'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning

• URL: http://arxiv.org/abs/2605.25548v1
• Date: Mon, 25 May 2026 08:04:32 GMT
• Title: 'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning
• Abstract summary: This paper introduces textbfSiST-GNN (textbfSimultaneous textbfSpatial-textbfTemporal textbfGNN), which fuses the two signals inside a single message-passing operation.<n>Our empirical study spans nine public baselines and fourteen model-dataset combinations, covering both fixed-split and live-update evaluation regimes.
• Score: 1.39296688544827
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. \emph{Temporal-first} approaches build per-node temporal embeddings and only afterwards perform spatial aggregation, whereas \emph{Spatial-first} approaches invert this order, feeding the output of a graph convolution into a downstream temporal module. In either case, the rigid sequencing forces the second stage to consume an already-compressed summary produced by the first, ruling out joint reasoning over topology and evolution; concretely, the message-passing operator never gets to weight a neighbor's contribution by that neighbor's \emph{past} trajectory. This paper introduces \textbf{SiST-GNN} (\textbf{Si}multaneous \textbf{S}patial-\textbf{T}emporal \textbf{GNN}), which fuses the two signals inside a single message-passing operation rather than chaining them. Concretely, at each snapshot we maintain a recurrent hidden state per node that summarises its history, pair it with the node's current feature vector, and treat the pair as two nodes joined by a cross-time edge; running a standard graph convolution on this temporally augmented graph yields the updated representation. Our empirical study spans nine public baselines and fourteen model-dataset combinations, covering both fixed-split and live-update evaluation regimes. Across every public benchmark, SiST-GNN sets a new state of the art in link prediction task over the strongest prior method by $109$--$277\%$ in the fixed-split setting and by $68$--$194\%$ in the live-update setting. We additionally construct three dynamic node-classification tasks by discretising the underlying continuous-time event streams; here SiST-GNN beats the leading discrete-time (DTDG) baseline by $7$--$22\%$ and matches continuous-time (CTDG) methods that consume the raw events directly.

Related papers

• Bridging the Divide: End-to-End Sequence-Graph Learning [47.95529678412846]
  We argue that sequences and graphs are not separate problems but complementary facets of the same dataset.<n>We introduce BRIDGE, a unified end-to-end architecture that couples a sequence encoder with a GNN under a single objective.<n>We show that BRIDGE consistently outperforms static GNNs, temporal graph methods, and sequence-only baselines on ranking and classification metrics.
  arXiv  Detail & Related papers  (2025-10-29T03:06:54Z)
• THeGCN: Temporal Heterophilic Graph Convolutional Network [51.25112923442657]
  We propose the Temporal Heterophilic Graph Convolutional Network (THeGCN) to accurately capture both edge (spatial) heterophily and temporal heterophily.<n>The THeGCN model consists of two key components: a sampler and an aggregator.<n>Extensive experiments conducted on 5 real-world datasets validate the efficacy of THeGCN.
  arXiv  Detail & Related papers  (2024-12-21T01:52:03Z)
• Repeat-Aware Neighbor Sampling for Dynamic Graph Learning [8.975322389416734]
  Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. We argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. This paper presents RepeatMixer, which considers evolving patterns of first and high-order repeat behavior in the neighbor sampling strategy and temporal information learning.
  arXiv  Detail & Related papers  (2024-05-24T03:24:29Z)
• Topological Graph Signal Compression [7.836468889756101]
  We propose a novel TDL-based method for compressing signals over graphs. Our results show that our framework improves both standard GNN and feed-forward architectures.
  arXiv  Detail & Related papers  (2023-08-21T22:26:21Z)
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation [67.26422477327179]
  Temporal graphs exhibit dynamic interactions between nodes over continuous time. We propose a novel method of temporal graph convolution with the whole neighborhood. Our proposed TAP-GNN outperforms existing temporal graph methods by a large margin in terms of both predictive performance and online inference latency.
  arXiv  Detail & Related papers  (2023-04-15T08:17:18Z)
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment [53.72873672076391]
  Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information. We propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information. S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.
  arXiv  Detail & Related papers  (2023-02-15T06:36:04Z)
• Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer [69.0621959845251]
  We propose a new framework Temporal Graph Sequential Recommender (TGSRec) upon our defined continuous-time bi-partite graph. TCT layer can simultaneously capture collaborative signals from both users and items, as well as considering temporal dynamics inside sequential patterns. Empirical results on five datasets show that TGSRec significantly outperforms other baselines.
  arXiv  Detail & Related papers  (2021-08-14T22:50:53Z)
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs [54.13919050090926]
  We propose an end-to-end structural temporal Graph Neural Network model for detecting anomalous edges in dynamic graphs. In particular, we first extract the $h$-hop enclosing subgraph centered on the target edge and propose the node labeling function to identify the role of each node in the subgraph. Based on the extracted features, we utilize Gated recurrent units (GRUs) to capture the temporal information for anomaly detection.
  arXiv  Detail & Related papers  (2020-05-15T09:17:08Z)
• Dynamic Spatiotemporal Graph Neural Network with Tensor Network [12.278768477060137]
  Dynamic spatial graph construction is a challenge in graph neural network (GNN) for time series data problems. We generate a spatial tensor graph (STG) to collect all the dynamic spatial relations, as well as a temporal tensor graph (TTG) to find the latent pattern along time at each node. We experimentally compare the accuracy and time costing with the state-of-the-art GNN based methods on the public traffic datasets.
  arXiv  Detail & Related papers  (2020-03-12T20:47:22Z)

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.