English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph Representation Learning (GRL) methods have impacted fields fromchemistry to social science. However, their algorithmic implementations arespecialized to specific use-cases e.g.message passing methods are rundifferently from node embedding ones. Despite their apparent differences, allthese methods utilize the graph structure, and therefore, their learning can beapproximated with stochastic graph traversals. We propose Graph Traversal viaTensor Functionals(GTTF), a unifying meta-algorithm framework for easing theimplementation of diverse graph algorithms and enabling transparent andefficient scaling to large graphs. GTTF is founded upon a data structure(stored as a sparse tensor) and a stochastic graph traversal algorithm(described using tensor operations). The algorithm is a functional that accepttwo functions, and can be specialized to obtain a variety of GRL models andobjectives, simply by changing those two functions. We show for a wide class ofmethods, our algorithm learns in an unbiased fashion and, in expectation,approximates the learning as if the specialized implementations were rundirectly. With these capabilities, we scale otherwise non-scalable methods toset state-of-the-art on large graph datasets while being more efficient thanexisting GRL libraries - with only a handful of lines of code for each methodspecialization. GTTF and its various GRL implementations are on:https://github.com/isi-usc-edu/gttf.

Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning