A library to generate explanations of recommendations generated by GNNs.
Project description
GNNUERS generates explanations in the form of user-item interactions that make a GNN-based recommender system favor a demographic group over another. GNNUERS learns a perturbation vector that modifies the adjacency matrix representing the training network. The edges modified by the perturbation vector are the explanations genereated by the framework. GNNUERS then needs to work on a slight extended version of a recommender system in order to include the perturbation vector and optimize it.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gnnuers-0.0.3a0.tar.gz
(93.9 kB
view details)
File details
Details for the file gnnuers-0.0.3a0.tar.gz.
File metadata
- Download URL: gnnuers-0.0.3a0.tar.gz
- Upload date:
- Size: 93.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
76ccbc51ffec354e25d3a3f9d7a80ce5306f680e2504ad9c00e5faee5a91b2b4
|
|
| MD5 |
8d30ef52c846179601999abdcfce494a
|
|
| BLAKE2b-256 |
601793d211cffcc2ae86c7a944b4c0c1ddc02095b825bd43164e3611c27ed9d2
|
