You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
PyTorch implementation of the paper "Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities". IJCAI2019.
The implementation is based on SIPS, see also the implementation of the AISTATS-19 paper "Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability".
Some of the code is also based on Facebook's poincare-embeddings, see also their implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations".
If you find this code useful for your research, please cite the following paper in your publication:
@inproceedings{ijcai2019-699,
title = {Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities},
author = {Kim, Geewook and Okuno, Akifumi and Fukui, Kazuki and Shimodaira, Hidetoshi},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI-19}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
pages = {5031--5038},
year = {2019},
month = {7},
doi = {10.24963/ijcai.2019/699},
url = {https://doi.org/10.24963/ijcai.2019/699},
}
PyTorch implementation of the paper "Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities". IJCAI2019.