mlsanityData to 14 Oct 2026

Academic Network Representation via Prediction-Sampling Incorporated Tensor Factorization

arXiv 2504.08323 ↗First posted 11 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 89 references that are in the map. First posted on arXiv 11 Apr 2025.

Builds on

20 of 89 references.

References · 20

  1. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  2. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  3. 2019Heterogeneous Graph Attention Networkcited by 734
  4. 2015LINE: Large-scale Information Network Embeddingcited by 582
  5. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  6. 2017Heterogeneous Information Network Embedding for Recommendationcited by 133
  7. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  8. 2018Tensor Robust Principal Component Analysis with A New Tensor Nuclear Normcited by 112
  9. 2017Network Representation Learning: A Surveycited by 101
  10. 2022Hypergraph Contrastive Collaborative Filteringcited by 63
  11. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  12. 2023HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformercited by 35
8 more
  1. 2022Self-Supervised Hypergraph Transformer for Recommender Systemscited by 32
  2. 2022DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priorscited by 15
  3. 2022MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filteringcited by 11
  4. 2023Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Networkcited by 6
  5. 2021Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networkscited by 4
  6. 2018QANet: Tensor Decomposition Approach for Query-based Anomaly Detection in Heterogeneous Information Networkscited by 2
  7. 2019BHIN2vec: Balancing the Type of Relation in Heterogeneous Information Networkcited by 2
  8. 2024An Adaptive Latent Factorization of Tensors Model for Embedding Dynamic Communication Networkcited by 1

Built on by

Not cited yet.