Future Link Prediction Without Memory or Aggregation

• URL: http://arxiv.org/abs/2505.19408v1
• Date: Mon, 26 May 2025 01:53:27 GMT
• Title: Future Link Prediction Without Memory or Aggregation
• Authors: Lu Yi, Runlin Lei, Fengran Mo, Yanping Zheng, Zhewei Wei, Yuhang Ye,
• Abstract summary: Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems.<n>Existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges.<n>We propose Cross-Attention based Future Link Predictor on Temporal Graphs (CRAFT), a simple yet effective architecture that discards memory and aggregation modules.
• Score: 25.066464612400768
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique identifiers and performing target-aware matching between source and destination nodes. To this end, we propose Cross-Attention based Future Link Predictor on Temporal Graphs (CRAFT), a simple yet effective architecture that discards memory and aggregation modules and instead builds on two components: learnable node embeddings and cross-attention between the destination and the source's recent interactions. This design provides strong expressive power and enables target-aware modeling of the compatibility between candidate destinations and the source's interaction patterns. Extensive experiments on diverse datasets demonstrate that CRAFT consistently achieves superior performance with high efficiency, making it well-suited for large-scale real-world applications.

Related papers

• Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing [30.204313638661255]
  Cross-document Relation Extraction aims to predict the relation between target entities located in different documents. We propose a novel graph-based cross-document RE model with non-bridge entity enhancement and prediction debiasing.
  arXiv  Detail & Related papers  (2024-06-24T11:08:28Z)
• Deep Representation Learning for Forecasting Recursive and Multi-Relational Events in Temporal Networks [12.142292322071299]
  This work addresses the problem of forecasting higher-order interaction events that can be multi-relational and recursive.<n>The proposed model, textitRelational Recursive Hyperedge Temporal Point Process (RRHyperTPP), uses an encoder that learns a dynamic node representation based on the historical interaction patterns.<n>We develop a noise contrastive estimation method to learn the parameters of our model, and we have experimentally shown that our models perform better than previous state-of-the-art methods for interaction forecasting.
  arXiv  Detail & Related papers  (2024-04-27T15:46:54Z)
• Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking [61.69892497726235]
  Composite Node Message Passing Network (CoNo-Link) is a framework for modeling ultra-long frames information for association. In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction. Our model can learn better predictions on longer-time scales by adding composite nodes.
  arXiv  Detail & Related papers  (2023-12-14T14:00:30Z)
• Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling [67.94143911629143]
  We propose a generative Transformer VAE architecture to model hand pose and action. To faithfully model the semantic dependency and different temporal granularity of hand pose and action, we decompose the framework into two cascaded VAE blocks. Results show that our joint modeling of recognition and prediction improves over isolated solutions.
  arXiv  Detail & Related papers  (2023-11-29T05:28:39Z)
• Mending of Spatio-Temporal Dependencies in Block Adjacency Matrix [3.529869282529924]
  We propose a novel end-to-end learning architecture designed to mend the temporal dependencies, resulting in a well-connected graph. Our methodology demonstrates superior performance on benchmark datasets, such as SurgVisDom and C2D2.
  arXiv  Detail & Related papers  (2023-10-04T06:42:33Z)
• Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation [47.7036344302777]
  Current Object Video reference methods follow the pipeline of extraction-then-matching.<n>We propose a unified VOS framework, coined as JointFormer, for jointly feature modeling, correspondence, and a compressed memory.
  arXiv  Detail & Related papers  (2023-08-25T17:30:08Z)
• Taming Local Effects in Graph-based Spatiotemporal Forecasting [28.30604130617646]
  Stemporal graph neural networks have shown to be effective in time series forecasting applications. This paper aims to understand the interplay between globality and locality in graph-basedtemporal forecasting. We propose a methodological framework to rationalize the practice of including trainable node embeddings in such architectures.
  arXiv  Detail & Related papers  (2023-02-08T14:18:56Z)
• Neural Temporal Point Processes for Forecasting Directional Relations in Evolving Hypergraphs [10.803714426078642]
  We provide a comprehensive solution to the problem of forecasting directional relations in a general setting.<n>The number of possible hyperedges is exponential in the number of nodes at each event time.<n>We propose a sequential generative approach that segments the forecasting process into multiple stages.
  arXiv  Detail & Related papers  (2023-01-28T14:32:14Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning [87.38675639186405]
  We propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs.
  arXiv  Detail & Related papers  (2021-05-17T15:33:25Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)
• Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency [6.019104024723682]
  This research studies two particular problems in traffic forecasting: (1) capture the dynamic and non-local spatial correlation between traffic links and (2) model the dynamics of temporal dependency for accurate multiple steps ahead predictions. We propose a deep learning framework named Spatial-Temporal Sequence to Sequence model (STSeq2Seq) to address these issues. This model builds on sequence to sequence (seq2seq) architecture to capture temporal feature and relies on graph convolution for aggregating spatial information.
  arXiv  Detail & Related papers  (2020-04-06T03:40:56Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

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.