Disentangled Spatiotemporal Graph Generative Models
- URL: http://arxiv.org/abs/2203.00411v1
- Date: Mon, 28 Feb 2022 08:36:50 GMT
- Title: Disentangled Spatiotemporal Graph Generative Models
- Authors: Yuanqi Du and Xiaojie Guo and Hengning Cao and Yanfang Ye and Liang
Zhao
- Abstract summary: graph data is becoming increasingly important, ranging from microscale (e.g. protein folding) to middle-scale (e.g. human mobility network)
- Score: 32.11916705039446
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Spatiotemporal graph represents a crucial data structure where the nodes and
edges are embedded in a geometric space and can evolve dynamically over time.
Nowadays, spatiotemporal graph data is becoming increasingly popular and
important, ranging from microscale (e.g. protein folding), to middle-scale
(e.g. dynamic functional connectivity), to macro-scale (e.g. human mobility
network). Although disentangling and understanding the correlations among
spatial, temporal, and graph aspects have been a long-standing key topic in
network science, they typically rely on network processing hypothesized by
human knowledge. This usually fit well towards the graph properties which can
be predefined, but cannot do well for the most cases, especially for many key
domains where the human has yet very limited knowledge such as protein folding
and biological neuronal networks. In this paper, we aim at pushing forward the
modeling and understanding of spatiotemporal graphs via new disentangled deep
generative models. Specifically, a new Bayesian model is proposed that
factorizes spatiotemporal graphs into spatial, temporal, and graph factors as
well as the factors that explain the interplay among them. A variational
objective function and new mutual information thresholding algorithms driven by
information bottleneck theory have been proposed to maximize the
disentanglement among the factors with theoretical guarantees. Qualitative and
quantitative experiments on both synthetic and real-world datasets demonstrate
the superiority of the proposed model over the state-of-the-arts by up to 69.2%
for graph generation and 41.5% for interpretability.
Related papers
- Injecting Hamiltonian Architectural Bias into Deep Graph Networks for Long-Range Propagation [55.227976642410766]
dynamics of information diffusion within graphs is a critical open issue that heavily influences graph representation learning.
Motivated by this, we introduce (port-)Hamiltonian Deep Graph Networks.
We reconcile under a single theoretical and practical framework both non-dissipative long-range propagation and non-conservative behaviors.
arXiv Detail & Related papers (2024-05-27T13:36:50Z) - Dynamic Causal Explanation Based Diffusion-Variational Graph Neural
Network for Spatio-temporal Forecasting [60.03169701753824]
We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting.
The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
arXiv Detail & Related papers (2023-05-16T11:38:19Z) - Relational representation learning with spike trains [0.0]
We present a model that allows us to learn spike train-based embeddings of knowledge graphs, requiring only one neuron per graph element by fully utilizing the temporal domain of spike patterns.
In general, the presented results show how relational knowledge can be integrated into spike-based systems, opening up the possibility of merging event-based computing and data to build powerful and energy efficient artificial intelligence applications and reasoning systems.
arXiv Detail & Related papers (2022-05-18T18:00:37Z) - Long-term Spatio-temporal Forecasting via Dynamic Multiple-Graph
Attention [20.52864145999387]
Long-term tensor-temporal forecasting (LSTF) makes use of long-term dependency between spatial and temporal domains, contextual information, and inherent pattern in the data.
We propose new graph models to represent the contextual information of each node and the long-term parking revealed-temporal data dependency structure.
Our proposed approaches significantly improve the performance of existing graph neural network models in LSTF prediction tasks.
arXiv Detail & Related papers (2022-04-23T06:51:37Z) - Hyperbolic Graph Neural Networks: A Review of Methods and Applications [55.5502008501764]
Graph neural networks generalize conventional neural networks to graph-structured data.
The performance of Euclidean models in graph-related learning is still bounded and limited by the representation ability of Euclidean geometry.
Recently, hyperbolic space has gained increasing popularity in processing graph data with tree-like structure and power-law distribution.
arXiv Detail & Related papers (2022-02-28T15:08:48Z) - Structured Time Series Prediction without Structural Prior [0.152292571922932]
Time series prediction is a widespread and well studied problem with applications in many domains.
We propose a fully data-driven model which does not rely on such a graph, nor any other prior structural information.
arXiv Detail & Related papers (2022-02-07T22:01:58Z) - Self-Supervised Graph Representation Learning for Neuronal Morphologies [75.38832711445421]
We present GraphDINO, a data-driven approach to learn low-dimensional representations of 3D neuronal morphologies from unlabeled datasets.
We show, in two different species and across multiple brain areas, that this method yields morphological cell type clusterings on par with manual feature-based classification by experts.
Our method could potentially enable data-driven discovery of novel morphological features and cell types in large-scale datasets.
arXiv Detail & Related papers (2021-12-23T12:17:47Z) - Towards Deeper Graph Neural Networks [63.46470695525957]
Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations.
Several recent studies attribute this performance deterioration to the over-smoothing issue.
We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
arXiv Detail & Related papers (2020-07-18T01:11:14Z) - A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for
Question Answering Over Dynamic Contexts [81.4757750425247]
We study question answering over a dynamic textual environment.
We develop a graph neural network over the constructed graph, and train the model in an end-to-end manner.
arXiv Detail & Related papers (2020-04-25T04:53:54Z) - EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs [26.77596449192451]
We propose a model that predicts the evolution of dynamic graphs.
Specifically, we use a graph neural network along with a recurrent architecture to capture the temporal evolution patterns of dynamic graphs.
We evaluate the proposed model on several artificial datasets following common network evolving dynamics, as well as on real-world datasets.
arXiv Detail & Related papers (2020-03-02T12:59:05Z)
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.