Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment

• URL: http://arxiv.org/abs/2302.07491v3
• Date: Sun, 28 Apr 2024 08:49:34 GMT
• Title: Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• Authors: Meng Liu, Ke Liang, Yawei Zhao, Wenxuan Tu, Sihang Zhou, Xinbiao Gan, Xinwang Liu, Kunlun He,
• Abstract summary: 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.
• Score: 53.72873672076391
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information, which has recently garnered increasing attention. In contrast to static graphs, temporal graphs are typically organized as node interaction sequences over continuous time rather than an adjacency matrix. Most temporal graph learning methods model current interactions by incorporating historical neighborhood. However, such methods only consider first-order temporal information while disregarding crucial high-order structural information, resulting in suboptimal performance. To address this issue, we propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information to learn more informative node representations. Notably, the initial node representations combine first-order temporal and high-order structural information differently to calculate two conditional intensities. An alignment loss is then introduced to optimize the node representations, narrowing the gap between the two intensities and making them more informative. Concretely, in addition to modeling temporal information using historical neighbor sequences, we further consider structural knowledge at both local and global levels. At the local level, we generate structural intensity by aggregating features from high-order neighbor sequences. At the global level, a global representation is generated based on all nodes to adjust the structural intensity according to the active statuses on different nodes. Extensive experiments demonstrate that the proposed model S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.

Related papers

• CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network [32.42051167404171]
  We propose a Continuous-Time Representation Learning model on temporal HINs. We train the model with a future event (a subgraph) prediction task to capture the evolution of the high-order network structure. The results demonstrate that our model significantly boosts performance and outperforms various state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-05-11T03:39:22Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• Deep Temporal Graph Clustering [77.02070768950145]
  We propose a general framework for deep Temporal Graph Clustering (GC) GC introduces deep clustering techniques to suit the interaction sequence-based batch-processing pattern of temporal graphs. Our framework can effectively improve the performance of existing temporal graph learning methods.
  arXiv  Detail & Related papers  (2023-05-18T06:17:50Z)
• 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)
• DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph [59.583555454424]
  We propose a novel disenTangled representation learning framework for discrete-time Dynamic graphs, namely DyTed. We specially design a temporal-clips contrastive learning task together with a structure contrastive learning to effectively identify the time-invariant and time-varying representations respectively.
  arXiv  Detail & Related papers  (2022-10-19T14:34:12Z)
• Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolution [60.695162101159134]
  Existing works merely view a dynamic graph as a sequence of changes. We formulate dynamic graphs as temporal edge sequences associated with joining time of. vertex and timespan of edges. A time-aware Transformer is proposed to embed. vertex' dynamic connections and ToEs into the learned. vertex representations.
  arXiv  Detail & Related papers  (2022-07-01T15:32:56Z)
• Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrast [0.8379286663107846]
  This paper proposes a self-supervised dynamic graph representation learning framework (DySubC) DySubC defines a temporal subgraph contrastive learning task to simultaneously learn the structural and evolutional features of a dynamic graph. Experiments on five real-world datasets demonstrate that DySubC performs better than the related baselines.
  arXiv  Detail & Related papers  (2021-12-16T09:35:34Z)
• Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling [2.3022070933226217]
  We propose a novel framework, namely static- and dynamic-graph learning-neural network (GL) The model acquires static and dynamic graph matrices from data to model long-term and short-term patterns respectively. It achieves state-of-the-art performance on almost all datasets.
  arXiv  Detail & Related papers  (2021-12-06T08:19:15Z)
• Inductive Representation Learning on Temporal Graphs [33.44276155380476]
  temporal dynamic graphs require handling new nodes as well as capturing temporal patterns. We propose the temporal graph attention layer to efficiently aggregate temporal-topological neighborhood features. By stacking TGAT layers, the network recognizes the node embeddings as functions of time and is able to inductively infer embeddings for both new and observed nodes.
  arXiv  Detail & Related papers  (2020-02-19T02:05:37Z)

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.