Memory and Capacity of Graph Embedding Methods
Frank Qiu
TL;DR
This paper investigates the memory requirements and capacity limits of various graph embedding methods, aiming to understand their effectiveness and scalability in representing graph structures.
Contribution
It introduces a comprehensive analysis of the memory and capacity constraints of existing graph embedding techniques, providing new theoretical insights.
Findings
Identifies key factors affecting embedding capacity
Provides bounds on memory usage for different methods
Suggests improvements for scalable graph representations
Abstract
THIS PAPER IS NOW DEFUNCT: Check out "Graph Embeddings via Tensor Products and Approximately Orthonormal Codes", where it has been combined into one paper.
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParallel Computing and Optimization Techniques · Quantum Computing Algorithms and Architecture · Tensor decomposition and applications