Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning

• URL: http://arxiv.org/abs/2504.08129v2
• Date: Sat, 02 Aug 2025 12:33:54 GMT
• Title: Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning
• Authors: Hsing-Huan Chung, Shravan Chaudhari, Xing Han, Yoav Wald, Suchi Saria, Joydeep Ghosh,
• Abstract summary: Seminal attention-based models like TGAT and DyGFormer rely on sinusoidal time encoders to capture temporal dependencies between edge events.<n>We show that the linear time encoder avoids temporal information loss caused by sinusoidal functions and reduces the need for high-dimensional time encoders.
• Score: 12.201459405989898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic graph learning is essential for applications involving temporal networks and requires effective modeling of temporal relationships. Seminal attention-based models like TGAT and DyGFormer rely on sinusoidal time encoders to capture temporal dependencies between edge events. Prior work justified sinusoidal encodings because their inner products depend on the time spans between events, which are crucial features for modeling inter-event relations. However, sinusoidal encodings inherently lose temporal information due to their many-to-one nature and therefore require high dimensions. In this paper, we rigorously study a simpler alternative: the linear time encoder, which avoids temporal information loss caused by sinusoidal functions and reduces the need for high-dimensional time encoders. We show that the self-attention mechanism can effectively learn to compute time spans between events from linear time encodings and extract relevant temporal patterns. Through extensive experiments on six dynamic graph datasets, we demonstrate that the linear time encoder improves the performance of TGAT and DyGFormer in most cases. Moreover, the linear time encoder can lead to significant savings in model parameters with minimal performance loss. For example, compared to a 100-dimensional sinusoidal time encoder, TGAT with a 2-dimensional linear time encoder saves 43% of parameters and achieves higher average precision on five datasets. While both encoders can be used simultaneously, our study highlights the often-overlooked advantages of linear time features in modern dynamic graph models. These findings can positively impact the design choices of various dynamic graph learning architectures and eventually benefit temporal network applications such as recommender systems, communication networks, and traffic forecasting.

Related papers

• Multivariate Time-Series Anomaly Detection based on Enhancing Graph Attention Networks with Topological Analysis [31.43159668073136]
  Unsupervised anomaly detection in time series is essential in industrial applications, as it significantly reduces the need for manual intervention. Traditional methods use Graph Neural Networks (GNNs) or Transformers to analyze spatial while RNNs to model temporal dependencies. This paper introduces a novel temporal model built on an enhanced Graph Attention Network (GAT) for multivariate time series anomaly detection called TopoGDN.
  arXiv  Detail & Related papers  (2024-08-23T14:06:30Z)
• Higher-order Spatio-temporal Physics-incorporated Graph Neural Network for Multivariate Time Series Imputation [9.450743095412896]
  Missing values is an essential but challenging issue due to the complex latent-temporal correlation and dynamic nature of time series. We propose a higher-ordertemporal physics-incorporated Graph Neural Networks (HSPGNN) to address this problem. HSPGNN provides better dynamic analysis and explanation than traditional data-driven models.
  arXiv  Detail & Related papers  (2024-05-16T16:35:43Z)
• Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality [39.476378833827184]
  Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. We introduce a novel spatial- temporal memories-enhanced graph autoencoder (STRIPE) STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
  arXiv  Detail & Related papers  (2024-03-14T02:26:10Z)
• Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs [50.25683648762602]
  We introduce Koopman VAE, a new generative framework that is based on a novel design for the model prior. Inspired by Koopman theory, we represent the latent conditional prior dynamics using a linear map. KoVAE outperforms state-of-the-art GAN and VAE methods across several challenging synthetic and real-world time series generation benchmarks.
  arXiv  Detail & Related papers  (2023-10-04T07:14:43Z)
• Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning [59.26623999209235]
  We present DiST, which disentangles the learning of spatial and temporal aspects of videos. The disentangled learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps.
  arXiv  Detail & Related papers  (2023-09-14T17:58:33Z)
• DyG2Vec: Efficient Representation Learning for Dynamic Graphs [26.792732615703372]
  Temporal graph neural networks have shown promising results in learning inductive representations by automatically extracting temporal patterns. We present an efficient yet effective attention-based encoder that leverages temporal edge encodings and window-based subgraph sampling to generate task-agnostic embeddings.
  arXiv  Detail & Related papers  (2022-10-30T18:13:04Z)
• NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
  This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
  arXiv  Detail & Related papers  (2022-09-29T04:06:00Z)
• Scalable Spatiotemporal Graph Neural Networks [14.415967477487692]
  Graph neural networks (GNNs) are often the core component of the forecasting architecture. In most pretemporal GNNs, the computational complexity scales up to a quadratic factor with the length of the sequence times the number of links in the graph. We propose a scalable architecture that exploits an efficient encoding of both temporal and spatial dynamics.
  arXiv  Detail & Related papers  (2022-09-14T09:47:38Z)
• Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations [11.486068333583216]
  This paper tackles the problem of learning effective models to reconstruct missing data points. We propose a class of attention-based architectures, that given a set of highly sparse observations, learn a representation for points in time and space. Compared to the state of the art, our model handles sparse data without propagating prediction errors or requiring a bidirectional model to encode forward and backward time dependencies.
  arXiv  Detail & Related papers  (2022-05-26T16:40:48Z)
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
  We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE) Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
  arXiv  Detail & Related papers  (2022-02-17T02:17:31Z)
• Online Graph Topology Learning from Matrix-valued Time Series [0.0]
  The focus is on the statistical analysis of matrix-valued time series, where data is collected over a network of sensors. The goal is to identify the dependency structure among these sensors and represent it with a graph. Online algorithms are adapted to these augmented data models, allowing for simultaneous learning of the graph and trend from streaming samples.
  arXiv  Detail & Related papers  (2021-07-16T17:21:14Z)
• Adaptive Machine Learning for Time-Varying Systems: Low Dimensional Latent Space Tuning [91.3755431537592]
  We present a recently developed method of adaptive machine learning for time-varying systems. Our approach is to map very high (N>100k) dimensional inputs into the low dimensional (N2) latent space at the output of the encoder section of an encoder-decoder CNN. This method allows us to learn correlations within and to track their evolution in real time based on feedback without interrupts.
  arXiv  Detail & Related papers  (2021-07-13T16:05:28Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)
• 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)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

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.