This shows you the differences between two versions of the page.
— |
papers:peysakhovich-2022 [2023/08/29 05:59] (current) leonb created |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ===== Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs ===== | ||
+ | {{ ar.png? | ||
+ | |||
+ | // | ||
+ | between two vectors give the strength of the edge. | ||
+ | Dot products make a strong transitivity assumption, however, many important forces generating | ||
+ | graphs in the real world lead to non-transitive | ||
+ | relationships. We remove the transitivity assumption by embedding nodes into a pseudo-Euclidean | ||
+ | space - giving each node an attract and a repel | ||
+ | vector. The inner product between two nodes is | ||
+ | defined by taking the dot product in attract vectors | ||
+ | and subtracting the dot product in repel vectors. | ||
+ | Pseudo-Euclidean embeddings can compress networks efficiently, | ||
+ | nearest neighbors each with their own interpretation, | ||
+ | such as exponential family embeddings or graph | ||
+ | neural networks for better link prediction. | ||
+ | |||
+ | <box 99% orange> | ||
+ | Alexander Peysakhovich and Leon Bottou: | ||
+ | |||
+ | [[http:// | ||
+ | [[http:// | ||
+ | [[http:// | ||
+ | </ | ||
+ | |||
+ | @article{peysakhovich-2022, | ||
+ | title = {Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs}, | ||
+ | author = {Peysakhovich, | ||
+ | journal = {arXiv preprint arXiv: | ||
+ | year = {2021}, | ||
+ | url = {http:// | ||
+ | } |