Copertina

Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Meynent, Léo, Melev, Ivan, Schürholt, Konstantin, Kauermann, Göran, Borth, Damian
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Model Zoo of Vision Transformers
di: Falk, Damian, et al.
Pubblicazione: (2025)

Learning Model Representations Using Publicly Available Model Hubs
di: Falk, Damian, et al.
Pubblicazione: (2025)

A Model Zoo on Phase Transitions in Neural Networks
di: Schürholt, Konstantin, et al.
Pubblicazione: (2025)

The Impact of Model Zoo Size and Composition on Weight Space Learning
di: Falk, Damian, et al.
Pubblicazione: (2025)

Towards Scalable and Versatile Weight Space Learning
di: Schürholt, Konstantin, et al.
Pubblicazione: (2024)

Position: There Is No Free Bayesian Uncertainty Quantification
di: Melev, Ivan, et al.
Pubblicazione: (2025)

Hyper-Representations: Learning from Populations of Neural Networks
di: Schürholt, Konstantin
Pubblicazione: (2024)

Sample Weight Estimation Using Meta-Updates for Online Continual Learning
di: Hemati, Hamed, et al.
Pubblicazione: (2024)

Toward Dynamic Stability Assessment of Power Grid Topologies using Graph Neural Networks
di: Nauck, Christian, et al.
Pubblicazione: (2022)

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
di: Liang, Zhiyuan, et al.
Pubblicazione: (2025)

Dirac--Bianconi Graph Neural Networks -- Enabling Non-Diffusive Long-Range Graph Predictions
di: Nauck, Christian, et al.
Pubblicazione: (2024)

Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation
di: Sattarov, Timur, et al.
Pubblicazione: (2025)

Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
di: Sattarov, Timur, et al.
Pubblicazione: (2025)

FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation
di: Sattarov, Timur, et al.
Pubblicazione: (2024)

GraphGuard: Contrastive Self-Supervised Learning for Credit-Card Fraud Detection in Multi-Relational Dynamic Graphs
di: Reynisson, Kristófer, et al.
Pubblicazione: (2024)

Human-in-the-loop: Towards Label Embeddings for Measuring Classification Difficulty
di: Hechinger, Katharina, et al.
Pubblicazione: (2023)

Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesis
di: Sattarov, Timur, et al.
Pubblicazione: (2024)

Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' View
di: Gruber, Cornelia, et al.
Pubblicazione: (2023)

MD tree: a model-diagnostic tree grown on loss landscape
di: Zhou, Yefan, et al.
Pubblicazione: (2024)

A Survey of Weight Space Learning: Understanding, Representation, and Generation
di: Han, Xiaolong, et al.
Pubblicazione: (2026)

Recurrent Diffusion for Large-Scale Parameter Generation
di: Wang, Kai, et al.
Pubblicazione: (2025)

Revisiting Active Learning under (Human) Label Variation
di: Gruber, Cornelia, et al.
Pubblicazione: (2025)

BoostNet-WB: Adaptive Boosting with Neural Network Weak Learners and Weighted Bootstrap Resampling
di: Olshenbaum, Konstantin
Pubblicazione: (2025)

Leveraging Task Structures for Improved Identifiability in Neural Network Representations
di: Chen, Wenlin, et al.
Pubblicazione: (2023)

Nonparametric Two-Sample Test for Networks Using Joint Graphon Estimation
di: Sischka, Benjamin, et al.
Pubblicazione: (2023)

On the Structural Limitations of Weight-Based Neural Adaptation and the Role of Reversible Behavioral Learning
di: Konduru, Pardhu Sri Rushi Varma
Pubblicazione: (2026)

Approximation Capabilities of Feedforward Neural Networks with GELU Activations
di: Yakovlev, Konstantin, et al.
Pubblicazione: (2025)

Few Edges Are Enough: Few-Shot Network Attack Detection with Graph Neural Networks
di: Bilot, Tristan, et al.
Pubblicazione: (2025)

Energy Considerations for Large Pretrained Neural Networks
di: Mei, Leo, et al.
Pubblicazione: (2025)

Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
di: Jain, Rishabh, et al.
Pubblicazione: (2026)

Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough
di: Dobler, Konstantin, et al.
Pubblicazione: (2024)

Leverage-Weighted Conformal Prediction
di: Fadnavis, Shreyas
Pubblicazione: (2026)

Leveraging Classical Algorithms for Graph Neural Networks
di: Wu, Jason, et al.
Pubblicazione: (2025)

On the Effectiveness of Random Weights in Graph Neural Networks
di: Bui, Thu, et al.
Pubblicazione: (2025)

Weight-Space Linear Recurrent Neural Networks
di: Nzoyem, Roussel Desmond, et al.
Pubblicazione: (2025)

Simultaneous Weight and Architecture Optimization for Neural Networks
di: Huang, Zitong, et al.
Pubblicazione: (2024)

Neural Networks With Dense Weights Are Not Universal Approximators
di: Rauchwerger, Levi, et al.
Pubblicazione: (2026)

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
di: Kim, Jiwoo, et al.
Pubblicazione: (2026)

Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
di: Tian, Bowen, et al.
Pubblicazione: (2025)

Explaining Deep Neural Networks by Leveraging Intrinsic Methods
di: La Rosa, Biagio
Pubblicazione: (2024)