Differences

This shows you the differences between two versions of the page.

@@ Line 1: / Line 1: @@
+===== Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs =====
+{{ ar.png?250}}
+//Abstract//: Dot product embeddings take a graph and construct vectors for nodes such that dot products
+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, allow for multiple notions of
+nearest neighbors each with their own interpretation, and can be ‘slotted’ into existing models
+such as exponential family embeddings or graph
+neural networks for better link prediction.
+<box 99% orange>
+Alexander Peysakhovich and Leon Bottou:  **Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs**,  //arXiv preprint arXiv:2106.09671//, 2021.
+[[http://leon.bottou.org/publications/djvu/peysakhovich-ar-2022.djvu|peysakhovich-ar-2022.djvu]]
+[[http://leon.bottou.org/publications/pdf/peysakhovich-ar-2022.pdf|peysakhovich-ar-2022.pdf]]
+[[http://leon.bottou.org/publications/psgz/peysakhovich-ar-2022.ps.gz|peysakhovich-ar-2022.ps.gz]]
+</box>
+  @article{peysakhovich-2022,
+    title = {Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs},
+    author = {Peysakhovich, Alexander and Bottou, Leon},
+    journal = {arXiv preprint arXiv:2106.09671},
+    year = {2021},
+    url = {http://leon.bottou.org/papers/peysakhovich-2022},
+  }

User Tools

Site Tools

Differences

Page Tools