Imagen de Portada

On the Expressive Power of Contextual Relations in Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Fraiman, Demián
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Expressive Power of Floating-Point Transformers
por: Park, Sejun, et al.
Publicado: (2026)

Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
por: Wang, Mingze, et al.
Publicado: (2024)

Transformers are Expressive, But Are They Expressive Enough for Regression?
por: Nath, Swaroop, et al.
Publicado: (2024)

Exact Expressive Power of Transformers with Padding
por: Merrill, William, et al.
Publicado: (2025)

The Expressive Power of Transformers with Chain of Thought
por: Merrill, William, et al.
Publicado: (2023)

On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
por: Xu, Kevin, et al.
Publicado: (2024)

On The Expressive Power of GNN Derivatives
por: Eitan, Yam, et al.
Publicado: (2025)

Imbalanced Classification under Capacity Constraints
por: Fraiman, Daniel, et al.
Publicado: (2026)

On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions
por: Gu, Linyan, et al.
Publicado: (2026)

Expressive Power of Temporal Message Passing
por: Wałęga, Przemysław Andrzej, et al.
Publicado: (2024)

On the Expressive Power of GNNs to Solve Linear SDPs
por: Qian, Chendi, et al.
Publicado: (2026)

Expressive Power of Deep Homomorphism Networks over Relational Databases
por: Schönherr, Moritz, et al.
Publicado: (2026)

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
por: Brösamle, Moritz, et al.
Publicado: (2026)

On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
por: Zhou, Cai, et al.
Publicado: (2024)

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

Expressivity of Transformers: A Tropical Geometry Perspective
por: Su, Ye, et al.
Publicado: (2026)

On the Expressive Power of GNNs for Boolean Satisfiability
por: Peltonen, Saku, et al.
Publicado: (2026)

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

On the Expressive Power of Sparse Geometric MPNNs
por: Sverdlov, Yonatan, et al.
Publicado: (2024)

On the Expressive Power of Permutation-Equivariant Weight-Space Networks
por: Dayan, Adir, et al.
Publicado: (2026)

On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks
por: Wang, Mingze, et al.
Publicado: (2025)

Rethinking the Expressive Power of GNNs via Graph Biconnectivity
por: Zhang, Bohang, et al.
Publicado: (2023)

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
por: Merrill, William, et al.
Publicado: (2025)

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

On the Expressive Power of Tree-Structured Probabilistic Circuits
por: Yin, Lang, et al.
Publicado: (2024)

RCStat: A Statistical Framework for using Relative Contextualization in Transformers
por: Mahapatra, Debabrata, et al.
Publicado: (2025)

The Expressive Power of Low-Rank Adaptation
por: Zeng, Yuchen, et al.
Publicado: (2023)

On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic
por: Park, Yeachan, et al.
Publicado: (2024)

On the Expressive Power of Subgraph Graph Neural Networks for Graphs with Bounded Cycles
por: Chen, Ziang, et al.
Publicado: (2025)

Expanding Expressivity in Transformer Models with MöbiusAttention
por: Halacheva, Anna-Maria, et al.
Publicado: (2024)

Expressive Power of Deep Networks on Manifolds: Simultaneous Approximation
por: Zhou, Hanfei, et al.
Publicado: (2025)

Improving the Expressiveness of $K$-hop Message-Passing GNNs by Injecting Contextualized Substructure Information
por: Yao, Tianjun, et al.
Publicado: (2024)

A Theoretical Study of Neural Network Expressive Power via Manifold Topology
por: Yao, Jiachen, et al.
Publicado: (2024)

Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
por: Wang, Zhe, et al.
Publicado: (2024)

On the Expressive Power and Limitations of Multi-Layer SSMs
por: Zubić, Nikola, et al.
Publicado: (2026)

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
por: Deng, Chenhui, et al.
Publicado: (2024)

Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers
por: Li, Xiaoyu, et al.
Publicado: (2024)

The Expressive Power of Graph Neural Networks: A Survey
por: Zhang, Bingxu, et al.
Publicado: (2023)

Maximising Quantum-Computing Expressive Power through Randomised Circuits
por: Yang, Yingli, et al.
Publicado: (2023)

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks
por: Chen, Jiawen, et al.
Publicado: (2026)