Imagen de Portada

Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Duanyu, Wu, Huijun, Xie, Min, Wu, Xugang, Wu, Zhenwei, Zhang, Wenzhe
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Perseus: Leveraging Common Data Patterns with Curriculum Learning for More Robust Graph Neural Networks
por: Xia, Kaiwen, et al.
Publicado: (2024)

ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
por: Guo, Jingwei, et al.
Publicado: (2022)

Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
por: Wang, Yongyu
Publicado: (2025)

Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
por: Pan, Mengting, et al.
Publicado: (2026)

HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training
por: Xu, Wen, et al.
Publicado: (2026)

IDEA: Invariant Defense for Graph Adversarial Robustness
por: Tao, Shuchang, et al.
Publicado: (2023)

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
por: Zhang, Yuxiang, et al.
Publicado: (2024)

DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling
por: Mancini, K., et al.
Publicado: (2024)

Mitigating the Structural Bias in Graph Adversarial Defenses
por: Fang, Junyuan, et al.
Publicado: (2025)

A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
por: elShehaby, Mohamed, et al.
Publicado: (2026)

Talos: Optimizing Top-$K$ Accuracy in Recommender Systems
por: Zhang, Shengjia, et al.
Publicado: (2026)

Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks
por: Shi, Jingze, et al.
Publicado: (2024)

Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture
por: Shi, Jingze, et al.
Publicado: (2024)

What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks
por: Zheng, Yilun, et al.
Publicado: (2024)

Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
por: Zhang, Rui, et al.
Publicado: (2024)

Gaussian Relational Graph Transformer
por: Ding, Zezhong, et al.
Publicado: (2026)

Directed Homophily-Aware Graph Neural Network
por: Zhang, Aihu, et al.
Publicado: (2025)

Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering
por: Wen, Zichen, et al.
Publicado: (2024)

Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
por: Qiu, Ruizhong, et al.
Publicado: (2025)

engGNN: A Dual-Graph Neural Network for Omics-Based Disease Classification and Feature Selection
por: Yang, Tiantian, et al.
Publicado: (2026)

Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive Approach
por: Liu, Yunhui, et al.
Publicado: (2026)

Disentangling Homophily and Heterophily in Multimodal Graph Clustering
por: Guo, Zhaochen, et al.
Publicado: (2025)

Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defense
por: Lukyanov, Kirill, et al.
Publicado: (2025)

LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning
por: Xu, Junjie, et al.
Publicado: (2024)

Unveiling the Impact of Local Homophily on GNN Fairness: In-Depth Analysis and New Benchmarks
por: Loveland, Donald, et al.
Publicado: (2024)

A Hybrid Loss Framework for Decomposition-based Time Series Forecasting Methods: Balancing Global and Component Errors
por: Han, Ronghui, et al.
Publicado: (2024)

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

S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
por: Shi, Dai, et al.
Publicado: (2026)

Revisiting Graph Homophily Measures
por: Mironov, Mikhail, et al.
Publicado: (2024)

A Differential Geometric View and Explainability of GNN on Evolving Graphs
por: Liu, Yazheng, et al.
Publicado: (2024)

Robustness Inspired Graph Backdoor Defense
por: Zhang, Zhiwei, et al.
Publicado: (2024)

On the Robustness of Graph Reduction Against GNN Backdoor
por: Zhu, Yuxuan, et al.
Publicado: (2024)

FlexHB: a More Efficient and Flexible Framework for Hyperparameter Optimization
por: Zhang, Yang, et al.
Publicado: (2024)

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

It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph
por: Mendelman, Harel, et al.
Publicado: (2025)

Graph-Based Prediction Models for Data Debiasing
por: Wu, Dongze, et al.
Publicado: (2025)

Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophily
por: Lu, Kangkang, et al.
Publicado: (2025)

ADAGE: Active Defenses Against GNN Extraction
por: Xu, Jing, et al.
Publicado: (2025)

InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update
por: Wu, Dan, et al.
Publicado: (2023)

An Efficient Recommendation Model Based on Knowledge Graph Attention-Assisted Network (KGATAX)
por: Wu, Zhizhong
Publicado: (2024)