HierCas: Hierarchical Temporal Graph Attention Networks for Popularity Prediction in Information Cascades

• URL: http://arxiv.org/abs/2310.13219v2
• Date: Sat, 27 Apr 2024 07:07:20 GMT
• Title: HierCas: Hierarchical Temporal Graph Attention Networks for Popularity Prediction in Information Cascades
• Authors: Zhizhen Zhang, Xiaohui Xie, Yishuo Zhang, Lanshan Zhang, Yong Jiang,
• Abstract summary: Information cascade popularity prediction is critical for many applications, including but not limited to identifying fake news and accurate recommendations. Traditional feature-based methods rely on handcrafted features, which are domain-specific and lack generalizability to new domains. We propose Hierarchical Temporal Graph Attention Networks for cascade popularity prediction (HierCas), which operates on the entire cascade graph by a dynamic graph modeling approach.
• Score: 25.564185461383655
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Information cascade popularity prediction is critical for many applications, including but not limited to identifying fake news and accurate recommendations. Traditional feature-based methods heavily rely on handcrafted features, which are domain-specific and lack generalizability to new domains. To address this problem, researchers have turned to neural network-based approaches. However, most existing methods follow a sampling-based modeling approach, potentially losing continuous dynamic information that emerges during the information diffusion process. In this paper, we propose Hierarchical Temporal Graph Attention Networks for cascade popularity prediction (HierCas), which operates on the entire cascade graph by a dynamic graph modeling approach. By leveraging time-aware node embedding, graph attention mechanisms, and hierarchical pooling structures, HierCas effectively captures the popularity trend implicit in the complex cascade. Extensive experiments conducted on two real-world datasets in different scenarios demonstrate that our HierCas significantly outperforms the state-of-the-art approaches. We have released our code at https://github.com/Daisy-zzz/HierCas.

Related papers

• On Your Mark, Get Set, Predict! Modeling Continuous-Time Dynamics of Cascades for Information Popularity Prediction [5.464598715181046]
  Key to accurately predicting information popularity lies in subtly modeling the underlying temporal information diffusion process. We propose ConCat, modeling the Continuous-time dynamics of Cascades for information popularity prediction. We conduct extensive experiments to evaluate ConCat on three real-world datasets.
  arXiv  Detail & Related papers  (2024-09-25T05:08:44Z)
• Hierarchical Information Enhancement Network for Cascade Prediction in Social Networks [51.54002032659713]
  We propose a novel Hierarchical Information Enhancement Network (HIENet) for cascade prediction. Our approach integrates fundamental cascade sequence, user social graphs, and sub-cascade graph into a unified framework.
  arXiv  Detail & Related papers  (2024-03-22T14:57:27Z)
• Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction [12.645792211510276]
  We propose an explicit Time embedding based Cascade Attention Network (TCAN) as a novel popularity prediction architecture for large-scale information networks. TCAN integrates temporal attributes into node features via a general time embedding approach (TE), and then employs a cascade graph attention encoder (CGAT) and a cascade sequence attention encoder (CSAT) to fully learn the representation of cascade graphs and cascade sequences.
  arXiv  Detail & Related papers  (2023-08-19T10:43:11Z)
• AoI-based Temporal Attention Graph Neural Network for Popularity Prediction and Content Caching [9.16219929722585]
  Information-centric network (ICN) aims to proactively keep limited popular content at the edge of network based on predicted results. In this paper, we leverage an effective dynamic graph neural network (DGNN) to jointly learn the structural and temporal patterns embedded in the bipartite graph. We also propose an age of information (AoI) based attention mechanism to extract valuable historical information.
  arXiv  Detail & Related papers  (2022-08-18T02:57:17Z)
• A Graph-Enhanced Click Model for Web Search [67.27218481132185]
  We propose a novel graph-enhanced click model (GraphCM) for web search. We exploit both intra-session and inter-session information for the sparsity and cold-start problems.
  arXiv  Detail & Related papers  (2022-06-17T08:32:43Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Temporal Graph Network Embedding with Causal Anonymous Walks Representations [54.05212871508062]
  We propose a novel approach for dynamic network representation learning based on Temporal Graph Network. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. We show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks.
  arXiv  Detail & Related papers  (2021-08-19T15:39:52Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)
• CasGCN: Predicting future cascade growth based on information diffusion graph [5.925905552955426]
  We propose a novel deep learning architecture for cascade growth prediction, called CasGCN. It employs the graph convolutional network to extract structural features from a graphical input, followed by the application of the attention mechanism. We conduct experiments on two real-world cascade growth prediction scenarios.
  arXiv  Detail & Related papers  (2020-09-10T21:20:09Z)
• GCN for HIN via Implicit Utilization of Attention and Meta-paths [104.24467864133942]
  Heterogeneous information network (HIN) embedding aims to map the structure and semantic information in a HIN to distributed representations. We propose a novel neural network method via implicitly utilizing attention and meta-paths. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation.
  arXiv  Detail & Related papers  (2020-07-06T11:09:40Z)

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.