Methods › Graphs › Graph Models › MPNN
Message Passing Neural Network
MPNN
Introduced by Justin Gilmer et al. in Neural Message Passing for Quantum Chemistry
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
There are at least eight notable examples of models from the literature that can be described using the Message Passing Neural Networks (MPNN) framework. For simplicity we describe MPNNs which operate on undirected graphs G with node features xᵥ and edge features e_(vw). It is trivial to extend the formalism to directed multigraphs. The forward pass has two phases, a message passing phase and a readout phase. The message passing phase runs for T time steps and is defined in terms of message functions Mₜ and vertex update functions Uₜ. During the message passing phase, hidden states hᵥᵗ at each node in the graph are updated based on messages mᵥᵗ⁺¹ according to mᵥᵗ⁺¹ = ∑_(w ∈N(v)) Mₜ(hᵥᵗ, h_wᵗ, e_(vw)) hᵥᵗ⁺¹ = Uₜ(hᵥᵗ, mᵥᵗ⁺¹) where in the sum, N(v) denotes the neighbors of v in graph G. The readout phase computes a feature vector for the whole graph using some readout function R according to ŷ = R( hᵥᵀ | v ∈G ) The message functions Mₜ, vertex update functions Uₜ, and readout function R are all learned differentiable functions. R operates on the set of node states and must be invariant to permutations of the node states in order for the MPNN to be invariant to graph isomorphism.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: fully differentiable MPNN; fully differentiable MPNN; Interleaved Multiscale Message-Passing Neural Networks (IM-MPNN).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 74 · with a code link: 34 · where Syntology ran a sample: 13 (12 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (13 of 74 tagged: 12 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 74 of 74, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Understanding Generalization in Node and Link Prediction 1 Jul 2025 · 0 repositories · arXiv:2507.00927
-
Exploring Graph-Transformer Out-of-Distribution Generalization Abilities 25 Jun 2025 · 0 repositories · arXiv:2506.20575
-
Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization 17 Jun 2025 · 0 repositories · arXiv:2506.14114
-
WILTing Trees: Interpreting the Distance Between MPNN Embeddings 30 May 2025 · 0 repositories · arXiv:2505.24642Syntology 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Improving the Effective Receptive Field of Message-Passing Neural Networks 29 May 2025 · 1 repository · arXiv:2505.23185Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory 28 May 2025 · 0 repositories · arXiv:2505.22152
-
Open the Eyes of MPNN: Vision Enhances MPNN in Link Prediction 13 May 2025 · 0 repositories · arXiv:2505.08266Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Efficient Parallelization of Message Passing Neural Network Potentials for Large-scale Molecular Dynamics 10 May 2025 · 0 repositories · arXiv:2505.06711
-
A Materials Map Integrating Experimental and Computational Data via Graph-Based Machine Learning for Enhanced Materials Discovery 10 Mar 2025 · 0 repositories · arXiv:2503.07378
-
Towards graph neural networks for provably solving convex optimization problems 4 Feb 2025 · 1 repository · arXiv:2502.02446
-
A Message Passing Neural Network Surrogate Model for Bond-Associated Peridynamic Material Correspondence Formulation 29 Oct 2024 · 0 repositories · arXiv:2411.08911
-
Causal GNNs: A GNN-Driven Instrumental Variable Approach for Causal Inference in Networks 13 Sep 2024 · 0 repositories · arXiv:2409.08544
-
MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs 17 Jul 2024 · 0 repositories · arXiv:2407.18267
-
Commute Graph Neural Networks 30 Jun 2024 · 0 repositories · arXiv:2407.01635
-
Next Level Message-Passing with Hierarchical Support Graphs 22 Jun 2024 · 1 repository · arXiv:2406.15852Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 6 pointer-only (licence)
-
Beyond 5G Network Failure Classification for Network Digital Twin Using Graph Neural Network 6 Jun 2024 · 0 repositories · arXiv:2406.06595
-
Graph Neural Networks Approach for Joint Wireless Power Control and Spectrum Allocation 3 Jun 2024 · 1 repository
-
Bundle Neural Networks for message diffusion on graphs 24 May 2024 · 0 repositories · arXiv:2405.15540
-
Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency 21 May 2024 · 0 repositories · arXiv:2405.12648
-
Could Chemical LLMs benefit from Message Passing 14 May 2024 · 0 repositories · arXiv:2405.08334
-
Generalization Bounds for Message Passing Networks on Mixture of Graphons 4 Apr 2024 · 0 repositories · arXiv:2404.03473
-
Weisfeiler-Leman at the margin: When more expressivity matters 12 Feb 2024 · 0 repositories · arXiv:2402.07568
-
On dimensionality of feature vectors in MPNNs 6 Feb 2024 · 0 repositories · arXiv:2402.03966
-
Accurate Segmentation of Optic Disc And Cup from Multiple Pseudo-labels by Noise-aware Learning 30 Nov 2023 · 1 repository · arXiv:2311.18496
-
LPFormer: An Adaptive Graph Transformer for Link Prediction 17 Oct 2023 · 1 repository · arXiv:2310.11009
-
Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering 7 Oct 2023 · 0 repositories · arXiv:2310.04910
-
Probabilistically Rewired Message-Passing Neural Networks 3 Oct 2023 · 1 repository · arXiv:2310.02156Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
Band-gap regression with architecture-optimized message-passing neural networks 12 Sep 2023 · 1 repository · arXiv:2309.06348
-
A principal odor map unifies diverse tasks in olfactory perception 1 Sep 2023 · 1 repository
-
