in Contextual Stochastic Block Models
• WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
• Is Homophily a Necessity for Graph Neural Networks?
• A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
• Pitfalls of Graph Neural Network Evaluation
• Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection
• Are Graph Neural Networks Miscalibrated?
• Graph Attention Networks

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