A Deep Embedding Model for Co-occurrence Learning

  title={A Deep Embedding Model for Co-occurrence Learning},
  author={Y. Shen and R. Jin and J. Chen and X. He and Jianfeng Gao and Li Deng},
  journal={2015 IEEE International Conference on Data Mining Workshop (ICDMW)},
  • Y. Shen, R. Jin, +3 authors Li Deng
  • Published 2015
  • Computer Science, Mathematics
  • 2015 IEEE International Conference on Data Mining Workshop (ICDMW)
Co-occurrence Data is a common and important information source in many areas, such as the word co-occurrence in the sentences, friends co-occurrence in social networks and products co-occurrence in commercial transaction data, etc, which contains rich correlation and clustering information about the items. In this paper, we study co-occurrence data using a general energy-based probabilistic model, and we analyze three different categories of energy-based model, namely, the L1, L2 and Lk models… Expand
5 Citations
Incorporating pre-training in long short-term memory networks for tweet classification
  • 7
Incorporating Pre-Training in Long Short-Term Memory Networks for Tweets Classification
  • 7
  • PDF
Computation of heterogeneous object co-embeddings from relational measurements
  • 2
  • PDF
Survey on Recommender System Using Deep Learning Networks
Harnessing search engine optimization experience to enhance the visibility of websites
  • 1
  • PDF


Statistical Models for Co-occurrence Data
  • 185
  • PDF
Learning word embeddings efficiently with noise-contrastive estimation
  • 463
  • PDF
Visualizing Data using t-SNE
  • 16,312
  • PDF
Latent Dirichlet Allocation
  • 26,331
  • Highly Influential
  • PDF
Learning personal + social latent factor model for social recommendation
  • 86
  • PDF
Euclidean Embedding of Co-occurrence Data
  • 226
  • PDF
Three new graphical models for statistical language modelling
  • 571
  • Highly Influential
  • PDF
A Connection Between Score Matching and Denoising Autoencoders
  • 259
  • PDF
Minimum Probability Flow Learning
  • 59
  • PDF
Modeling High-Dimensional Discrete Data with Multi-Layer Neural Networks
  • 111
  • PDF