A Graph Neural Network Approach for Temporal Mesh Blending and Correspondence 23 Jun 2023 · 0 repositories · arXiv:2306.13452
-
Substitutional Alloying Using Crystal Graph Neural Networks 19 Jun 2023 · 1 repository · arXiv:2306.10766
-
Learning on Graphs under Label Noise 14 Jun 2023 · 0 repositories · arXiv:2306.08194
-
Local-to-global Perspectives on Graph Neural Networks 11 Jun 2023 · 1 repository · arXiv:2306.06547
-
Simplicial Message Passing for Chemical Property Prediction 9 Jun 2023 · 0 repositories · arXiv:2307.05392
-
Fine-grained Expressivity of Graph Neural Networks 6 Jun 2023 · 1 repository · arXiv:2306.03698
-
How does over-squashing affect the power of GNNs? 6 Jun 2023 · 0 repositories · arXiv:2306.03589
-
A graphon-signal analysis of graph neural networks 25 May 2023 · 1 repository · arXiv:2305.15987
-
DRew: Dynamically Rewired Message Passing with Delay 13 May 2023 · 1 repository · arXiv:2305.08018Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples)
-
Ewald-based Long-Range Message Passing for Molecular Graphs 8 Mar 2023 · 1 repository · arXiv:2303.04791Syntology official (archive's flag): 8 ran · 8 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
Neural Common Neighbor with Completion for Link Prediction 2 Feb 2023 · 1 repository · arXiv:2302.00890
-
On the Connection Between MPNN and Graph Transformer 27 Jan 2023 · 1 repository · arXiv:2301.11956
-
End-to-end AI framework for interpretable prediction of molecular and crystal properties 21 Dec 2022 · 1 repository · arXiv:2212.11317
-
Multi-Mask Aggregators for Graph Neural Networks 24 Nov 2022 · 1 repository
-
Predicting the clinical citation count of biomedical papers using multilayer perceptron neural network 7 Sep 2022 · 0 repositories · arXiv:2210.06346
-
Spatio-Temporal Wind Speed Forecasting using Graph Networks and Novel Transformer Architectures 29 Aug 2022 · 1 repository · arXiv:2208.13585
-
MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields 15 Jun 2022 · 4 repositories · arXiv:2206.07697Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
Fundamental Limits in Formal Verification of Message-Passing Neural Networks 10 Jun 2022 · 0 repositories · arXiv:2206.05070
-
Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces 29 May 2022 · 1 repository · arXiv:2205.14627
-
Recipe for a General, Powerful, Scalable Graph Transformer 25 May 2022 · 4 repositories · arXiv:2205.12454Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 18 unverified (of 21 harvested samples)
-
Automatic Identification of Chemical Moieties 30 Mar 2022 · 0 repositories · arXiv:2203.16205
-
On the expressive power of message-passing neural networks as global feature map transformers 17 Mar 2022 · 0 repositories · arXiv:2203.09555
-
Generalization Analysis of Message Passing Neural Networks on Large Random Graphs 1 Feb 2022 · 0 repositories · arXiv:2202.00645
-
Edge-based Tensor prediction via graph neural networks 15 Jan 2022 · 0 repositories · arXiv:2201.05770
-
Multiwave COVID-19 Prediction from Social Awareness using Web Search and Mobility Data 22 Oct 2021 · 1 repository · arXiv:2110.11584
-
CGNN: Traffic Classification with Graph Neural Network 19 Oct 2021 · 0 repositories · arXiv:2110.09726
-
From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness 7 Oct 2021 · 2 repositories · arXiv:2110.03753Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 18 harvested samples) · 2 pointer-only (licence)
-
Equivariant Subgraph Aggregation Networks 6 Oct 2021 · 1 repository · arXiv:2110.02910Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
GIR Framework: Learning Graph Positional Embeddings with Anchor Indication and Path Encoding 29 Sep 2021 · 0 repositories
-
Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance 2 Aug 2021 · 0 repositories · arXiv:2108.01068
-
Curvature Graph Neural Network 30 Jun 2021 · 0 repositories · arXiv:2106.15762
-
Breaking the Limits of Message Passing Graph Neural Networks 8 Jun 2021 · 2 repositories · arXiv:2106.04319
-
Predicting Quantum Potentials by Deep Neural Network and Metropolis Sampling 6 Jun 2021 · 0 repositories · arXiv:2106.03126
-
Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs 1 Dec 2020 · 0 repositories
-
Bayesian Graph Neural Networks for Molecular Property Prediction 25 Nov 2020 · 1 repository · arXiv:2012.02089
-
Deep Data Flow Analysis 21 Nov 2020 · 0 repositories · arXiv:2012.01470
-
Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures 15 Nov 2020 · 3 repositories · arXiv:2011.07457
-
A step towards neural genome assembly 10 Nov 2020 · 1 repository · arXiv:2011.05013Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Graph Neural Network Architecture Search for Molecular Property Prediction 27 Aug 2020 · 0 repositories · arXiv:2008.12187
-
Deep Learning for Abstract Argumentation Semantics 15 Jul 2020 · 1 repository · arXiv:2007.07629
-
How hard is to distinguish graphs with graph neural networks? 13 May 2020 · 0 repositories · arXiv:2005.06649
-
Directional Message Passing for Molecular Graphs 6 Mar 2020 · 4 repositories · arXiv:2003.03123Syntology official (archive's flag): 1 ran · 8 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 3 pointer-only (licence)
-
Assessing Graph-based Deep Learning Models for Predicting Flash Point 26 Feb 2020 · 0 repositories · arXiv:2002.11315
-
Crystal Graph Neural Networks for Data Mining in Materials Science 27 May 2019 · 1 repository
-
Neural Message Passing for Quantum Chemistry 4 Apr 2017 · 20 repositories · arXiv:1704.01212Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 63 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections