STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
- URL: http://arxiv.org/abs/2403.12418v4
- Date: Sat, 18 May 2024 11:58:16 GMT
- Title: STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
- Authors: Lincan Li, Hanchen Wang, Wenjie Zhang, Adelle Coster,
- Abstract summary: We introduce Spatial-Temporal Graph Mamba (STG-Mamba) as the first exploration of leveraging the powerful selective state space models for STG learning.
STG-Mamba treats STG Network as a system, and meticulously explore the STG system's dynamic state evolution across temporal dimension.
It not only surpasses existing state-of-the-art methods in terms of STG forecasting performance, but also effectively alleviate the computational bottleneck of large-scale graph networks.
- Score: 11.211981320116323
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Spatial-Temporal Graph (STG) data is characterized as dynamic, heterogenous, and non-stationary, leading to the continuous challenge of spatial-temporal graph learning. In the past few years, various GNN-based methods have been proposed to solely focus on mimicking the relationships among node individuals of the STG network, ignoring the significance of modeling the intrinsic features that exist in STG system over time. In contrast, modern Selective State Space Models (SSSMs) present a new approach which treat STG Network as a system, and meticulously explore the STG system's dynamic state evolution across temporal dimension. In this work, we introduce Spatial-Temporal Graph Mamba (STG-Mamba) as the first exploration of leveraging the powerful selective state space models for STG learning by treating STG Network as a system, and employing the Spatial-Temporal Selective State Space Module (ST-S3M) to precisely focus on the selected STG latent features. Furthermore, to strengthen GNN's ability of modeling STG data under the setting of selective state space models, we propose Kalman Filtering Graph Neural Networks (KFGN) for dynamically integrate and upgrade the STG embeddings from different temporal granularities through a learnable Kalman Filtering statistical theory-based approach. Extensive empirical studies are conducted on three benchmark STG forecasting datasets, demonstrating the performance superiority and computational efficiency of STG-Mamba. It not only surpasses existing state-of-the-art methods in terms of STG forecasting performance, but also effectively alleviate the computational bottleneck of large-scale graph networks in reducing the computational cost of FLOPs and test inference time. The implementation code is available at: \url{https://github.com/LincanLi98/STG-Mamba}.
Related papers
- DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs [59.434893231950205]
Dynamic graph learning aims to uncover evolutionary laws in real-world systems.
We propose DyG-Mamba, a new continuous state space model for dynamic graph learning.
We show that DyG-Mamba achieves state-of-the-art performance on most datasets.
arXiv Detail & Related papers (2024-08-13T15:21:46Z) - Spatio-Temporal Meta Contrastive Learning [18.289397543341707]
We propose a new-temporal contrastive learning framework to encode robust and generalizable S-temporal Graph representations.
We show that our framework significantly improves performance over various state-of-the-art baselines in traffic crime prediction.
arXiv Detail & Related papers (2023-10-26T04:56:31Z) - DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising
Diffusion Models [53.67562579184457]
This paper focuses on probabilistic STG forecasting, which is challenging due to the difficulty in modeling uncertainties and complex dependencies.
We present the first attempt to generalize the popular denoising diffusion models to STGs, leading to a novel non-autoregressive framework called DiffSTG.
Our approach combines the intrinsic-temporal learning capabilities STNNs with the uncertainty measurements of diffusion models.
arXiv Detail & Related papers (2023-01-31T13:42:36Z) - Space-Time Graph Neural Networks with Stochastic Graph Perturbations [100.31591011966603]
Space-time graph neural networks (ST-GNNs) learn efficient graph representations of time-varying data.
In this paper we revisit the properties of ST-GNNs and prove that they are stable to graph stabilitys.
Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs.
arXiv Detail & Related papers (2022-10-28T16:59:51Z) - Spatio-Temporal Latent Graph Structure Learning for Traffic Forecasting [6.428566223253948]
We propose a new traffic forecasting framework--S-Temporal Latent Graph Structure Learning networks (ST-LGSL)
The model employs a graph based on Multilayer perceptron and K-Nearest Neighbor, which learns the latent graph topological information from the entire data.
With the dependencies-kNN based on ground-truth adjacency matrix and similarity metric in kNN, ST-LGSL aggregates the top focusing on geography and node similarity.
arXiv Detail & Related papers (2022-02-25T10:02:49Z) - Data-Driven Short-Term Voltage Stability Assessment Based on
Spatial-Temporal Graph Convolutional Network [14.837629132539902]
Post-fault dynamics of short-term voltage stability (SVS) present spatial-temporal characteristics.
This paper develops a novel spatial-temporal graph convolutional network (STGCN) to address this problem.
It can result in higher assessment accuracy, better robustness and adaptability than conventional methods.
arXiv Detail & Related papers (2021-03-05T15:00:47Z) - Spatio-Temporal Graph Scattering Transform [54.52797775999124]
Graph neural networks may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data.
We put forth a novel mathematically designed framework to analyze-temporal data.
arXiv Detail & Related papers (2020-12-06T19:49:55Z) - On the spatial attention in Spatio-Temporal Graph Convolutional Networks
for skeleton-based human action recognition [97.14064057840089]
Graphal networks (GCNs) promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a graph.
Most of the recently proposed G-temporal-based methods improve the performance by learning the graph structure at each layer of the network.
arXiv Detail & Related papers (2020-11-07T19:03:04Z) - Efficient and Stable Graph Scattering Transforms via Pruning [86.76336979318681]
Graph scattering transforms ( GSTs) offer training-free deep GCN models that extract features from graph data.
The price paid by GSTs is exponential complexity in space and time that increases with the number of layers.
The present work addresses the complexity limitation of GSTs by introducing an efficient so-termed pruned (p) GST approach.
arXiv Detail & Related papers (2020-01-27T16:05:56Z)
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.