exact-embeddings
Demo of an LPCA algorithm for exact low-dimensional representations of networks
view repo
Low-dimensional embeddings, from classical spectral embeddings to modern neural-net-inspired methods, are a cornerstone in the modeling and analysis of complex networks. Recent work by Seshadhri et al. (PNAS 2020) suggests that such embeddings cannot capture local structure arising in complex networks. In particular, they show that any network generated from a natural low-dimensional model cannot be both sparse and have high triangle density (high clustering coefficient), two hallmark properties of many real-world networks. In this work we show that the results of Seshadhri et al. are intimately connected to the model they use rather than the low-dimensional structure of complex networks. Specifically, we prove that a minor relaxation of their model can generate sparse graphs with high triangle density. Surprisingly, we show that this same model leads to exact low-dimensional factorizations of many real-world networks. We give a simple algorithm based on logistic principal component analysis (LPCA) that succeeds in finding such exact embeddings. Finally, we perform a large number of experiments that verify the ability of very low-dimensional embeddings to capture local structure in real-world networks.
READ FULL TEXT
Low-dimensional node embeddings play a key role in analyzing graph datas...
read it
The study of complex networks is a significant development in modern sci...
read it
We consider constraint-based methods for causal structure learning, such...
read it
How can we effectively encode evolving information over dynamic graphs i...
read it
The skip-gram model for learning word embeddings (Mikolov et al. 2013) h...
read it
Low-dimensional embedding techniques such as tSNE and UMAP allow visuali...
read it
We consider the problem of interpretable network representation learning...
read it
Demo of an LPCA algorithm for exact low-dimensional representations of networks
Comments
There are no comments yet.