How to Find a Near Optimal Mapping of Neural Networks onto Message Passing Multicomputers

ICANN ’93 ◽  
1993 ◽  
pp. 1054-1057
Author(s):  
B. Kreimeier ◽  
M. Schöne ◽  
R. Steiner ◽  
R. Eckmiller
Keyword(s):  
Neural Networks ◽  
Message Passing

scholarly journals Graph convolutional neural networks with node transition probability-based message passing and DropNode regularization

2021 ◽  
Vol 174 ◽  
pp. 114711
Author(s):  
Tien Huu Do ◽  
Duc Minh Nguyen ◽  
Giannis Bekoulis ◽  
Adrian Munteanu ◽  
Nikos Deligiannis
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Message Passing ◽  
Transition Probability

scholarly journals Coloring Graph Neural Networks for Node Disambiguation

2020 ◽  
Author(s):  
George Dasoulas ◽  
Ludovic Dos Santos ◽  
Kevin Scaman ◽  
Aladin Virmaux
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
State Of The Art ◽  
Structural Characteristics ◽  
Expressive Power ◽  
Continuous Functions ◽  
Graph Classification ◽  
Node Attributes ◽  
Graph Neural Networks ◽  
Coloring Graph

In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks (MPNNs). More specifically, we introduce a graph neural network called Colored Local Iterative Procedure (CLIP) that uses colors to disambiguate identical node attributes, and show that this representation is a universal approximator of continuous functions on graphs with node attributes. Our method relies on separability, a key topological characteristic that allows to extend well-chosen neural networks into universal representations. Finally, we show experimentally that CLIP is capable of capturing structural characteristics that traditional MPNNs fail to distinguish, while being state-of-the-art on benchmark graph classification datasets.

Generalizing Message Passing Neural Networks to Heterophily Using Position Information

2021 ◽  
pp. 230-242
Author(s):  
Wenzheng Zhang ◽  
Jie Liu ◽  
Liting Liu
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
Position Information

scholarly journals Message-passing neural networks for high-throughput polymer screening

2019 ◽  
Vol 150 (23) ◽  
pp. 234111 ◽  
Author(s):  
Peter C. St. John ◽  
Caleb Phillips ◽  
Travis W. Kemper ◽  
A. Nolan Wilson ◽  
Yanfei Guan ◽  
...  
Keyword(s):  
Neural Networks ◽  
High Throughput ◽  
Message Passing

scholarly journals The message passing neural networks for chemical property prediction on SMILES

Methods ◽  
2020 ◽  
Vol 179 ◽  
pp. 65-72 ◽  
Author(s):  
Jeonghee Jo ◽  
Bumju Kwak ◽  
Hyun-Soo Choi ◽  
Sungroh Yoon
Keyword(s):  
Neural Networks ◽  
Chemical Property ◽  
Message Passing ◽  
Property Prediction

scholarly journals Fast Quaternion Product Units for Learning Disentangled Representations in SO(3)

2022 ◽  
Author(s):  
Shaofei Qin ◽  
Xuan Zhang ◽  
Hongteng Xu ◽  
Yi Xu
Keyword(s):  
Neural Networks ◽  
Real World ◽  
Message Passing ◽  
Point Clouds ◽  
Rotation Group ◽  
Structured Data ◽  
Data Indexing ◽  
Basic Module ◽  
Real Neuron ◽  
Rotation Groups

Real-world 3D structured data like point clouds and skeletons often can be represented as data in a 3D rotation group (denoted as $\mathbb{SO}(3)$). However, most existing neural networks are tailored for the data in the Euclidean space, which makes the 3D rotation data not closed under their algebraic operations and leads to sub-optimal performance in 3D-related learning tasks. To resolve the issues caused by the above mismatching between data and model, we propose a novel non-real neuron model called \textit{quaternion product unit} (QPU) to represent data on 3D rotation groups. The proposed QPU leverages quaternion algebra and the law of the 3D rotation group, representing 3D rotation data as quaternions and merging them via a weighted chain of Hamilton products. We demonstrate that the QPU mathematically maintains the $\mathbb{SO}(3)$ structure of the 3D rotation data during the inference process and disentangles the 3D representations into ``rotation-invariant'' features and ``rotation-equivariant'' features, respectively. Moreover, we design a fast QPU to accelerate the computation of QPU. The fast QPU applies a tree-structured data indexing process, and accordingly, leverages the power of parallel computing, which reduces the computational complexity of QPU in a single thread from $\mathcal{O}(N)$ to $\mathcal {O}(\log N)$. Taking the fast QPU as a basic module, we develop a series of quaternion neural networks (QNNs), including quaternion multi-layer perceptron (QMLP), quaternion message passing (QMP), and so on. In addition, we make the QNNs compatible with conventional real-valued neural networks and applicable for both skeletons and point clouds. Experiments on synthetic and real-world 3D tasks show that the QNNs based on our fast QPUs are superior to state-of-the-art real-valued models, especially in the scenarios requiring the robustness to random rotations.<br>

scholarly journals UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

2021 ◽  
Author(s):  
Jing Huang ◽  
Jie Yang
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
State Of The Art ◽  
Representation Learning ◽  
Graph Representation ◽  
Challenging Problem ◽  
Unified Framework ◽  
Real World Datasets ◽  
Graph Neural Networks ◽  
Research Domains

Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4% to 88.8% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at https://github.com/OneForward/UniGNN.

Message Passing Neural Networks

2020 ◽  
pp. 199-214 ◽  
Author(s):  
Justin Gilmer ◽  
Samuel S. Schoenholz ◽  
Patrick F. Riley ◽  
Oriol Vinyals ◽  
George E. Dahl
Keyword(s):  
Neural Networks ◽  
Message Passing
Sign in / Sign up

Export Citation Format

Share Document