Copertina

Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Errica, Federico, Christiansen, Henrik, Zaverkin, Viktor, Maruyama, Takashi, Niepert, Mathias, Alesiani, Francesco
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
di: Zaverkin, Viktor, et al.
Pubblicazione: (2024)

Adaptive Width Neural Networks
di: Errica, Federico, et al.
Pubblicazione: (2025)

Fast, Modular, and Differentiable Framework for Machine Learning-Enhanced Molecular Simulations
di: Christiansen, Henrik, et al.
Pubblicazione: (2025)

Geometric Kolmogorov-Arnold Superposition Theorem
di: Alesiani, Francesco, et al.
Pubblicazione: (2025)

Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
di: Zaverkin, Viktor, et al.
Pubblicazione: (2023)

Variational Kolmogorov-Arnold Network
di: Alesiani, Francesco, et al.
Pubblicazione: (2025)

Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations
di: Zaverkin, Viktor, et al.
Pubblicazione: (2025)

Self-Tuning Hamiltonian Monte Carlo for Accelerated Sampling
di: Christiansen, Henrik, et al.
Pubblicazione: (2023)

Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
di: Arnaiz-Rodriguez, Adrian, et al.
Pubblicazione: (2025)

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
di: Errica, Federico, et al.
Pubblicazione: (2023)

Logical Guidance for the Exact Composition of Diffusion Models
di: Alesiani, Francesco, et al.
Pubblicazione: (2026)

Physics-Informed Weakly Supervised Learning for Interatomic Potentials
di: Takamoto, Makoto, et al.
Pubblicazione: (2024)

Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks
di: Bose, Kushal, et al.
Pubblicazione: (2025)

Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing
di: Taha, Diaaeldin, et al.
Pubblicazione: (2025)

Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
di: Hossen, Md Sazzad, et al.
Pubblicazione: (2026)

Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
di: Sun, Li, et al.
Pubblicazione: (2025)

On the Complexity of Optimal Graph Rewiring for Oversmoothing and Oversquashing in Graph Neural Networks
di: Chehreghani, Mostafa Haghir
Pubblicazione: (2026)

A Leibniz rule of distributional pairing and hyperforce sum rule
di: Maruyama, Takashi, et al.
Pubblicazione: (2026)

Probabilistically Rewired Message-Passing Neural Networks
di: Qian, Chendi, et al.
Pubblicazione: (2023)

Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability
di: Guan, Weiqi, et al.
Pubblicazione: (2025)

Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies
di: Mathys, Joël, et al.
Pubblicazione: (2025)

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
di: Shenaj, Donald, et al.
Pubblicazione: (2026)

Adaptive Physics-informed Neural Networks: A Survey
di: Torres, Edgar, et al.
Pubblicazione: (2025)

PDEBENCH: An Extensive Benchmark for Scientific Machine Learning
di: Takamoto, Makoto, et al.
Pubblicazione: (2022)

Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
di: Southern, Joshua, et al.
Pubblicazione: (2024)

Graph Reasoning Networks
di: Zopf, Markus, et al.
Pubblicazione: (2024)

Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
di: Hossain, Tanvir, et al.
Pubblicazione: (2026)

Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
di: Nguyen, Duy M. H., et al.
Pubblicazione: (2024)

A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs
di: Wang, Jiaqi, et al.
Pubblicazione: (2025)

L2XGNN: Learning to Explain Graph Neural Networks
di: Serra, Giuseppe, et al.
Pubblicazione: (2022)

Short-Range Oversquashing
di: Mishayev, Yaaqov, et al.
Pubblicazione: (2025)

ADMP-GNN: Adaptive Depth Message Passing GNN
di: Abbahaddou, Yassine, et al.
Pubblicazione: (2025)

Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
di: Chen, Xuanze, et al.
Pubblicazione: (2024)

MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning
di: Manolache, Andrei, et al.
Pubblicazione: (2024)

Generalization Bounds for Message Passing Networks on Mixture of Graphons
di: Maskey, Sohir, et al.
Pubblicazione: (2024)

Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
di: Park, MoonJeong, et al.
Pubblicazione: (2024)

Heterophily-informed Message Passing
di: Wang, Haishan, et al.
Pubblicazione: (2025)

Are We Measuring Oversmoothing in Graph Neural Networks Correctly?
di: Zhang, Kaicheng, et al.
Pubblicazione: (2025)

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
di: Ariguib, Boshra, et al.
Pubblicazione: (2025)

Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering
di: Islam, Md Aminul, et al.
Pubblicazione: (2026)