Corpus ID: 231979264

Privacy-Preserving Graph Convolutional Networks for Text Classification

@article{Igamberdiev2021PrivacyPreservingGC,
  title={Privacy-Preserving Graph Convolutional Networks for Text Classification},
  author={Timour Igamberdiev and Ivan Habernal},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.09604}
}
Graph convolutional networks (GCNs) are a 001 powerful architecture for representation learn002 ing on documents that naturally occur as 003 graphs, e.g., citation or social networks. How004 ever, sensitive personal information, such as 005 documents with people’s profiles or relation006 ships as edges, are prone to privacy leaks, 007 as the trained model might reveal the orig008 inal input. Although differential privacy 009 (DP) offers a well-founded privacy-preserving 010 framework, GCNs pose… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 53 REFERENCES
When Differential Privacy Meets Graph Neural Networks
Inductive Representation Learning on Large Graphs
How Powerful are Graph Neural Networks?
Towards Differentially Private Text Representations
Question Answering by Reasoning Across Documents with Graph Convolutional Networks
Privacy-preserving Neural Representations of Text
Using word embeddings to improve the privacy of clinical notes
...
1
2
3
4
5
...