Image de couverture de livre

Surprisingly Strong Performance Prediction with Neural Graph Features

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kadlecová, Gabriela, Lukasik, Jovita, Pilát, Martin, Vidnerová, Petra, Safari, Mahmoud, Neruda, Roman, Hutter, Frank
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Transferrable Surrogates in Expressive Neural Architecture Search Spaces
par: Qin, Shiwen, et autres
Publié: (2025)

Efficient Search for Customized Activation Functions with Gradient Descent
par: Strack, Lukas, et autres
Publié: (2024)

Weight-Entanglement Meets Gradient-Based Neural Architecture Search
par: Sukthanker, Rhea Sanjay, et autres
Publié: (2023)

ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
par: Qin, Shiwen, et autres
Publié: (2025)

Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics
par: Das, Indrashis, et autres
Publié: (2025)

Utilizing Novelty-based Evolution Strategies to Train Transformers in Reinforcement Learning
par: Lorenc, Matyáš, et autres
Publié: (2025)

Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning
par: Lorenc, Matyáš, et autres
Publié: (2025)

Layered Quantum Architecture Search for 3D Point Cloud Classification
par: Meli, Natacha Kuete, et autres
Publié: (2026)

Smooth Model Compression without Fine-Tuning
par: Runkel, Christina, et autres
Publié: (2025)

How Usable is Automated Feature Engineering for Tabular Data?
par: Schäfer, Bastian, et autres
Publié: (2025)

Large Language Models Engineer Too Many Simple Features For Tabular Data
par: Küken, Jaris, et autres
Publié: (2024)

On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
par: Zhu, Jiong, et autres
Publié: (2024)

Beyond Surprise: Improving Exploration Through Surprise Novelty
par: Le, Hung, et autres
Publié: (2023)

Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks
par: Krzywda, Maciej, et autres
Publié: (2024)

SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
par: Zhang, Huopu, et autres
Publié: (2025)

Can We Talk Models Into Seeing the World Differently?
par: Gavrikov, Paul, et autres
Publié: (2024)

From Code to Prediction: Fine-Tuning LLMs for Neural Network Performance Classification in NNGPT
par: Hanouneh, Mahmoud, et autres
Publié: (2026)

Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
par: Mukherjee, Sagnik, et autres
Publié: (2026)

Chemically-Informed Machine Learning Approach for Prediction of Reactivity Ratios in Radical Copolymerization
par: Safari, Habibollah, et autres
Publié: (2025)

Regularized Neural Ensemblers
par: Arango, Sebastian Pineda, et autres
Publié: (2024)

Dirac--Bianconi Graph Neural Networks -- Enabling Non-Diffusive Long-Range Graph Predictions
par: Nauck, Christian, et autres
Publié: (2024)

Rethinking Performance Measures of RNA Secondary Structure Problems
par: Runge, Frederic, et autres
Publié: (2023)

An Augmented Surprise-guided Sequential Learning Framework for Predicting the Melt Pool Geometry
par: Raihan, Ahmed Shoyeb, et autres
Publié: (2024)

c-TPE: Tree-structured Parzen Estimator with Inequality Constraints for Expensive Hyperparameter Optimization
par: Watanabe, Shuhei, et autres
Publié: (2022)

Fast Tensorization of Neural Networks via Slice-wise Feature Distillation
par: Hamreras, Safa, et autres
Publié: (2026)

RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction
par: Asadi, Anahita, et autres
Publié: (2025)

Surprisal-Rényi Free Energy
par: Matsumoto, Shion, et autres
Publié: (2026)

Mind the Gap: Measuring Generalization Performance Across Multiple Objectives
par: Feurer, Matthias, et autres
Publié: (2022)

Position: The Future of Bayesian Prediction Is Prior-Fitted
par: Müller, Samuel, et autres
Publié: (2025)

Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
par: Liu, Mingxuan, et autres
Publié: (2023)

Bayes' Power for Explaining In-Context Learning Generalizations
par: Müller, Samuel, et autres
Publié: (2024)

A General Framework for User-Guided Bayesian Optimization
par: Hvarfner, Carl, et autres
Publié: (2023)

Early Stopping Tabular In-Context Learning
par: Küken, Jaris, et autres
Publié: (2025)

Causal Data Augmentation for Robust Fine-Tuning of Tabular Foundation Models
par: Bühler, Magnus, et autres
Publié: (2026)

React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN
par: Barbara, Nicholas H., et autres
Publié: (2025)

Adaptive Node Feature Selection For Graph Neural Networks
par: Navarro, Madeline, et autres
Publié: (2025)

Topological Feature Compression for Molecular Graph Neural Networks
par: Khorana, Rahul
Publié: (2025)

Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection
par: Özer, Kadir-Kaan, et autres
Publié: (2026)

GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment
par: Hou, Zhenyu, et autres
Publié: (2024)

Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization
par: Carstensen, Timur, et autres
Publié: (2025)