Node Embeddings and Exact Low-Rank Representations of Complex Networks

Abstract

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.

PDF NeurIPS Semantic Scholar

Cite

Text

Chanpuriya et al. "Node Embeddings and Exact Low-Rank Representations of Complex Networks." Neural Information Processing Systems, 2020.

Markdown

[Chanpuriya et al. "Node Embeddings and Exact Low-Rank Representations of Complex Networks." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/chanpuriya2020neurips-node/)

BibTeX

@inproceedings{chanpuriya2020neurips-node,
  title     = {{Node Embeddings and Exact Low-Rank Representations of Complex Networks}},
  author    = {Chanpuriya, Sudhanshu and Musco, Cameron and Sotiropoulos, Konstantinos and Tsourakakis, Charalampos},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/chanpuriya2020neurips-node/}
}