通过预测采样增强张量分解，提升不完整学术网络的表示学习能力。
Academic Network Representation via Prediction-Sampling Incorporated Tensor Factorization
- 构建分层张量分解架构，捕捉学术网络的多层级特征。
- 引入非线性预测采样策略，逐层生成新数据以补全缺失关系。
- 在三个真实数据集上显著优于现有模型，适合关系预测任务。
准确表示学术网络对科研影响力预测等关系挖掘至关重要。现有的张量潜在因子分解（LFT）模型虽有效，但面对高维且不完整的学术网络（HDI）时表现受限。本文提出预测采样式张量分解（PLFT）模型，包含两个核心思想：1）设计级联式LFT架构，通过学习网络的分层特征提升表示能力；2）引入融合非线性激活的预测-采样策略，逐层生成新网络数据以更精准地补全缺失关系。在三个真实学术网络数据集上的实验表明，该模型在预测未探索关系方面优于现有方法。
原文摘要 · Abstract (English)
Accurate representation to an academic network is of great significance to academic relationship mining like predicting scientific impact. A Latent Factorization of Tensors (LFT) model is one of the most effective models for learning the representation of a target network. However, an academic network is often High-Dimensional and Incomplete (HDI) because the relationships among numerous network entities are impossible to be fully explored, making it difficult for an LFT model to learn accurate representation of the academic network. To address this issue, this paper proposes a Prediction-sampling-based Latent Factorization of Tensors (PLFT) model with two ideas: 1) constructing a cascade LFT architecture to enhance model representation learning ability via learning academic network hierarchical features, and 2) introducing a nonlinear activation-incorporated predicting-sampling strategy to more accurately learn the network representation via generating new academic network data layer by layer. Experimental results from the three real-world academic network datasets show that the PLFT model outperforms existing models when predicting the unexplored relationships among network entities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。