Computationally Tractable Riemannian Manifolds for Graph Embeddings

Authors: Calin Cruceru, Gary Becigneul, Octavian-Eugen Ganea7133-7141

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we demonstrate consistent improvements over Euclidean geometry while often outperforming hyperbolic and elliptical embeddings based on various metrics that capture different graph properties. Our results serve as new evidence for the benefits of non-Euclidean embeddings in machine learning pipelines.
Researcher Affiliation Collaboration 1 Department of Computer Science, ETH Z urich, Switzerland 2 Computer Science and Artificial Intelligence Lab, MIT, USA
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described.
Open Datasets Yes Facebook (Leskovec and Mcauley 2012) used in our experiments. It shows the Ollivier-Ricci curvatures of edges and their averages for nodes. More such drawings are included in Appendix H. (...) We embed several graphs with traits associated with positive curvature in Grassmann manifolds and compare them to spherical embeddings. Table 3 shows that the former yields non-negligibly lower average distortion on the cat-cortex dissimilarity dataset (Scannell, Blakemore, and Young 1995)
Dataset Splits No The paper does not specify exact training/validation/test splits, percentages, or absolute sample counts for the datasets used.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions using
Experiment Setup No The paper mentions optimizing embeddings for