https://github.com/trangptm/Column_networks

Column Networks for Collective Classification: A novel deep learning model for collective classification in multi-relational domains
https://github.com/trangptm/Column_networks

Last synced: about 2 months ago
JSON representation

Column Networks for Collective Classification: A novel deep learning model for collective classification in multi-relational domains

• Host: GitHub
• URL: https://github.com/trangptm/Column_networks
• Owner: trangptm
• Created: 2016-11-10T05:17:20.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2016-11-22T03:36:43.000Z (about 8 years ago)
• Last Synced: 2024-08-05T10:10:40.785Z (5 months ago)
• Language: Python
• Homepage:
• Size: 13 MB
• Stars: 12
• Watchers: 3
• Forks: 7
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-graph-based-semi-supervised-learning - code

README

        
# Column_networks

A novel deep learning model for collective classification in multi-relational domains.

A machine learning model normally learns from data with an assumption that all the instances are iid. However, ignoring the dependency among instances may hurt the performance in many data. For example, in a citation network, two publications may be in the same category if one cites the other. Our work models multiple-type relations among instances in data using neural networks. This improves the classification performance in 3 networked datasets.

Link to the paper: https://arxiv.org/abs/1609.04508

See *training_instruction.txt* for running experiments