Give Me Some SALT: Structure-Aware Link Modeling for Temporal Weighted Link Prediction

In dynamic graph analysis, research has predominantly focused on temporal link prediction (TLP) for unweighted links, with growing interest in predicting temporal link weights in recent years. Temporal weighted link prediction (TWLP) aims to estimate both the existence and the link weights, which is naturally formulated as a regression task. The long-tail distribution and short-term randomness of link weights pose significant challenges for TWLP. In this paper, we introduce SALT, a Structure-Aware Link modeling for Temporal weighted link prediction, which consists of Weighted Link Encoder (WLE) and Temporal Link State Space Module (TLSSM). WLE encodes each snapshot into link-centric embeddings with common neighbor information, and addresses the long-tail issue by leveraging weights to adjust the embedding distribution. Additionally, TLSSM is designed to handle short-term randomness in temporal modeling. On eight datasets, our model achieves average reductions of 19.86% in RMSE and 24.61% in MAE compared to state-of-the-art baselines.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3746252.3760991
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Learning the long-tail distribution in latent space for Weighted Link Prediction via conditional Invertible Neural Networks

  2024cited by this paper
• PointMamba: A Simple State Space Model for Point Cloud Analysis

  2024cited by this paper
• State Space Models on Temporal Graphs: A First-Principles Study

  2024cited by this paper
• Line Graph Neural Networks for Link Weight Prediction

  2023cited by this paper
• Pure Message Passing Can Estimate Common Neighbor for Link Prediction

  2023cited by this paper
• WinGNN: Dynamic Graph Neural Networks with Random Gradient Aggregation Window

  2023cited by this paper
• Neural Common Neighbor with Completion for Link Prediction

  2023cited by this paper
• Link and edge weight prediction in air transport networks—An RNN approach

  2023cited by this paper
• High-Quality Temporal Link Prediction for Weighted Dynamic Graphs via Inductive Embedding Aggregation

  2023cited by this paper
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces

  2023cited by this paper
• Temporal and Topological Augmentation-based Cross-view Contrastive Learning Model for Temporal Link Prediction

  2023cited by this paper
• Unidirectional and bidirectional LSTM models for edge weight predictions in dynamic cross-market equity networks

  2022cited by this paper
• LWP-WL: Link weight prediction based on CNNs and the Weisfeiler-Lehman algorithm

  2022cited by this paper
• Efficiently Modeling Long Sequences with Structured State Spaces

  2021cited by this paper
• STGSN - A Spatial-Temporal Graph Neural Network framework for time-evolving social networks

  2021influential reference
• An Advanced Deep Generative Framework for Temporal Link Prediction in Dynamic Networks

  2020cited by this paper
• GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks

  2019cited by this paper
• Graph regularization weighted nonnegative matrix factorization for link prediction in weighted complex network

  2019cited by this paper
• EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

  2019cited by this paper
• E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction

  2019cited by this paper
• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Deep Dynamic Network Embedding for Link Prediction

  2018cited by this paper
• Link Prediction Based on Graph Neural Networks

  2018cited by this paper
• GC-LSTM: graph convolution embedded LSTM for dynamic network link prediction

  2018cited by this paper
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning

  2018cited by this paper
• Can co-location be used as a proxy for face-to-face contacts?

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Link prediction in weighted networks via structural perturbations

  2017cited by this paper
• Xception: Deep Learning with Depthwise Separable Convolutions

  2016cited by this paper
• Semi-Supervised Classification with Graph Convolutional Networks

  2016cited by this paper
• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  2014cited by this paper
• Link prediction in weighted networks: The role of weak ties

  2010cited by this paper
• Finding and evaluating community structure in networks.

  2003cited by this paper

• No citing papers are available for this paper.