LASAGNE: Locality and Structure Aware Graph Node Embedding
By Evgheniy Faerman, Felix Borutta, Kimon Fountoulakis, Michael W. Mahoney. 2017
18 citations recorded by the source corpus.
In this work we propose LASAGNE, a methodology to learn locality and structure aware graph node embeddings in an unsupervised way. In particular, we show that the performance of existing random-walk based approaches depends strongly on the structural properties of the graph, e.g., the size of the graph, whether the graph has a flat or upward-sloping Network Community Profile (NCP), whether the graph is expander-like, whether the classes of interest are more k-core-like or more peripheral, etc. For larger graphs with flat NCPs that are strongly expander-like, existing methods lead to random walks that expand rapidly, touching many dissimilar nodes, thereby leading to lower-quality vector representations that are less useful for downstream tasks. Rather than relying on global random walks or neighbors within fixed hop distances, LASAGNE exploits strongly local Approximate Personalized PageRank stationary distributions to more precisely engineer local information into node embeddings. This leads, in particular, to more meaningful and more useful vector representations of nodes in poorly-structured graphs. We show that LASAGNE leads to significant improvement in downstream multi-label classification for larger graphs with flat NCPs and that it is comparable for smaller graphs with upward-sloping NCPs.
Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Kiran Koshy Thekumparampil
- Li-Jia Li
- Chong Wang
- Sewoong Oh
- Peter Kairouz
- Pramod Viswanath
- Jure Leskovec
- Song Han
In Molecular Biology
In Statistical and Nonlinear Physics
Citations in the corpus
- Attention-based Graph Neural Network for Semi-supervised Learning (2018, methodology): “DeepWalk [35] and node2vec [22] use random walks as skip-grams, LINE [40] uses local proximities, LASAGNE [18] uses the Personalized PageRank random walk.”