Equivariant Graph Hierarchy-Based Neural Networks
- URL: http://arxiv.org/abs/2202.10643v1
- Date: Tue, 22 Feb 2022 03:11:47 GMT
- Title: Equivariant Graph Hierarchy-Based Neural Networks
- Authors: Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun, Wenbing Huang
- Abstract summary: We propose Equivariant Hierarchy-based Graph Networks (EGHNs)
EGHNs consist of the three key components: generalized Equivariant Matrix Message Passing (EMMP), E-Pool and E-UpPool.
Considerable experimental evaluations verify the effectiveness of our EGHN on several applications including multi-object dynamics simulation, motion capture, and protein dynamics modeling.
- Score: 53.60804845045526
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Equivariant Graph neural Networks (EGNs) are powerful in characterizing the
dynamics of multi-body physical systems. Existing EGNs conduct flat message
passing, which, yet, is unable to capture the spatial/dynamical hierarchy for
complex systems particularly, limiting substructure discovery and global
information fusion. In this paper, we propose Equivariant Hierarchy-based Graph
Networks (EGHNs) which consist of the three key components: generalized
Equivariant Matrix Message Passing (EMMP) , E-Pool and E-UpPool. In particular,
EMMP is able to improve the expressivity of conventional equivariant message
passing, E-Pool assigns the quantities of the low-level nodes into high-level
clusters, while E-UpPool leverages the high-level information to update the
dynamics of the low-level nodes. As their names imply, both E-Pool and E-UpPool
are guaranteed to be equivariant to meet physic symmetry. Considerable
experimental evaluations verify the effectiveness of our EGHN on several
applications including multi-object dynamics simulation, motion capture, and
protein dynamics modeling.
Related papers
- E(n) Equivariant Topological Neural Networks [10.603892843083173]
Graph neural networks excel at modeling pairwise interactions, but they cannot flexibly accommodate higher-order interactions and features.
Topological deep learning (TDL) has emerged recently as a promising tool for addressing this issue.
This paper introduces E(n)Equivariant Topological Neural Networks (ETNNs), which are E(n)-equivariant networks operating on unifying graphs, hypergraphs, simplicial objects, path, and cell complexes.
arXiv Detail & Related papers (2024-05-24T10:55:38Z) - Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics [32.115887916401036]
We develop an equivariant version of Fourier-temporal GNNs to represent and simulate dynamics of physical systems.
We evaluate our model on three real datasets corresponding to the molecular-, protein- and macro-level.
arXiv Detail & Related papers (2024-05-21T15:33:21Z) - A quatum inspired neural network for geometric modeling [14.214656118952178]
We introduce an innovative equivariant Matrix Product State (MPS)-based message-passing strategy.
Our method effectively models complex many-body relationships, suppressing mean-field approximations.
It seamlessly replaces the standard message-passing and layer-aggregation modules intrinsic to geometric GNNs.
arXiv Detail & Related papers (2024-01-03T15:59:35Z) - Spline-based neural network interatomic potentials: blending classical
and machine learning models [0.0]
We introduce a new MLIP framework which blends the simplicity of spline-based MEAM potentials with the flexibility of a neural network architecture.
We demonstrate how this framework can be used to probe the boundary between classical and ML IPs.
arXiv Detail & Related papers (2023-10-04T15:42:26Z) - From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
We present an expressive family of parameterized, hypergraph-regularized energy functions.
We then demonstrate how minimizers of these energies effectively serve as node embeddings.
We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
arXiv Detail & Related papers (2023-06-16T04:40:59Z) - Deep Graph Neural Networks via Flexible Subgraph Aggregation [50.034313206471694]
Graph neural networks (GNNs) can learn from graph-structured data and learn the representation of nodes through aggregating neighborhood information.
In this paper, we evaluate the expressive power of GNNs from the perspective of subgraph aggregation.
We propose a sampling-based node-level residual module (SNR) that can achieve a more flexible utilization of different hops of subgraph aggregation.
arXiv Detail & Related papers (2023-05-09T12:03:42Z) - Spatial Attention Kinetic Networks with E(n)-Equivariance [0.951828574518325]
Neural networks that are equivariant to rotations, translations, reflections, and permutations on n-dimensional geometric space have shown promise in physical modeling.
We propose a simple alternative functional form that uses neurally parametrized linear combinations of edge vectors to achieve equivariance.
We design spatial attention kinetic networks with E(n)-equivariance, or SAKE, which are competitive in many-body system modeling tasks while being significantly faster.
arXiv Detail & Related papers (2023-01-21T05:14:29Z) - Equivariant vector field network for many-body system modeling [65.22203086172019]
Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers.
We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
arXiv Detail & Related papers (2021-10-26T14:26:25Z) - Frame Averaging for Invariant and Equivariant Network Design [50.87023773850824]
We introduce Frame Averaging (FA), a framework for adapting known (backbone) architectures to become invariant or equivariant to new symmetry types.
We show that FA-based models have maximal expressive power in a broad setting.
We propose a new class of universal Graph Neural Networks (GNNs), universal Euclidean motion invariant point cloud networks, and Euclidean motion invariant Message Passing (MP) GNNs.
arXiv Detail & Related papers (2021-10-07T11:05:23Z) - Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors.
It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features.
We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
arXiv Detail & Related papers (2020-06-26T17:03:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.