Beyond Fixed Features: Architecture-Dependent Sensitivity to Node Representations under Heterophily

arXiv:2609.33764 · cs.LG, cs.AI, cs.IR · Submitted 2026-09-27 · Read on arXiv

cs.LG, cs.AI, cs.IR

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/priyanathmaji/graphdatasets

Terminology

• Benchmark — 54× in this paper · explained in 2 episodes
• Embeddings — 16× in this paper · explained in 2 episodes
• Transformer — 14× in this paper · explained in 2 episodes
• Aggregation — 12× in this paper · explained in 1 episode
• GNNs — 10× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• F1 Score — 4× in this paper · explained in 3 episodes
• Structural Control — 4× in this paper · explained in 2 episodes
• Balanced Accuracy — 3× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Graph Neural Networks (GNNs) — 2× in this paper · explained in 7 episodes
• Overall Accuracy — 2× in this paper
• Representation Learning — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Geometric Distribution — 1× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Over-smoothing — 1× in this paper · explained in 4 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs

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