TL;DR
Cleora introduces a scalable, unsupervised graph embedding algorithm that leverages iterative averaging of neighbor embeddings, achieving high-quality results faster than existing methods without complex optimization.
Contribution
The paper presents Cleora, a novel graph embedding scheme combining simplicity, scalability, and competitive quality, avoiding costly eigen-decomposition and contrastive learning frameworks.
Findings
Cleora produces embeddings comparable to contrastive methods on downstream tasks.
It runs faster than other CPU-based graph embedding algorithms.
Achieves rapid convergence in just a few iterations.
Abstract
The area of graph embeddings is currently dominated by contrastive learning methods, which demand formulation of an explicit objective function and sampling of positive and negative examples. This creates a conceptual and computational overhead. Simple, classic unsupervised approaches like Multidimensional Scaling (MSD) or the Laplacian eigenmap skip the necessity of tedious objective optimization, directly exploiting data geometry. Unfortunately, their reliance on very costly operations such as matrix eigendecomposition make them unable to scale to large graphs that are common in today's digital world. In this paper we present Cleora: an algorithm which gets the best of two worlds, being both unsupervised and highly scalable. We show that high quality embeddings can be produced without the popular step-wise learning framework with example sampling. An intuitive learning objective of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsContrastive Learning
