Giter VIP home page Giter VIP logo

confgcn's Introduction

Confidence-based Graph Convolutional Networks for Semi-Supervised Learning

Source code for AISTATS 2019 paper: Confidence-based Graph Convolutional Networks for Semi-Supervised Learning.

Label prediction on node a by Kipf-GCN and ConfGCN (this paper). L0 is a’s true label. Shade intensity of a node reflects the estimated score of label L1 assigned to that node. Since Kipf-GCN is not capable of estimating influence of one node on another, it is misled by the dominant label L1 in node a’s neighborhood and thereby making the wrong assignment. ConfGCN, on the other hand, estimates confidences (shown by bars) over the label scores, and uses them to increase influence of nodes b and c to estimate the right label on a. Please refer to paper for more details.

Dependencies

  • Compatible with TensorFlow 1.x and Python 3.x.
  • Dependencies can be installed using requirements.txt.

Dataset:

  • We use citation network datasets: Cora, Citeseer, Pubmed, and CoraML for evaluation in our paper.
  • Cora, Citeseer, and Pubmed datasets was taken directly from here. CoraML dataset was taken from here and was placed in the same format as other datasets for semi-supervised settings.
  • data.zip contains all the datasets in the required format.

Evaluate pretrained model:

  • Run setup.sh for setting up the environment and extracting the datasets and pre-trained models.
  • confgcn.py contains TensorFlow (1.x) based implementation of ConfGCN (proposed method).
  • Execute evaluate.sh for evaluating pre-trained ConfGCN model on all four datasets.

Training from scratch:

  • Execute setup.sh for setting up the environment and extracting datasets.

  • config/hyperparams.jsoncontains the best parameters for all four datasets.

  • For training ConfGCN run:

    python conf_gcn.py -data citeseer -name new_run

Citation

Please cite us if you use this code.

@InProceedings{vashishth19a,
  title = 	 {Confidence-based Graph Convolutional Networks for Semi-Supervised Learning},
  author = 	 {Vashishth, Shikhar and Yadav, Prateek and Bhandari, Manik and Talukdar, Partha},
  booktitle = 	 {Proceedings of Machine Learning Research},
  pages = 	 {1792--1801},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Sugiyama, Masashi},
  volume = 	 {89},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {},
  month = 	 {16--18 Apr},
  publisher = 	 {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v89/vashishth19a/vashishth19a.pdf},
  url = 	 {http://proceedings.mlr.press/v89/vashishth19a.html}
}

For any clarification, comments, or suggestions please create an issue or contact [email protected].

confgcn's People

Contributors

svjan5 avatar parthatalukdar avatar manikbhandari avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.