Copertina

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	El, Batu, Choudhury, Deepro, Liò, Pietro, Joshi, Chaitanya K.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Transformers are Graph Neural Networks
di: Joshi, Chaitanya K.
Pubblicazione: (2025)

GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning
di: Sun, Zhongtian, et al.
Pubblicazione: (2025)

Superposition in Graph Neural Networks
di: Pertl, Lukas, et al.
Pubblicazione: (2025)

How Smoothing is N-simplicial Attention?
di: Dussolle, Alexandre, et al.
Pubblicazione: (2025)

Actionable Interpretability via Causal Hypergraphs: Unravelling Batch Size Effects in Deep Learning
di: Sun, Zhongtian, et al.
Pubblicazione: (2025)

Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
di: Cornelio, Cristina, et al.
Pubblicazione: (2025)

Interpretable Hierarchical Concept Reasoning through Attention-Guided Graph Learning
di: Debot, David, et al.
Pubblicazione: (2025)

MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder
di: Wang, Zhiyu, et al.
Pubblicazione: (2025)

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

KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis
di: Zuo, Kaiwen, et al.
Pubblicazione: (2024)

VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention
di: Zhou, Jingbo, et al.
Pubblicazione: (2026)

CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning
di: Purves, Carlos, et al.
Pubblicazione: (2026)

Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
di: Ashworth, Cassidy, et al.
Pubblicazione: (2025)

Explaining the Explainers in Graph Neural Networks: a Comparative Study
di: Longa, Antonio, et al.
Pubblicazione: (2022)

Inefficiencies of Meta Agents for Agent Design
di: El, Batu, et al.
Pubblicazione: (2025)

Towards Principled Graph Transformers
di: Müller, Luis, et al.
Pubblicazione: (2024)

Graph Convolutions Enrich the Self-Attention in Transformers!
di: Choi, Jeongwhan, et al.
Pubblicazione: (2023)

nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
di: Dumas, Clément
Pubblicazione: (2025)

Mechanistic Interpretability for Transformer-based Time Series Classification
di: Kalnāre, Matīss, et al.
Pubblicazione: (2025)

HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily
di: Li, Xinyi, et al.
Pubblicazione: (2026)

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities
di: Longa, Antonio, et al.
Pubblicazione: (2023)

Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
di: Wang, Yuwen, et al.
Pubblicazione: (2024)

Wavelet-Enhanced Neural ODE and Graph Attention for Interpretable Energy Forecasting
di: Joy, Usman Gani
Pubblicazione: (2025)

k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
di: De Schouwer, Jonas, et al.
Pubblicazione: (2026)

TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting
di: Margeloiu, Andrei, et al.
Pubblicazione: (2024)

Mechanistic Interpretability of Fine-Tuned Vision Transformers on Distorted Images: Decoding Attention Head Behavior for Transparent and Trustworthy AI
di: Bahador, Nooshin
Pubblicazione: (2025)

On the Expressive Power of Geometric Graph Neural Networks
di: Joshi, Chaitanya K., et al.
Pubblicazione: (2023)

Fast and Interpretable Protein Substructure Alignment via Optimal Transport
di: Wang, Zhiyu, et al.
Pubblicazione: (2025)

Algebraic Priors for Approximately Equivariant Networks
di: Ali, Riccardo, et al.
Pubblicazione: (2025)

Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability
di: Bini, Lorenzo, et al.
Pubblicazione: (2024)

Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
di: Chorna, Sofiia, et al.
Pubblicazione: (2025)

Hybrid Focal and Full-Range Attention Based Graph Transformers
di: Zhu, Minhong, et al.
Pubblicazione: (2023)

Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning
di: Luo, Yi, et al.
Pubblicazione: (2026)

Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences
di: El, Batu, et al.
Pubblicazione: (2025)

Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets
di: Liu, Chang, et al.
Pubblicazione: (2025)

KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
di: Logothetis, Stelios Boulitsakis, et al.
Pubblicazione: (2026)

Scaling Graph Transformers: A Comparative Study of Sparse and Dense Attention
di: Dimitrov, Leon
Pubblicazione: (2025)

Exploring the Global-to-Local Attention Scheme in Graph Transformers: An Empirical Study
di: Wu, Gang, et al.
Pubblicazione: (2025)

Spacetime $E(n)$-Transformer: Equivariant Attention for Spatio-temporal Graphs
di: Charles, Sergio G.
Pubblicazione: (2024)

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
di: Zhang, Jinhao, et al.
Pubblicazione: (2026)