Copertina

GNNMerge: Merging of GNN Models Without Accessing Training Data

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Garg, Vipul, Thakre, Ishita, Ranu, Sayan
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

GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability
di: Armgaan, Burouj, et al.
Pubblicazione: (2025)

GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
di: Kosan, Mert, et al.
Pubblicazione: (2023)

Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
di: Gupta, Mridul, et al.
Pubblicazione: (2026)

Mirage: Model-Agnostic Graph Distillation for Graph Classification
di: Gupta, Mridul, et al.
Pubblicazione: (2023)

EUGENE: Explainable Structure-aware Graph Edit Distance Estimation with Generalized Edit Costs
di: Bommakanti, Aditya, et al.
Pubblicazione: (2024)

Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems
di: Bishnoi, Suresh, et al.
Pubblicazione: (2022)

GRAIL: Graph Edit Distance and Node Alignment Using LLM-Generated Code
di: Verma, Samidha, et al.
Pubblicazione: (2025)

NeuroCUT: A Neural Approach for Robust Graph Partitioning
di: Shah, Rishi, et al.
Pubblicazione: (2023)

Bonsai: Gradient-free Graph Condensation for Node Classification
di: Gupta, Mridul, et al.
Pubblicazione: (2024)

Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
di: Tang, Anke, et al.
Pubblicazione: (2025)

MassiveGNN: Efficient Training via Prefetching for Massively Connected Distributed Graphs
di: Sarkar, Aishwarya, et al.
Pubblicazione: (2024)

GRAPHGINI: Fostering Individual and Group Fairness in Graph Neural Networks
di: Sirohi, Anuj Kumar, et al.
Pubblicazione: (2024)

Revealing Interpretable Failure Modes of VLMs
di: Chaudhary, Isha, et al.
Pubblicazione: (2026)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
di: Wang, Jiapeng, et al.
Pubblicazione: (2026)

DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training
di: Liu, Renjie, et al.
Pubblicazione: (2024)

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
di: Huang, Kezhao, et al.
Pubblicazione: (2023)

Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access
di: Gaur, Mudit, et al.
Pubblicazione: (2025)

Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
di: Zhou, Wenjie, et al.
Pubblicazione: (2026)

Panorama: Fast-Track Nearest Neighbors
di: Ramani, Vansh, et al.
Pubblicazione: (2025)

Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents
di: Sarkar, Aishwarya, et al.
Pubblicazione: (2026)

Adaptive Graph Coarsening for Efficient GNN Training
di: Olshevskyi, Rostyslav, et al.
Pubblicazione: (2025)

Cyborg Data: Merging Human with AI Generated Training Data
di: North, Kai, et al.
Pubblicazione: (2025)

Optimization of GNN Training Through Half-precision
di: Tarafder, Arnab Kanti, et al.
Pubblicazione: (2024)

Training-free Heterogeneous Model Merging
di: Xu, Zhengqi, et al.
Pubblicazione: (2024)

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
di: Na, Clara, et al.
Pubblicazione: (2024)

CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
di: Sun, Wenju, et al.
Pubblicazione: (2025)

LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme
di: Park, Jeongmin Brian, et al.
Pubblicazione: (2024)

Learning Without Training
di: O'Dowd, Ryan
Pubblicazione: (2026)

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
di: Song, Zeyu, et al.
Pubblicazione: (2023)

Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
di: Zhang, Bingjie, et al.
Pubblicazione: (2025)

Provably Convergent Subgraph-wise Sampling for Fast GNN Training
di: Wang, Jie, et al.
Pubblicazione: (2023)

Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective
di: Yuan, Hao, et al.
Pubblicazione: (2023)

Model Merging via Data-Free Covariance Estimation
di: Hameed, Marawan Gamal Abdel, et al.
Pubblicazione: (2026)

Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
di: Junhao, Wei, et al.
Pubblicazione: (2025)

Fast and Effective GNN Training through Sequences of Random Path Graphs
di: Bonchi, Francesco, et al.
Pubblicazione: (2023)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
di: Lou, Jiadong, et al.
Pubblicazione: (2025)

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
di: Morrison, Jacob, et al.
Pubblicazione: (2026)

Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training
di: Wei, Cunyang, et al.
Pubblicazione: (2026)

Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
di: Darade, Ishita, et al.
Pubblicazione: (2026)

Exploring Training Data Attribution under Limited Access Constraints
di: Zhang, Shiyuan, et al.
Pubblicazione: (2025)