Cover Image

Aggregate-Combine-Readout GNNs Are More Expressive Than Logic C2

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hauke, Stan P, Wałęga, Przemysław Andrzej
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
by: Sälzer, Marco, et al.
Published: (2025)

The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic
by: Grau, Bernardo Cuenca, et al.
Published: (2025)

Towards Understanding the Expressive Power of GNNs with Global Readout
by: Funk, Maurice, et al.
Published: (2026)

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

Description Logics with Two Types of Definite Descriptions: Complexity, Expressiveness, and Automated Deduction
by: Sochański, Michał, et al.
Published: (2025)

Parity, Sensitivity, and Transformers
by: Kozachinskiy, Alexander, et al.
Published: (2026)

Logical Characterizations of GNNs with Mean Aggregation
by: Schönherr, Moritz, et al.
Published: (2025)

Goal-Driven Reasoning in DatalogMTL with Magic Sets
by: Wang, Shaoyu, et al.
Published: (2024)

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

Preservation Theorems for Unravelling-Invariant Classes: A Uniform Approach for Modal Logics and Graph Neural Networks
by: Wałęga, Przemysław Andrzej, et al.
Published: (2026)

Fuzzy Datalog$^\exists$ over Arbitrary t-Norms
by: Lanzinger, Matthias, et al.
Published: (2024)

Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation
by: Yu, Han, et al.
Published: (2025)

Message Passing on the Edge: Towards Scalable and Expressive GNNs
by: Barceló, Pablo, et al.
Published: (2025)

Logical Expressivity and Explanations for Monotonic GNNs with Scoring Functions
by: Morris, Matthew, et al.
Published: (2025)

Verifying Quantized GNNs With Readout Is Decidable But Highly Intractable
by: Chernobrovkin, Artem, et al.
Published: (2025)

Computational Complexity of Standpoint LTL
by: Demri, Stéphane, et al.
Published: (2024)

Hybrid Modal Operators for Definite Descriptions
by: Wałęga, Przemysław Andrzej, et al.
Published: (2024)

Connectivity-Guided Sparsification of 2-FWL GNNs: Preserving Full Expressivity with Improved Efficiency
by: Chen, Rongqin, et al.
Published: (2025)

Bounded Fitting for Expressive Description Logics
by: Funk, Maurice, et al.
Published: (2026)

IID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirements
by: Stol, Maarten C., et al.
Published: (2024)

Label Over Logic? How Source Cues Bias Human Fallacy Judgments More Than LLMs
by: Nahar, Mahjabin, et al.
Published: (2026)

Are Biological Systems More Intelligent Than Artificial Intelligence?
by: Bennett, Michael Timothy
Published: (2024)

Brain-Aware Readout Layers in GNNs: Advancing Alzheimer's early Detection and Neuroimaging
by: Youn, Jiwon, et al.
Published: (2024)

More Expressive Attention with Negative Weights
by: Lv, Ang, et al.
Published: (2024)

AI Needs Physics More Than Physics Needs AI
by: Coveney, Peter, et al.
Published: (2025)

A Logic for Reasoning About Aggregate-Combine Graph Neural Networks
by: Nunn, Pierre, et al.
Published: (2024)

Learning More Expressive General Policies for Classical Planning Domains
by: Ståhlberg, Simon, et al.
Published: (2024)

Relational GNNs Cannot Learn $C_2$ Features for Planning
by: Chen, Dillon Z.
Published: (2025)

Relative Expressiveness of Defeasible Logics II
by: Maher, Michael J.
Published: (2021)

Tokenization Is More Than Compression
by: Schmidt, Craig W., et al.
Published: (2024)

LLMs Struggle with Abstract Meaning Comprehension More Than Expected
by: Alhazmi, Hamoud, et al.
Published: (2026)

Who Do LLMs Trust? Human Experts Matter More Than Other LLMs
by: Bajaj, Anooshka, et al.
Published: (2026)

More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation
by: Yu, Jie, et al.
Published: (2026)

More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks
by: Bhosale, Swapnil, et al.
Published: (2025)

More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations
by: Wang, Mingze, et al.
Published: (2026)

Data Complexity in Expressive Description Logics With Path Expressions
by: Bednarczyk, Bartosz
Published: (2024)

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

A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models
by: Pham, Duc Hao, et al.
Published: (2026)

AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
by: Gedik, Hakan Emre, et al.
Published: (2025)

More Than Irrational: Modeling Belief-Biased Agents
by: Zhu, Yifan, et al.
Published: (2025)