Spectral Analysis of Molecular Features: When Richer Features Do Not Guarantee Better Generalization

arXiv:2510.14217 · cs.LG, physics.chem-ph · Submitted 2025-10-16 · Read on arXiv

cs.LG, physics.chem-ph

Submitted: 2025-10-16

Updated: 2026-10-02

Code: https://github.com/Asma-Jamali/spectral-molecular-kernels

Terminology

• Generalization — 4× in this paper · explained in 13 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Kernel Ridge Regression — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Self-Supervised Learning (SSL) — 1× in this paper · explained in 4 episodes

Sources

• ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
• Molecular representation learning with language models and domain-relevant auxiliary tasks
• The Low-Rank Simplicity Bias in Deep Networks
• TGNN: A Joint Semi-supervised Framework for Graph-level Classification
• Equivariant Graph Attention Networks for Molecular Property Prediction
• Molecule Attention Transformer
• ADMET property prediction through combinations of molecular fingerprints
• Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning
• A Large Encoder-Decoder Family of Foundation Models For Chemical Language
• Gaussian Processes with Spectral Delta kernel for higher accurate Potential Energy surfaces for large molecules

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks