Graph WaveNet for Deep Spatial-Temporal Graph Modeling
read the original abstract
Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.
This paper has not been read by Pith yet.
Forward citations
Cited by 24 Pith papers
-
CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting
CausalPOI proposes a spatio-temporal graph causal learning method for cold-start POI check-in forecasting that builds functional interaction graphs and treatment-control pairs to outperform baselines on SafeGraph data.
-
Graph Navier Stokes Networks
GNSN defines a dynamic velocity field on graphs to enable convection alongside diffusion, mitigating oversmoothing and outperforming baselines on twelve datasets with varying homophily.
-
Bridge: Retrieval-Augmented Spatiotemporal Modeling for Urban Delivery Demand
Bridge augments a graph neural network backbone with time-aware retrieval from a memory of region-time windows to improve cold-start and cross-city urban delivery demand forecasting.
-
SpatialEpiBench: Benchmarking Spatial Information and Epidemic Priors in Forecasting
SpatialEpiBench shows adjacency-informed models with epidemic priors underperform a last-value baseline across 11 datasets from 1 day to 1 month ahead, identifying failures in outbreak anticipation, sparsity handling,...
-
AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecasting
AirQualityBench is a realistic global benchmark using hourly data from 3720 stations across 2021-2025 for six pollutants, preserving native missingness masks and evaluating on inverse-transformed physical scales.
-
SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective
SCOT uses Sinkhorn entropic optimal transport to learn explicit soft correspondences between unequal region sets for multi-source cross-city transfer, adding contrastive sharpening and cycle reconstruction for stabili...
-
SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective
SCOT learns explicit soft region correspondences via entropic optimal transport and a shared prototype hub to improve multi-source cross-city transfer accuracy and robustness.
-
STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction
STM3 is a spatio-temporal mixture-of-multiscale-Mamba model that uses disentangled experts, stable routing, and causal contrastive learning to achieve state-of-the-art long-term forecasting on ten real-world benchmarks.
-
Graph Retention Networks for Dynamic Graphs
Graph Retention Networks extend retention to dynamic graphs to enable parallelizable training, O(1) inference, and chunkwise long-term training while delivering competitive performance with major efficiency gains.
-
From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction
STRP is a granularity-aware model that predicts fine-grained spatio-temporal traffic from coarse inputs via tree convolution and inverse dilated convolution, outperforming baselines on six datasets in window-based and...
-
Graph Navier Stokes Networks
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 1...
-
HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
HELIX uses learnable feature identities and hybrid temporal-feature attention to achieve state-of-the-art time series imputation across multiple datasets and settings.
-
GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba
GAMMA-Net combines Graph Attention Networks and multi-axis Mamba to outperform prior models in long-horizon traffic forecasting, with up to 16.25% lower MAE on benchmarks like METR-LA and PEMS datasets.
-
Unveiling Stochasticity: Universal Multi-modal Probabilistic Modeling for Traffic Forecasting
A drop-in Gaussian Mixture Model output layer converts deterministic traffic models to multi-modal probabilistic predictors trained solely with negative log-likelihood loss.
-
Modern Structure-Aware Simplicial Spatiotemporal Neural Network
ModernSASST is the first simplicial complex-based spatiotemporal model that combines random walks on high-dimensional complexes with parallelizable temporal convolutional networks for efficient high-order topology capture.
-
BiTA: Bidirectional Gated Recurrent Unit-Transformer Aggregator in a Temporal Graph Network Framework for Alert Prediction in Computer Networks
BiTA redesigns temporal aggregation in TGNs by jointly using bidirectional GRU for sequential dependencies and Transformer for long-range context to improve alert prediction accuracy on real network data.
-
Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head
A plug-and-play learnable Tweedie output head attached to ST-GNN backbones improves RMSE on sparse maritime traffic data by predicting means and learning node-level variance powers via closed-form unit deviance optimization.
-
Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
GC-MoE improves MAE on four traffic forecasting benchmarks by routing nodes to combinations of frozen spatio-temporal GNN experts via a graph-conditioned lightweight router, training only ~17K parameters atop 1.5M fro...
-
TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting
TSNN matches time series entries to a training-derived memory bank to forecast traffic without any trainable parameters and achieves competitive accuracy on four real-world datasets.
-
STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series Prediction
STM3 is a new multiscale Mamba mixture-of-experts model with graph causal networks and contrastive routing that reports state-of-the-art results on 10 long-term spatio-temporal forecasting benchmarks.
-
FDN: Interpretable Spatiotemporal Forecasting with Future Decomposition Networks
FDN is a neural forecasting architecture that decomposes future predictions via classification to yield interpretable latent patterns alongside SOTA-level accuracy at reduced memory and runtime cost.
-
Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting
Gated QKAN fast-weight programmer achieves lowest pooled RMSE on Abilene TM forecasting while using 22.4% of a larger LSTM's parameters and outperforming classical G-FWP.
-
Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models
Large vision-language models applied to multi-scale remote sensing imagery can generate recommendations on built environment design, constructability, land use, and risks for smart city decision-making.
-
Global-local Spatial-temporal Aware Graph Attention Network for Network Traffic Forecasting
GLSTaGAT is a spatial-temporal graph attention network using data-driven fusion graphs, global-local blocks, node normalization, and a transformer encoder to outperform baselines on real-world network traffic datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.