Imagen de Portada

Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mao, Yuhao, Zhang, Yani, Vechev, Martin
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning Compact Boolean Networks
por: Wang, Shengpu, et al.
Publicado: (2026)

CTBENCH: A Library and Benchmark for Certified Training
por: Mao, Yuhao, et al.
Publicado: (2024)

Dual Randomized Smoothing: Beyond Global Noise Variance
por: Sun, Chenhao, et al.
Publicado: (2025)

Understanding Certified Training with Interval Bound Propagation
por: Mao, Yuhao, et al.
Publicado: (2023)

The Cost of Relaxation: Evaluating the Error in Convex Neural Network Verification
por: Papamichail, Merkouris, et al.
Publicado: (2026)

NeuronSeek: On Stability and Expressivity of Task-driven Neurons
por: Pei, Hanyu, et al.
Publicado: (2025)

Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations
por: Balauca, Stefan, et al.
Publicado: (2024)

On the Expressive Power of Graph Neural Networks
por: Nalwade, Ashwin, et al.
Publicado: (2024)

Extracting Formulae in Many-Valued Logic from Deep Neural Networks
por: Zhang, Yani, et al.
Publicado: (2024)

Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints
por: Azizi, Niloofar, et al.
Publicado: (2024)

Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
por: Schnaus, Dominik, et al.
Publicado: (2023)

Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks
por: Mohammadizadeh, Mahdi, et al.
Publicado: (2024)

Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
por: Spieler, Aaron, et al.
Publicado: (2026)

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
por: Jiang, Fengqing, et al.
Publicado: (2026)

Transferrable Surrogates in Expressive Neural Architecture Search Spaces
por: Qin, Shiwen, et al.
Publicado: (2025)

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency
por: Liu, Zongxin, et al.
Publicado: (2024)

Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting
por: Jin, Ming, et al.
Publicado: (2023)

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
por: Rao, Xuan, et al.
Publicado: (2022)

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
por: Yu, Lijia, et al.
Publicado: (2025)

Will More Expressive Graph Neural Networks do Better on Generative Tasks?
por: Zou, Xiandong, et al.
Publicado: (2023)

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
por: Spieler, Aaron, et al.
Publicado: (2023)

Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
por: Lin, Tzu-Yuan, et al.
Publicado: (2023)

Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Physical Dynamics Learning
por: Zheng, Zinan, et al.
Publicado: (2024)

Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification
por: Marzari, Luca, et al.
Publicado: (2025)

Watermark Stealing in Large Language Models
por: Jovanović, Nikola, et al.
Publicado: (2024)

AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs
por: Ünsal, Mert, et al.
Publicado: (2024)

BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs
por: Petrov, Ivo, et al.
Publicado: (2025)

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
por: Yukhymenko, Hanna, et al.
Publicado: (2026)

Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks
por: Dorszewski, Teresa, et al.
Publicado: (2024)

Influence Functions for Edge Edits in Non-Convex Graph Neural Networks
por: Heo, Jaeseung, et al.
Publicado: (2025)

Neural Control and Certificate Repair via Runtime Monitoring
por: Yu, Emily, et al.
Publicado: (2024)

Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs
por: Beddar-Wiesing, Silvia, et al.
Publicado: (2022)

Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks
por: Liu, Cong, et al.
Publicado: (2024)

Back to the Drawing Board for Fair Representation Learning
por: Pouget, Angéline, et al.
Publicado: (2024)

Widening the Gap: Exploiting LLM Quantization via Outlier Injection
por: Zhan, Xiaohua, et al.
Publicado: (2026)

MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing
por: Wu, Chaokai, et al.
Publicado: (2026)

FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
por: Lorenz, Tobias, et al.
Publicado: (2024)

SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression
por: Li, Jingyang, et al.
Publicado: (2026)

An Empirical Study of Realized GNN Expressiveness
por: Wang, Yanbo, et al.
Publicado: (2023)

No One-Size-Fits-All Neurons: Task-based Neurons for Artificial Neural Networks
por: Fan, Feng-Lei, et al.
Publicado: (2024)