message-passing

Tag

Cards List
#message-passing

Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials

arXiv cs.LG · 22h ago Cached

The paper provides a completeness theory proving that multi-layer message passing in graph neural networks achieves universal approximation for interatomic potentials, justifying common architectural practices in machine-learned potentials.

0 favorites 0 likes
#message-passing

Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivarianc

arXiv cs.LG · 2026-08-18 Cached

The paper introduces Riemannian Hodge Message Passing (RHMP), a neural architecture that separates topology and geometry for learning physical fields on meshes, achieving superior performance across multiple benchmarks.

0 favorites 0 likes
#message-passing

The Boolean Power of ReLU

arXiv cs.LG · 2026-08-14 Cached

This theoretical paper proves that ReLU-based message-passing GNNs are strictly more expressive than GNNs using any eventually constant activation functions (e.g., truncated ReLU) with respect to Boolean queries, even on Boolean-featured graphs.

0 favorites 0 likes
#message-passing

Designing a Good Virtual Node: Addressable and Cardinality-Preserving Global Memory for Message Passing Architectures

arXiv cs.LG · 2026-08-05 Cached

This paper introduces addressable and cardinality-preserving global memory for message-passing neural networks via cross-attention slots, addressing the finite-capacity bottleneck of virtual nodes and improving performance on multiplicity-aware tasks.

0 favorites 0 likes
#message-passing

Universality and Approximation Rates of Graph Neural Networks with Random Features

arXiv cs.LG · 2026-07-30 Cached

This paper proves that graph neural networks with random node features can universally approximate permutation-invariant or equivariant functions on directed graphs, and provides approximation rate bounds for differentiable functions.

0 favorites 0 likes
#message-passing

Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

arXiv cs.LG · 2026-07-30 Cached

This paper studies the efficacy of various Graph Neural Network message-passing layers in regression contexts, finding that deep convolutional GNNs, particularly GEN, outperform attention-based GNNs.

0 favorites 0 likes
#message-passing

HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws

arXiv cs.LG · 2026-07-24 Cached

HypNO introduces a graph-based neural operator that uses physics-informed message passing on a space-time finite-volume cell graph to solve scalar hyperbolic conservation laws, accurately capturing shocks and discontinuities. The method is benchmarked on LWR and ARZ traffic-flow models.

0 favorites 0 likes
#message-passing

Message Passing Based Two-Timescale Bayesian Learning for Joint Channel and Memory Hardware Impairments Tracking

arXiv cs.LG · 2026-07-03 Cached

Proposes a message-passing-based two-timescale Bayesian deep learning framework for joint channel and memory hardware impairment tracking in massive MIMO systems.

0 favorites 0 likes
#message-passing

Latent Bridges for Multi-Table Question Answering

arXiv cs.CL · 2026-06-30 Cached

GRAB uses a GNN encoder to convert relational tables into latent tokens for frozen LLMs, achieving significant performance gains in multi-table question answering.

0 favorites 0 likes
#message-passing

Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion

arXiv cs.LG · 2026-06-18 Cached

This paper proposes a K-Hop Gaussian (KHG) diffusion kernel as a preprocessing module for graph neural networks, balancing local and global information propagation to mitigate over-smoothing and information bottlenecks. Experiments show significant improvements over traditional message-passing GNNs and existing diffusion kernels, especially on noisy or structurally complex graphs.

0 favorites 0 likes
#message-passing

What Type of Inference is Active Inference?

arXiv cs.AI · 2026-06-04 Cached

This paper analyzes Active Inference by proving that the Variational Free Energy of an augmented generative model can be decomposed into the predictive model's VFE plus explicit entropy-correction terms, yielding a full variational characterization of Expected Free Energy-based planning. The authors derive a message-passing scheme for EFE-based planning and validate it on grid-world environments.

0 favorites 0 likes
#message-passing

Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection

arXiv cs.LG · 2026-06-02 Cached

Proposes a node-level spectral energy formulation for detecting camouflaged anomalies in graphs, extending to spatio-temporal settings with energy-driven message passing. Demonstrates effectiveness on large-scale benchmarks.

0 favorites 0 likes
#message-passing

Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion

arXiv cs.LG · 2026-05-26 Cached

The paper introduces a novel task of fact generation for hyper-relational knowledge graphs (HKGs) and proposes KREPE, a generative representation learning method using masked discrete diffusion that unifies link prediction and fact generation, achieving state-of-the-art performance.

0 favorites 0 likes
← Back to home

Submit Feedback